Maintworld 1/2020

1/2020 www.maintworld.com 

maintenance & asset management 

Rotating Equipment Services: 

A comprehensive, 

worry-free package p 8 

SELF-INFLICTED RELIABILITY PROBLEMS OF ROTATING MACHINERY PG 12 VIEWING MAINTENANCE AS A SYSTEM TO OPTIMIZE PERFORMANCE PG 40

Your best weapon against poor 

reliability is knowledge. 

You need knowledge. Your colleagues need knowledge. Techniques, 

solutions, strategy and the business case - it is all critical knowledge. 

MOBIUS CONNECT is your gateway to knowledge. Whether your 

focus is condition monitoring or the bigger picture of reliability 

improvement our websites, live events and worldwide communities 

provide easy access to the information you need. 

We invite you to be part of MOBIUS CONNECT. With MOBIUS 

CONNECT you can... 

• Learn and share 

• Customize your learning pathway 

• Continue your educational journey, live or online 

• Engage with industry leaders from around the world 

The #1 Worldwide Training Event 

Get hands-on learning experience, participate 

in interactive workshops, network with peers, 

talk with industry experts and see the latest 

technologies. 

Learn more at www.thecbmconference.com

Find 

Your 

Learning 

Path 

15,000+ 

Live Session Attendees 

1500+ 

Educational Videos 

and Articles 

600+ 

Contributors 

www.mobiusconnect.com

Break the Break/Fix Cycle 

Stop being reactive. Shift to a truly predictive maintenance model. Anticipate 

problems before they cause costly downtime, and keep your equipment 

and facilities running more efficiently than ever before. 

ICONICS’ Fault Detection and Diagnostics (FDD) technology significantly reduces costs and improves 

operational efficiency. It incorporates a standard library of fault rules that can be customized to predict 

equipment failures and advise personnel of preventive actions. It also digitizes the knowledge of your 

expert workers so even new technicians are able to leverage tried-and-true techniques for addressing the 

toughest issues. Evolve to a connected field service operation, where scheduling the right person to be in 

the right place at the right time happens without you having to lift a finger. 

Check out the 

solution video at: 

iconics.com/cfsvideo

Automatically Detect Faults 

ROI Typically Within 12 to 18 Months 

Library of Preconfigured Fault Rules 

Rich Visualization and Reporting 

Predict, Reduce, and Eliminate 

Equipment Downtime 

Reduce Maintenance and Determine 

Probable Causes

EDITORIAL 

The COVID-19 Crisis, 

a Maintainer’s View 

‘NOUS SOMMES EN GUERRE!’ I can’t state any 

better than the French President Emmanuel 

Macron, that humanity is currently at war with 

COVID-19. This type of lung infection is caused 

by the Severe Acute Respiratory Syndrome 

CoronaVirus 2 (SARS-CoV-2), which is spreading 

around the world after an initial outbreak in 

the Chinese Wuhan region in December 2019. 

Many governments are taking severe measures, 

including travel bans, school closures, lockdowns 

requiring people to stay at home, factory shutdowns, 

etc. The world economy has been impacted 

severely; stock markets colour deep red. I don’t 

need to explain to you that this situation is unprecedented. Let’s look at the current 

situation through the eyes of a maintenance, reliability and asset manager. 

Chronicle of a Problem Foretold 

Coronavirus infections have already been lurking for several years. Usually these 

viruses cause relatively mild symptoms, such as colds in winter and early spring. As 

a matter of fact, 5 to 10 percent of colds are caused by coronaviruses. But we knew 

from the 2002 SARS and 2012 MERS outbreaks, that coronaviruses could potentially 

become very dangerous. However, even after two major wake-up calls, policy 

makers and companies were still not willing to make the investment in preventative 

measures. We had plenty of time to develop medicines and vaccines to prevent 

today's outbreak, but it just did not happen. Sounds familiar, doesn’t it? How many 

times do maintainers need to remind upper management that it is better to prevent 

than to repent (= feel regret and remorse)? Also, the asset manager knows all 

too well that the risk of doing nothing needs to be incorporated into investment 

decisions. Unfortunately, this is often not the case. A small short-term gain usually 

wins over over long-term benefit. As a result, we now live in times of repent. 

System Overload 

The risk of developing a severe COVID-19 lung infection through the Coronavirus 

increases with age – for the geeks: it is a failure pattern B. Taking into account that 

in Europe 18 percent of the population is aged (compared to only three percent in 

Africa), hospitals are hit by an exponentially increasing number of patients. 

Just as technicians are firefighting an ever-increasing number of failures 

caused by overaged assets, doctors and nurses are overwhelmed by the huge demand 

on intensive care. Add to this the fact there is no proper treatment and it 

becomes clear we are headed for a complete health system overload. 

Valuable Assets Need to be Protected 

Just as it is the maintenance technicians that keep things running in a factory, it is 

the doctors and nurses (and hospital technicians) who are our most valuable assets 

at the front of the war against COVID-19. It goes without saying that, if we want to 

win the battle, we need to protect those doctors and nurses from being infected. 

Enter the facemasks. The global shortage of facemasks has revealed another major 

risk in today’s society. The relentless offshoring of manufacturing has led to very 

vulnerable global supply chains. If there is a single lesson to be learned from the current 

Corona Crises, then it is the fact that decision takers need to do more and better 

long-term thinking. All of us can help by making the right choices ourselves. 

Stay healthy! 

Wim Vancauwenberghe 

Maintenance Evangelist 

34 

A 

good root cause 

elimination program 

needs a process, practical 

training in critical 

thinking, and coordination 

and follow-up of actions. 

6 maintworld 1/2020

IN THIS ISSUE 1/2020 

20 

There 

are many ways Asset 

Performance Management 

(APM) 4.0 helps you gain 

insights from data and 

optimize asset performance. 

= 

46 

Chemicals plants often 

have plenty of good 

data on equipment 

performance and reliability. 

A predictivemaintenance 

program might be the worst 

way to use it. 

8 

Rotating Equipment Services: A 

comprehensive, worry-free package 

12 

16 

20 

24 

Self-Inflicted Reliability Problems of 

Rotating Machinery 

Cloud-Enabled, On-Premises, or 

Both? 

DATA IS ABUNDANT Insights and 

Actionable Information are Hard to 

Find 

Experience Feedback – Rotating 

Machinery 

28 

32 

34 

36 

38 

RESONANCE - The Hidden Threat 

How predictive maintenance 

enhances plant safety 

Root Cause of an Electrical Problem, 

Did You Find the Systematic 

Problem to Solve? 

The Day After Tomorrow in Asset 

Performance 

A standardised methodology with 

factory specific outcome Multi-site 

approach with VDMXL 

40 

43 

46 

48 

Viewing Maintenance as a System 

to Optimize Performance 

Use of High-speed Thermography 

in Laser High-temperature Capillary 

Gap Brazing 

Predictive Maintenance: The Wrong 

Solution to the Right Problem in 

Chemicals 

Industrial AI in Maintenance: False 

Hopes or Real ACHIEVEMENTS? 

Issued by Promaint (Finnish Maintenance Society), Messuaukio 1, 00520 Helsinki, Finland tel. +358 29 007 4570 

Publisher Omnipress Oy, Mäkelänkatu 56, 00510 Helsinki, tel. +358 20 6100, toimitus@omnipress.fi, www.omnipress.fi 

Editor-in-chief Nina Garlo-Melkas tel. +358 50 36 46 491, nina.garlo@omnipress.fi, Advertisements Kai Portman, Sales 

Director, tel. +358 358 44 763 2573, ads@maintworld.com Layout Menu Meedia, www.menuk.ee Subscriptions and 

Change of Address members toimisto@kunnossapito.fi, non-members tilaajapalvelu@media.fi Printed by Painotalo Plus 

Digital Oy, www.ppd.fi Frequency 4 issues per year, ISSN L 1798-7024, ISSN 1798-7024 (print), ISSN 1799-8670 (online). 

1/2020 maintworld 7

PARTNER ARTICLE 

Rotating Equipment Services: 

A comprehensive, worry-free package 

for pumps, turbines, compressors, etc. 

Many processing plants include rotating equipment that is in continual use and 

contributes significantly to the enterprise’s productivity. This equipment must be 

operated in a cost-effective manner and must not break down. To ensure this, 

Bilfinger offers rotating equipment services covering the entire lifecycle of the 

systems involved. A project currently underway at the fertilizer producer Yara 

Porsgrunn in Norway shows how this works in practice. 

BERNARDO SEQUEIRA, Business Development Rotating Equipment, Bilfinger SE; 

ØYSTEIN HALDORSEN, Department Manager, Rotating Machinery, Bilfinger Industrial Services Norway AS. 

BILFINGER’S NETWORK for the provision 

of rotating equipment services covers all 

of Europe and consists of several centers 

of competence; the intention is to 

further expand this network in future. 

It comprises a large number of technical 

specialists like engineers and technicians 

and allows Bilfinger’s national 

companies to share their expertise along 

with the experiences they have gained 

with regional particularities. Customers 

benefit from having a service provider on 

call who can offer all the required services 

from under one roof, across national 

boundaries and regardless of the type of 

machinery involved. Bilfinger aims to 

position itself as a complementary service 

provider alongside OEMs (original 

equipment manufacturers). 

The target industries in this context 

are chemical & petrochemical, oil & gas, 

as well as energy & utilities. Obviously, 

every plant features different types of 

equipment. Bilfinger has classified rotating 

equipment into two categories and 

has set up a center of competence for each 

one. The first is “heavy rotating equipment,” 

which includes turbomachinery, 

piston compressors as well as multistage 

high-pressure pumps and gear units. The 

second is “small rotating equipment,” 

which comprises standard pumps and 

drive motors. In all cases, Bilfinger provides 

end-to-end support specifically 

tailored to its customers’ needs, including 

manufacturer-independent consulting, 

installation and commissioning of new 

equipment; maintenance, repair and ongoing 

optimization during operation; as 

well as the final decommissioning. 

Investment phase, installation 

and commissioning 

The lifecycle of a piece of machinery 

essentially consists of four phases: Its 

initial acquisition in the investment 

phase, its installation and commissioning, 

the operating phase, and the final 

decommissioning. Each of these lifecycle 

phases is fully covered by Bilfinger’s rotating 

equipment services. 



During the investment phase, Bilfinger 

advises its customers as to which 

equipment will best suit their needs, 

while offering feasibility and engineering 

studies along with the planning to be 

submitted along with the building permit 

application. If so requested, Bilfinger 

can also provide the full range of asset 

management services for small rotating 

equipment. In this case, Bilfinger offers 

its customer an equipment-rental pool 

from which roughly 20,000 devices such 

as pumps, electric motors or frequency 

converters, etc. can be leased at reasonable 

cost. This ensures the highest possible 

level of availability, as do comprehensive 

support services for the repair 

or replacement of faulty devices – which 

can be provided in a matter of hours, depending 

on location. 

The arrangement offered by Bilfinger 

known as the “Value Performance 

Contract” is unique on the market. It 

offers customers a guarantee for a respective 

pump’s availability in return for 

Operating phase and 

decommissioning 

During the operating phase, Bilfinger’s 

task is to provide detailed maintenance 

services and regular repairs for the customer’s 

rotating equipment. Since these 

services are performed on a continual 

basis, any long or unexpected downtimes 

are prevented that potentially could result 

in huge losses of production. Upkeep 

and repair measures of a more extensive 

nature are planned far in advance and 

in constant coordination with the customer. 

This ensures that any protracted 

downtimes can be kept to a minimum. 

Likewise, the developments in the 

field of industrial automation (“Industry 

4.0”) are highly relevant to rotating 

equipment services, specifically when it 

comes to prescriptive maintenance. For 

example, vibration sensors can be used 

to monitor the status of rotating machines 

and to alert the competent maintenance 

team should the monitored parameters 

deviate from their target range. This 

allows the maintenance team to intervene 

promptly and head off any impending 

damage. One service Bilfinger Industrial 

Services Norway offers its customers is 

the evaluation of the vibration signals 

emitted by compressors and turbines. On 

that basis, irregular running noises are analyzed 

and attributed to a specific cause, 

so that appropriate action can be taken 

immediately if required. This type of status 

monitoring protects the machinery 

involved from unexpected breakdowns. 

In Germany, Bilfinger distributes a vibration 

sensor specifically developed for the 

monitoring of pumps, and also provides 

supervision and evaluation services. 

The optimization and modification of 

rotating equipment is another field that 

Bilfinger looks after. Here, the main objective 

is to realize potential energy-savings – 

a significant aspect given that energy consumption 

accounts for about 80 percent 

MANY PROCESSING PLANTS INCLUDE ROTATING 

EQUIPMENT THAT IS IN CONTINUAL USE AND CONTRIBUTES 

SIGNIFICANTLY TO THE ENTERPRISE’S PRODUCTIVITY. 

a fixed price, along with contractually 

assured, progressive reductions of the 

maintenance costs. Bilfinger delivers the 

desired rotating equipment and provides 

support services to ensure it continues 

to be functional over a longer term. 

of the lifecycle costs of many pumps. Up to 

60 percent of these costs potentially could 

be saved by adjusting the respective pump 

to run at its optimal operating point. 

Technicians from the Bilfinger network 

analyze the relevant systems and draw 

on their decades of experience to prepare 

and implement proposals for technical 

improvement. 

A case in practice: Yara 

Porsgrunn in Norway 

Depending on a customer’s requirements, 

each service will be provided by a specific 

team drawn from the network. In Norway, 

Bilfinger is in a unique position since the 

center of competence for heavy rotating 

equipment located there constitutes the 

largest trove of experience in both onshore 

and offshore services. One example 

is Yara Porsgrunn, a Norwegian fertilizer 

producer running four nitric acid plants, a 

key input material for fertilizer. These facilities 

are among the biggest of their kind 

in the world, with a total output capacity 

of 1.8 million tons per annum. Bilfinger’s 

task was to recondition a compressor 

train during a scheduled downtime, while 

concomitantly performing a chemical 



cleaning and oil-flush of the lubricating/ 

hydraulic system. The compressor train 

consists of a steam turbine, a centrifugal 

compressor, a gear unit, an axial compressor 

and an expander, all of which 

were coupled to a drive shaft. 

The biggest challenge in this case was 

to carry all out the activities simultaneously 

in order to keep the stop time as 

brief as possible. The work was performed 

by roughly 3 engineers and 50 

technicians supplied by Bilfinger, who 

worked as a team with Yara Porsgrunn 

with added assistance from MAN Energy 

Solutions as the OEM. A local Bilfinger 

workshop manufactured a number of 

replacement parts and was able to perform 

repairs on site. This was a significant 

advantage, since the delivery times 

of the OEM were too long. Thanks to 

Bilfinger’s seasoned experts, the project 

ran smoothly. Despite the unexpected 

discovery of worn-out parts, the scheduled 

downtime of three weeks was only 

slightly exceeded as a consequence of the 

flexible approach taken by Bilfinger and 

its technical expertise. 

Rotating equipment services in 

the future 

The end-to-end package offered by 

Bilfinger bundles all the required services 

under one roof, while leaving them customizable 

to each customer’s needs. The 

advantage this service delivers over OEMs 

is that it allows customers to obtain independent 

advice and to tap into expertise 

transcending that of any one manufacturer. 

Compared to its competitors in the 

field of rotating equipment, Bilfinger also 

is able to deliver a greater amount of qualified 

manpower. Roughly 200 technical 

specialists for heavy rotating equipment 

currently belong to the network. 

In other words, Bilfinger is in an 

excellent position to handle upcoming 

developments on the market, particularly 

in view of the fact that cooperation 

models will become increasingly important 

in future: Global customers are 

looking for providers who are able to 

offer services of consistently high quality 

across the globe, while ensuring that 

these services are steered centrally. The 

demand for the rotating equipment services 

offered by Bilfinger as a leading international 

industrial services provider 

is certain to grow steadily in the years 

to come – also because customers need 

to fill the prevailing shortfall in skilled 

personnel with the required expertise 

in rotating equipment. 


ASSET MANAGEMENT 

Self-Inflicted Reliability Problems 

of Rotating Machinery 

The root cause of poor reliability can come from many sources. You may 

experience reliability issues due to the age of your plant. Or perhaps poor design 

decisions were made. Or the original construction crew cared nothing for reliability. 

And there may be other reasons, outside of your control, that resulted in the 

reliability problems you experience today. 

IN ANY RELIABILITY IMPROVEMENT 

initiative, you will need to address 

these issues, but first, you need to address 

the self-inflicted reliability issues. 

“But we don't have self-inflicted reliability 

problems." 

It is a bitter pill to swallow, but yes, 

you do. But that is good news because 

it is much easier to deal with the selfinflicted 

root causes than the inherent 

reliability problems you adopted. 

What are self-inflicted 

reliability problems? 

In order to determine why equipment 

fails prematurely (or why you experience 

slowdowns, safety incidences, or quality 

problems), you could go through a 

detailed failure modes, effects, and criticality 

(FMECA) analysis process, or you 

could perform root cause failure analysis 

12 maintworld 1/2020 

JASON TRANTER, 

ARP-E/L, CMRP 

Mobius Institute 

(RCFA) after each failure occurs. Or you 

could learn from the experience gained 

at thousands of plants around the world 

and consider some of the most common 

root causes of equipment failure - we will 

focus on rotating machinery. 

The number three cause of 

reliability problems 

Let’s start with the most obvious problems 

and then we will work backward to 

their root causes. 

Most equipment, like motors, pumps, 

fans, compressors, and turbines, are 

designed to run for many, many years 

without unplanned downtime. Yes, they 

may have some components that wear 

out, but many of the components, such 

as the bearings and gears, are designed to 

give years of trouble-free operation. But 

that assumes that all of the parts were 

installed correctly, the components are 

precision-aligned, the bearings and gears 

are correctly lubricated, all fasteners are 

tightened to the correct tension, there 

is no resonance, belts are tightened to 

the correct tension, and the rotors are 

precision-balanced. 

And it assumes that the equipment 

is operated as per design. Pumps, for 

example, should be operated at their 

“best efficiency point.” 

What happens at your plant? Do these

The 

The 

The Uptimization 

Uptimization Experts. 

Experts. 

What does 

DOWNTIME 

mean to you? 

marshallinstitute.com 

marshallinstitute.com


root causes exist? If you are not sure, 

then they almost certainly do. 

We will now take a quick look at just 

a few of those areas so that you can see 

why seemingly minor issues cause such 

serious problems. 

Shaft alignment 

When two shafts are “collinear” (no 

angle or offset between their centerlines), 

it reduces the stress on the bearings, 

couplings, shafts, and the rest of 

the machine components. Research was 

performed that revealed that just 5/60 th 

of a degree of angular misalignment can 

halve the life of your bearings. 

If you use laser alignment with 

appropriate tolerances, and you remove 

soft foot in all its forms (base issues, pipestrain, 

etc.), then you will have eliminated 

a common root cause of failure. 

Balancing 

When you balance to ISO 21940-11 grade 

G 1.0, the cyclical forces on the bearings, 

shaft, and structure are minimized, and 

thus you gain greater reliability. If you 

do not have a balancing standard, then 

unbalance will be a root cause of failure. 

And if you wait until the unbalance 

generates “high” vibration, “forcing” 

you to perform corrective maintenance, 

then you will have reduced the life of the 

equipment and supporting structure. 

Why is that? The life of a bearing is 

inversely proportional to the cube of the 

load. That sounds very complicated, but 

an easier way to say it is that if you double 

the load, the life will be reduced to 

one-eighth (23). 

Therefore, while the rotor is out-ofbalance, 

the bearings are being stressed, 

and their life expectancy will be reduced. 

Misalignment also generates these forces, 

and that is why it must be minimized. 

The unbalance is also generating 

forces that stress the structure, potentially 

resulting in fatigue failure of the 

structure itself or its foundations. 

The unbalance forces are also amplified 

by resonance. The structure will 

“naturally” vibrate back-and-forth, or 

side-to-side, or in other ways at certain 

frequencies. If the vibration generated 

by unbalance (or misalignment, or 

pump-vane vibration, or other avoidable 

“forcing frequencies”) is close to one of 

these natural resonant frequencies, the 

motion will be amplified. That is not 

good for the machine or structure. 

Lubrication 

When you correctly lubricate bearings 

and gears, whether you use grease or 

oil, and that lubricant is free of contaminants, 

you will achieve maximum 

life. But if bearings are not adequately 

greased, their life will be reduced. If the 

oil is contaminated, or the viscosity is 

incorrect, or the additives are depleted, 

then the life of gears and bearings will be 

greatly reduced. 

Research was performed to determine 

which particles caused the greatest 

damage. It was not the 40 µm particles, 

or the 10 µm particles - it was the tiny 

“3-5 µm” particles. 

And you may think that if you can’t 

see the water in oil, then the oil must 

be fine. Sadly, that is not correct. By the 

time you can see the water, the life of the 

bearing has been reduced by 70 percent. 

We could continue the discussion, 

but suffice to say that there is a great deal 

we can do to avoid problems that arise 

due to imperfect maintenance and operating 

practices. 

The number two cause of 


It is one thing to understand all of the 

root causes we have just discussed – and 

there are many others – but it is another 

thing to be able to get approval to establish 

standards and purchase all of the 

tools, such as laser alignment systems, 

that enable the technicians and operators 

to do the job correctly. But owning 

the tools and having standard operating 

procedures will not solve the problem. 

The problem will only be solved when 

the maintenance technicians and operators 

want to use them properly, and they 

are given the time and encouragement to 

use them. 

So we will need to address the desire, 

i.e., the culture. Culture is the key to 

success. 

The number one cause of 


A strong case could be made that the root 

cause of all failures ultimately derives 

from the lack of senior management support 

for a culture that values reliability. 

Without their support, it will be impossible 

to change the culture and thus 

change behaviour. 

Just think of the initiative to improve 

safety at your plant. If senior management 

did not support it, do you think 

your plant would have made the gains 



that it has made? Senior management 

enabled people to be employed in safety 

roles, it invested in the training and tools, 

it agreed to signage that provided warning 

and feedback on progress, it stood 

strong when there were opportunities to 

cut corners that would risk safety, and it 

made it quite clear how important safety 

is to the future of the organization. (Well, 

I hope that is the case at your plant.) 

You need the same thing to happen 

with reliability improvement. 

Everyone within the organization 

needs to understand that reliability is 

critically important to the organization 

and that senior management will stand 

strong when shortcuts that compromise 

reliability are proposed. 

Therefore, you need to gain senior 

management support so you can change 

the culture and thus successfully implement 

a reliability improvement initiative 

that eliminates the self-inflicted root 

causes. 

But wait, is there more? 

Since we are discussing root causes, let’s 

consider the root cause of the lack of senior 

management support. Is it their fault 

for not appreciating the opportunity 

to improve reliability, or is it your fault 

because you have not presented the business 

case for reliability improvement? 

It is common for people to talk about 

the “commonsense” benefits of reliability 

improvement. It is also common 

for reliability and condition monitoring 

teams to assume that senior management 

appreciates the benefits of what 

they have achieved, without ever 

communicating the financial benefits 

of their actions. 

Therefore, perhaps the true root 

cause of poor reliability is the inability 

(or unwillingness) of reliability and 

condition monitoring team leaders to 

establish a business case, sell the business 

case, and continually communicate 

the value of the reliability improvement 

initiative. 

Where does condition 

monitoring fit into this? 

Many people will believe that if they 

have a condition monitoring program, 

the reliability will be optimized. Sadly, 

that is not true. Most faults detected are 

avoidable, and while it is important to 

get an early warning, it is much more important 

to avoid the problem in the first 

place. Condition monitoring can help by 

detecting the root causes of failure: misalignment, 

unbalance, lubrication issues, 

looseness, and so on. If those problems are 

cost-effectively nipped in the bud, then we 

will avoid future failures. 

Another way that condition monitoring 

can play an important role is by performing 

acceptance testing. As part of the 

purchase agreement, the condition monitoring 

specialists can perform tests to ensure 

the new or overhauled equipment is 

“defect-free.” You may be surprised at how 

many problems you bring into the plant. 

Learning more 

As you can imagine, there is a great 

deal more that could be said about all 

of these topics. In an attempt to clarify 

the process we are discussing in this 

article, we developed a process called 

Asset Reliability Transformation, or ART. 

You can learn more, without charge, at 

www.reliabilityconnect.com. 

Conclusion 

The condition monitoring group has an 

important role to play. Providing an 

early warning minimizes the impact of 

premature failure, and detecting and 

eliminating the root causes ensures that 

we achieve the greatest life and value 

from our precious assets. 

The reliability improvement team 

has an even more important role to play. 

Proactively eliminating the root causes 

of failure ensures there will be fewer 

failures. 

But trying to improve reliability 

without aligning every activity to the 

goals of the organization, and thus 

gaining support from senior management, 

which then drives the necessary cultural 

changes, will never achieve the true 

potential of the initiative. 

Asset Reliabiity 

Transformation. 

The Key to a 

Happy Life. 



Cloud-Enabled, 

On-Premises, 

or Both? 

Which Data Structure 

Works Best for 

Your Maintenance 

Operations? 

ICONICS develops automation software that visualizes, archives, analyzes, mobilizes, 

and cloud-enables organizations’ data. With the expansion of the Industrial Internet 

of Things (IIoT), the data processes involved in many automation-based capabilities 

can be performed either on-premises (as has traditionally been done by the 

majority of organizations worldwide) or via the cloud (which has increasingly and 

rapidly become a more attractive option). 

THERE ARE MULTIPLE reasons why organizations’ 

maintenance operations 

would select IIoT-integrated monitoring 

and control solutions. Among these are: 

• Reduced on-site hardware obsolescence 

• •Secure access across multiple 

locations 

• Expanded connectivity 

Reduced On-site Hardware 

Obsolescence 

A business starts or an organization 

forms. It begins to amass the equipment 

needed to perform its functions, as 


TOM BUCKLEY, 

IoT Business 

Development Manager, 

ICONICS 

well as the automation solutions it will 

deploy. Oftentimes, these same entities 

also begin their own maintenance operations 

in order to keep their hardware in 

good working condition. Just as a company/organization 

accumulates equipment 

to run the business itself, it also 

accumulates IT hardware (servers, PCs, 

networking equipment, etc.) that is used 

to perform related tasks (such as those 

critical to automation and maintenance 

operations). 

However, just like business-focused 

machinery (e.g., an aging piece of manufacturing 

equipment), an organization’s 

IT equipment can also start showing 

signs of aging. What may have been sufficient 

even just a few years ago may no 

longer be comparable to newer machines 

that can perform more advanced tasks. 

Organizations are now able to consider 

the costs associated with upgrading/


retrofitting/replacing their onsite IT 

machinery versus the cost of moving applications 

to the cloud, where the cloud 

service operators are responsible for 

agreed-upon performance of their equipment. 

Many customers of cloud service 

providers are able to take advantage of 

an increase in processor performance to 

be able to take care of the heavy lifting of 

such tasks as advanced data analytics or, 

specifically for maintenance operations, 

predictive maintenance / fault detection 

and diagnostics (FDD) applications. 

Cloud service customers also appreciate 

the increase in capacity for rapid big data 

storage and retrieval. 

There are even ways for existing production 

equipment to take advantage of 

the cloud. Even though newer modern 

equipment may come with the ability 

to tie in directly to the IIoT, some older 

hardware can be used with emerging 

edge devices (IoT gateways) to make it 

easier and more cost-effective to become 

“cloud-enabled” instead of undergoing 

a full replacement. These gateways 

provide multiple other benefits, as well, 

including the integration of multiple 

devices, sensors, and other equipment to 

publish messages to the cloud independently 

from subscribers. Software modules 

built into such gateways decrease latency, 

provide edge data processing, and 

THERE ARE WAYS FOR 

EXISTING PRODUCTION 

EQUIPMENT TO TAKE 

ADVANTAGE OF THE CLOUD. 

empower edge analytics with onboard 

FDD and workflow technologies with 

real-time visualization of KPI data. 

Secure Access Across 

Multiple Locations 

Cloud security is accomplished by 

methods between both the applications 

themselves and the cloud service 

being used. For instance, this could be 

between the applications being accessed 

through an on-site edge device/IoT 

gateway and Microsoft Azure, to name 

one of many cloud services. Software, 

such as ICONICS IoTWorX, running 

on the IoT gateway can be provisioned 

and can communicate data securely via 

the Microsoft Azure IoT Hub, taking advantage 

of the inherent security features 

that come with an Azure subscription. 

Additionally, cloud-based automation 



(HMI/SCADA, historian, analytics, etc.) 

systems are backed up securely off site 

from where the data originates, keeping 

it safe from equipment damage or natural 

disasters. 

Such decentralized security measures 

are compelling for businesses/organizations 

that outgrow one central geographical 

location. Global enterprises, 

especially, see the benefits in trusting the 

security options provided through their 

cloud service providers and the integrated 

software that utilizes them. ICONICS 

IoTWorX, for instance, can connect multiple 

buildings, factories, and equipment 

through secure TLS encryption and popular 

cloud platforms, such as Microsoft 

Azure and Amazon Web Services. Data 

can be accessed from anywhere through 

a pub/sub architecture for real-time 

visualization of KPI data at the edge. 

IoTWorX delivers an efficient, secure 

connection to the cloud through bidirectional 

AMQP for Microsoft Azure, 

as well as MQTT, REST, and WebSockets 

for third-party cloud providers. 

Expanded Connectivity 

Another benefit of utilizing cloud-based 

automation solutions is that there is often 

an increase in the number of available 

communication protocols that can be 

used. This is in addition to the advanced 

security measures (bidirectional AMQP 

transport protocol [for Microsoft Azure] 

and MQTT, REST, and WebSockets [for 

third-party providers]) that cloud-based 

solutions provide. 

For maintenance operations, it’s definitely 

a benefit to be able to “talk to” as 

many of the machines within the organization 

as possible. As an example, ICON- 

ICS IoTWorX software is compatible 

with multiple standard communication 

protocols. These include protocols specific 

to plant floor applications; such as 

OPC Classic, OPC Unified Architecture 

(OPC UA), and Modbus; as well as those 

specific to building automation (BACnet) 

and IT hardware (SNMP). This provides 

users with the ability to communicate 

with a wider array of connected 

equipment, ultimately enabling users to 

better detect potential issues and utilize 

an organization’s data, wherever it might 

be created, transmitted, or stored. 

Cloud Contingencies 

For those concerned about the viability 

of cloud-based solutions during interruptions 

to internet service, there are 

measures that can be put into place to 

help ensure data doesn’t go missing or 

get corrupted. ICONICS has solutions 

that provide rapid data archiving and retrieval, 

including a "store-and-forward" 

feature that is useful when a network 

connection is unavailable; one specifically 

edge-based (IoT Hyper Collector) 

and the other traditionally on-premises 

or cloud-enabled (Hyper Historian). 

IoT Hyper Collector is part of IoT- 

WorX, the previously mentioned micro- 

SCADA software suite installed on a 

third-party IoT edge device. The collector 

has the ability to replay buffered 

data back locally, as well as to store and 

forward to the cloud when connectivity 

is present. For a more traditional 

on-premises approach, ICONICS Hyper 

Historian Collector also utilizes a similar 

store-and-forward feature. If a collector 

has lost connectivity to the logger, it will 

continue to buffer the data until connectivity 

is reestablished. 

Best of Both 

While the IoT Hyper Collector and 

Hyper Historian Collector are examples 

of how to retain data integrity both via 

the cloud and on-premises, respectively, 

there is nothing to prevent an organization 

from taking a hybrid approach. 

This bridges the gap between OT and 

IT and alleviates any "silo effect" of the 

organization’s data collection, storage, 

and retrieval. The same can be said for an 

organization’s entire automation solution 

and related data, as a whole. Some 

may benefit from a strictly cloud-based 

solution. Others may still have reason 

to remain with an entirely on-premises 

one. However, neither has any restriction 

towards using elements of the other 

in such a hybrid scenario. 

Each organization will make its own 

determination regarding what works 

best for their business processes and operations 

(cloud, on-premises, or hybrid), 

as well as to the automation software 

vendors that can best support it. 


YOUR PARTNER IN 

ULTRASOUND 

INSTRUMENTS 

Leak Detection 

Bearing Condition Monitoring 

Bearing Lubrication 

Steam Traps & Valves 

Electrical Inspection 

TRAINING 

CAT & CAT II Ultrasound Training 

Onsite Implementation Training 

Application Specific Training 

CONTINUOUS SUPPORT 

UE SYSTEMS 

Windmolen 20 

7609 NN Almelo 

The Netherlands 

T: +31 546 725 125 

E: info@uesystems.eu 

W: www.uesystems.eu 

Free support & license-free software 

Online Courses 

Free access to our Learning Center 

(webinars, articles, tutorials) 

CONTACT US FOR AN 

ONSITE DEMONSTRATION

DIGITALISATION 

DATA IS ABUNDANT 

Insights and Actionable 

Information are Hard to Find 

Plant Managers Can 

Improve Decision Making 

with Asset Performance 

Management 4.0 and 

Digital Twins 

SAVVY PLANT EXECUTIVES have noticeably 

changed how they approach topline 

revenue growth opportunities and 

bottom-line cost reductions. In assetintensive 

industries, digital advancement 

strategies like Asset Performance 

Management 4.0 and digital twins are 

becoming critical strategies for operational 

excellence. 

Within a plant, digital twins empower 

engineering, operations, and maintenance 

to collaborate and capitalize 

on the opportunity of Industry 4.0. If 

common pitfalls can be overcome, such 

as data overload, the lack of systems 

integration and interoperability, inconsistent 

business processes, and siloed 

data, then this open and connected data 

environment can become a sustainable 

competitive advantage. 

Maximizing the 

Value of Assets 

The reason plant staff collect, store, and 

analyze plant data is to improve decision-making 

and operations. Ultimately, 

they want to maximize the return on 

assets, minimize production, labor, and 

material costs, reduce the total cost of 

asset ownership and investment, and deliver 

predictable performance, on time. 

We can improve the performance of 

the physical assets used for production 

through the way people operate equipment, 

through improved maintenance 


SANDRA DIMATTEO 

Sandra DiMatteo is 

the Global Director 

of Marketing 

for Digital Twin 

Solutions, Asset and Network 

Performance at Bentley Systems. 

She has more than 20 years 

of experience in digitalization 

solutions in asset performance 

management and reliability 

software, asset lifecycle information 

management and EAM enterprise 

asset management operating in 

a connected data environment in 

energy and process industries, 

utilities and public infrastructure. She 

is an advocate and speaker on digital 

twins, IIoT analytics, AI and machine 

learning, BIM and asset management 

technology solutions. Sandra is on 

the Reliability Leadership Institute 

Board of Advisors and founded 

the Ontario Chapter of the Society 

of Maintenance and Reliability 

Professionals. 

practices, or through design and engineering. 

This is not a new concept, as an 

average plant might have 30 to 50 design 

optimizations, modifications, or additions 

per year. 

However, the siloed approach separating 

engineering, operations, and 

maintenance is no longer good enough. 

Success now requires a new way forward 

with a collaborative focus on asset health 

to attain performance targets. A reliability 

strategy actively resolves asset health 

shortcomings, leading to eliminating 

performance shortfalls. 

Asset Performance 

Management 

Asset Performance Management (APM) 

focuses on meeting performance requirements 

through reliability and takes 

a cross-discipline approach to fulfil plant 

goals and customer needs. Asset performance 

management is the plant manager’s 

opportunity to extend asset life 

safely and reliably, which avoids capital 

expenditures. 

Some of the key characteristics of an 

Asset Performance Management system 

include: 

• Asset strategy and risk analysis 

• Condition-based or reliability 

centered maintenance processes 

and practices 

• A mobile inspection platform with 

augmented reality and virtual reality 

capabilities 

• Predictive analyses including 

statistical modeling, neural networks, 

artificial intelligence, and 

machine learning 

• Spare parts optimization 

• Asset lifecycle information management 

• 

The Tipping Point for IIoT 

APM 4.0 is effectively deployed within 

a digital twin because the Industrial Internet 

of Things (IIoT) movement has 

arrived at the tipping point. The cost of 

sensors, data connection, and data storage 

is now a fraction of what it used to be. 

As a result, the amount of raw data being 

generated in plants from IIoT sources is 

growing exponentially, and many organizations 

cannot keep up. Every sensor you 

add produces thousands of additional 

data points. As a result, making sense 

of the data to gain meaningful insights


and get to the right decisions can be 

time-consuming and difficult if you are 

not sure of its relevance or accuracy. 

For most plant managers, the vision of 

a completely autonomous plant is still a 

pipe dream. 

Industry 4.0 can connect physical assets 

in the plant to their digital counterparts 

to improve the automation of plant 

operations and maintenance. Using edge 

computing to implement artificial intelligence 

and automated rules is a fast and 

easy way to alert personnel of problems 

that must be addressed. However, edge 

computing might not monitor all aspects 

of every asset over the long-term. To fully 

oversee a facility, you need a systematic, 

sustainable approach for tracking 

asset health over time with visible, accessible, 

and trusted engineering data. 

Plant managers have embraced 

IIoT out of a desire to eliminate human 

senses from inspections, such as seeing a 

leak or hearing a malfunctioning motor. 

Even with the explosion of sensors that 

can detect changes in operating conditions, 

the ugly truth is that plants remain 

highly people dependent. To improve 

automation, plants need an efficient, 

effective, and comprehensive program 

that goes beyond what people can notice 

themselves. Such a program should include 

a playbook of fully defined organizational 

and business processes, proactive 

and predictive asset management 

practices, and the right technology that 

enables the implementation and execution 

of real-time asset performance. 

Gain Insights to Make 

Effective Decisions 

There are many ways APM 4.0 helps you 

gain insights from data and optimize 

asset performance. Automated rules, 

calculations, artificial intelligence, and 

machine learning are all valuable methods 

to enable faster and more effective 

decisions. But, engineering information 

for each must be complete, accurate, and 

available to ensure you are making the 

right decision at the right time. Otherwise, 

it becomes harder to mitigate costs 

and downtime when the asset fails. 

In short, effective decision-making 

depends on always knowing the current 

state of the asset and becoming informed 

immediately when that state changes. 

This knowledge should include essential 

engineering information, as well as how 

to bring the asset back to the as-built, 

as-commissioned, or as-designed states. 

Asset lifecycle information management 

is the backbone of APM 4.0. Components, 

structures, systems, and operating 

states all change over time due to 

wear and tear, operator decisions, and 

overall plant conditions. Changes in any 

single asset can negatively impact wider 

systems and processes. Trustworthy 

engineering data enables plant engineers 

to determine why a change occurred and 

who caused the change. 

However, raw sensor data alone might 

not be useful as the complexity and 

interconnections of piping and process 

equipment, systems, instrumentation, 

and control devices has increased. Operations 

technology relies on analytics 

visibility as well as subject matter experts 

that can act based on the massive 

amount of data being generated. Digital 

twins, together with asset performance 

management 4.0, can harness that raw 

data and create a trusted system of 

systems. They can connect data with 

processes and identify, consolidate, and 

analyze all relevant sources of data to 

make asset health more visible and drive 

informed decisions and measurable 

business results. 

Digital Twins Enable 

Collaboration between 

Engineering, Operations and 

Maintenance 

A digital twin is a digital representation 

of a physical asset, process or system, as 

well as the engineering information to 

understand and model its performance. 

Typically, a digital twin can be continuously 

synchronized from multiple federated 

sources, including sensors and 

continuous surveying, to represent its 

near real-time status, working condition 

or position. Digital twins enable users to 

visualize the asset, check status, perform 

analysis and generate insights in order to 

predict and optimize asset performance. 



As a result, digital twins eliminate silos 

of data to deliver situational awareness 

and intelligence. 

Additionally, a continually updated 

digital twin provides proof of accurate 

information needed for regulatory compliance. 

Engineering, operations, and 

maintenance greatly benefit from the 

combination of APM and digital twins. 

APM provides the strategy and analytics, 

while digital twins unify the data, provide 

situational awareness and insights, 

and deliver actionable information in the 

hands of those who need it when they 

need it. 

Don’t Forget the ET in Your 

IT - OT Strategy 

Engineering data is always evolving. 

As assets are designed, commissioned, 

and operated, new information becomes 

generated. Individual assets 

also evolve through maintenance and 

modifications during the operational 

phase. The convergence of information 

technology, operations technology, and 

engineering technology (or IT-OT-ET) 

feeds the digital engineering model and 

creates a comprehensive digital twin of 

the working assets in the plant, facility, 

or network. In addition to communicating 

the current state of the asset, the 

digital twin can perform operational 

and engineering simulations to model 

the performance of an asset over time 

and evaluate options to improve performance. 

Essentially, the digital twin connects 

the data from IT-OT-ET in a single portal 

view, allowing the team to validate, 

visualize, and analyze all plant data in 

any format and any data storage location. 

A digital twin environment that is 

open, interoperable, connected, and contextualized 

enables true collaboration 

between engineering, operations and 

maintenance. 

A Day in the Life… Who Needs 

a Digital Twin and Why? 

From the plant floor to the boardroom, 

digital twins quickly give plant staff the 

information they need to make important 

decisions. 

GLOBAL AND REGIONAL EXECUTIVES – 

Executives overseeing a division, region, 

or the entire global operation need to 

track and compare plants and fleets. This 

includes identifying high-performing 

and under-performing plants, then determining 

what makes them succeed or 

fail. Executives must also provide stakeholders 

with proof that the plants are in 

control and that assets are safe and reliable. 

Using digital twins enables them to 

generate informative visualizations of 

large-scale assets and grant a regional or 

companywide perspective. 

PLANT MANAGERS – Plant managers 

must ensure plant production is predictable, 

safe, and efficient. They need 

continual access to key performance 

indicators to identify and evaluate units 

that are underperforming. When issues 

are reported, managers rely on accurate 

information for audits and course-corrections. 

By providing a unified digital 

twin that provides a complete, consistent 

view of plant data, managers allow engi- 



neering, maintenance, and operations 

to collaborate and solve problems more 

effectively and efficiently. 

ENGINEERS – Engineers must quickly 

identify potential operational problems 

and consider solutions. They need to determine 

what has changed in engineering 

models, piping and instrumentation 

documents, drawings, or the maintenance 

and reliability program. Most 

importantly, they need to know that 

the data is trustworthy so that they can 

investigate, troubleshoot, and make fast 

and informed decisions. Digital twins 

can provide this peace of mind, especially 

when engineers can update digital 

twins as needed and view relevant IIoT 

and engineering information in an open, 

connected data environment. 

OPERATIONS – Operators need access 

to performance and maintenance data 

without having to waste time determining 

which data is relevant and which is 

not. They must review as-operated data 

and historical data alike to understand 

what field changes and engineering decisions 

were made and why. Digital twins 

help operators see the big picture and 

optimize production. By supplementing 

control systems with performance dashboards 

containing real-time performance 

data, operators receive a holistic overview 

of the complete facility including areas or 

units not available in the local DCS. 

MAINTENANCE AND RELIABILITY – Maintenance 

managers must review upcoming 

work before attending production 

scheduling meetings. Maintenance, reliability, 

and integrity engineers need to 

monitor and manage equipment health 

as well as piping and vessel integrity to 

easily spot trends and bad actors. They 

need to know what engineering changes 

were made in the past and use rules, 

calculations, AI, and machine learning 

to analyze data. Digital twins combine 

analysis methods and provide valuable 

insights to ensure safety, reliability, and 

asset integrity. 

Digital Transformation 

For any successful team, operational 

excellence depends on a clear strategy, 

skilled players trained on the best techniques, 

efficient and effective equipment, 

and leadership that can coach the 

team to cohesively execute the game 

plan. When done correctly, this leads to 

consistent wins. 

APM 4.0 and digital twins are digitally 

transforming plants to help them stay 

ahead of the competition. Everyone from 

the plant floor to the boardroom needs 

insights to make more informed decisions. 

Digital twins provide a federated 

portal view of all necessary systems and 

data, which gives workers at all levels the 

insight needed for overall success. 

SEVERAL CASE STUDIES 

OMAN GAS COMPANY implemented 

a digitalized, automated framework 

for its reliability and integrity program. 

Establishing a connected data 

environment and digital workflows 

reduced failures and improved reliability 

performance by 9%. The technology 

transformed the team and 

how they manage assets, resulting in 

significant economic gains. 

ARCELORMITTAL USA successfully 

implemented an equipment reliability 

initiative, saving USD 2.1 million during 

a year-long pilot program at one 

of its hot strip mills. The success of 

the pilot led to a wider implementation 

across 10 key focus areas and a 

savings of more than USD 14 million 

nationwide over two years. Arcelor- 

Mittal adopted asset performance 

management best practices, processes, 

methodologies, and digitalization 

technology to efficiently share 

trusted information and change the 

company’s maintenance culture from 

reactive to proactive. 

EPCOR UTILITIES INC. implemented 

an ISO 55000-aligned; risk-based 

asset management process supported 

by Bentley System’s APM technology. 

Using asset health indexing, they 

gained an understanding of the consequence 

of asset failures, including 

replacement costs, damage to adjacent 

assets, impacts to safety, and 

environmental cleanup costs. Coupling 

this information with outage 

times and electrical load data, they 

could better predict the annual risk 

cost. The result was lowering their 

SAIDI Interruptions Duration Index 

score to 0.833, well below the regulated 

threshold of 1.15 hours/customer. 

BP created a central information 

store (CIS) to manage information 

needed for operations, including all 

documents, tags, metadata, and 3D 

model visualization. Using a Microsoft 

Azure-based cloud deployment 

of Bentley Systems’ AssetWise asset 

performance software, the project 

team seamlessly integrated engineering 

information into operations. 

Doing so supports safe, reliable, and 

efficient operations throughout the 

life of their assets. With safety at the 

heart of all operations, BP ensures it 

continuously maintains the integrity 

of operational information. 



Experience Feedback – 

Rotating Machinery 

PATRICE DANNEPOND, SDT Ultrasound Solutions 

Display of the database in the UAS software 

Experience feedback on 

the implementation of an 

ultrasound-based preventive 

maintenance program. 

Introduction 

In this article, we would like to share an 

experience feedback from a paper mill that 

has implemented a preventive maintenance 

program to monitor rotating machines using 

ultrasound technology. SDT International 

helped implement this monitoring program 

by training and coaching the teams in charge 

of mechanical maintenance reliability. The 

purpose of this program is to monitor a fleet 

of about 70 rotating machines during the year 

after its implementation and to extend it to 

100 machines over the second year. 

Issue 

This paper mill has relied on preventive 

maintenance for many years, using known 

and proven technologies for the monitoring 

of rotating machines. In 2018, they decided to 

extend this monitoring to equipment with rotation 

speeds up to 30 RPM, as well as to their 

speed-reducing gears. 

They purchased an SDT270 type ultrasound 

detector, in DU version, along with its 

UltrAnalysis (UAS) software, and SDT International 

and the Reliability department of 

the paper mill developed a training program 

suited to the rotating machinery monitoring 

program. The first step consisted in creating 

the database including these 70 machines, 

and then in recording an initial measurement 

of the mechanical status of each bearing 

and each gear. After a simple onsite analysis 

(ultrasonic listening) and a more detailed 

analysis (overall or static measurements and 

spectral or dynamic measurements) using 

UAS, pre-alarm, alarm and danger thresholds 

were assigned to each measurement point. 

This background work, which is required, 

allows technicians of the reliability department 

in charge of the measurements routes 

to get a quick overview of the asset hierarchy 

and immediately see the machines that have 

an alarm status. 

Display of the asset hierarchy including all rotating machines under monitoring 

and alarm statuses for each piece of equipment. In the present case, 19 rotating 

machines are monitored, 2 of which have exceeded the danger threshold for the 

bearings of the rear motor. 

ISSUE 

This preventive maintenance program has 3 objectives: 

• Highlight the efficiency of ultrasound measurements on rotating machines. 

• Issue a relevant diagnosis. 

• Offer preventive maintenance with reliable indicators. 

Experience feedback after onsite measurement sessions from 

October 2018 to November 2019 

Monitoring of a parallel reduction gear 

• Machine: Decanter – High-speed input bearing of the reduction gear 

Measurement carried out on 16/10/2018 Measurement carried out on 20/09/2019 



On the time spectra (same scale), we can observe the occurrence 

of shocks compared to the first measurement carried out 

in 2018. The trend curves show the evolution of the RMS static 

value: from -4.3 dBµV in 2018 to +16.8 dBµV in 2019. 

Based on SDT criteria, this increase corresponds to the early 

failure of a mechanical part of the reduction gear (bearings and/ 

or gears). 

Zooming in on the FFT frequency spectrum allows highlighting 

dissymmetry of the modulation around the meshing frequency, 

which is characteristic of a damaged gear mesh. 

Listening to the bearing and analysing the frequency spectra 

(see chart above) has allowed confirming this diagnosis by observing 

the emergence of significant peaks associated with this 

gear damage. 

We can observe repeated shocks associated with the frequency 

of the high-speed input drive pinion of the reduction 

gear (24.93 Hz and its harmonics) with demodulation at each 

peak. Broken tooth and teeth clearance. Replacement of the reduction 

gear during a scheduled production shutdown, which 

avoided an untimely breakdown which could have generated 

significant expenses due to production losses. 

The endoscopic video inspection of the worm screw of the reduction 

gear confirmed the ultrasound diagnosis. 

The customer took the reduction gear down during a production 

shutdown. 

Wear detected on the tooth of the worm screw of a reduction gear, 

wheel and screw: 

• Machine: Lime mud filter agitator – High-speed input 

bearing of the reduction gear 

We can observe that between each revolution of the worm 

screw, there is a phenomenon occurring, which can be heard 

through the ultrasound detector as a sliding of the gear (worm 

screw/bronze wheel). 

Measurement carried out on 

10/07/2018 


29/10/2019. After replacement of 

the reduction gear 

Monitoring of the degradation of the bearing of a low-speed reduction 

gear (opposite transmission): 

• Machine: Vertex separator reduction gear – 4-train 

parallel reduction gear 

Measurement carried out on 11/12/2016 

From the beginning of the monitoring of this reduction gear 

(August 2018) using ultrasound technology, the occurrence of 

shocks can be observed on the time spectrum. 



By zooming in on the time spectra, one can observe repeated 

shocks at 9.756 Hz (see the table of characteristic frequencies 

below) related to the frequency of the inner ring of the bearing 

of the low-speed reduction gear (opposite side of transmission). 

Diagnosis confirmed on the frequency spectrum (see below). 

Monitoring of the degradation of the bearing of a low-speed reduction 

gear (opposite transmission): 

• Machine: Lime mud filter – Bearing opposite transmission 

23140 CCK – 14.28 RPM 


16/10/2018 


07/01/2019 

The amplitude of the scaling-type defect is modulated by the 

rotation speed. 

On the spectrum, this is evidenced by a peak at the frequency 

of the defect of the inner ring of the output bearing of the reduction 

gear and by sidebands at the rotation frequency of the 

shaft, i.e., 0.5 Hz – 30 RPM (low-speed reduction gear). 

On time spectra (same scales), one can observe the occurrence of 

shocks right from the beginning of the monitoring of this bearing. 

After replacement of the bearing, all shocks disappeared. The 

rolling elements were no longer held in their housings. 

Trend curves show the decrease of the RMS value after servicing 

(from +10.7 dBµV in 10/2018 to -4.4 dBµV in 01/2019). 

Trend curves show the decrease of the RMS value after servicing, 

from +12 dBµV in 08/2019 to +1.2 dBµV in 11/2019. 


26/08/2019 


25/11/2019. After replacement 

of the reduction gear 

Replacement of the reduction gear during a scheduled production 

shutdown, which avoided an untimely breakdown which 

could have generated significant expenses due to production 

losses. 

Conclusion 

The challenge was taken up by the Reliability team of this paper 

mill. The implementation of a preventive maintenance program 

for 70 rotating machines has had a beneficial and decisive outcome. 

It will be extended to 100 other machines over the course 

of 2020. SDT International offered a simple solution and suitable 

measurement tools, along with a LEVEL1 ASNT certified training 

program. Users have acquired a comprehensive mastery of 

this technology, which was new to them. 

1. Using ultrasound technology to monitor low-speed rotating 

machines, this paper mill was able to avoid a number of unscheduled 

shutdowns (see examples below) and highlight the complementarity 

of ultrasound and vibration technologies. 

2. Based on this experience, the Reliability department has 

decided to initiate ultrasound-aided greasing campaigns. Using 

suitable equipment (software and hardware), this acoustic lubrication 

program will ensure perfect greasing by indicating: 

• the right grease, 

• the right greasing location, 

• the right greasing interval, 

• the right quantity of grease to add, 

• the right indicators for the lubrication condition. 

Thus, full traceability of the lubrication program will be ensured. 

3. The versatility of ultrasound detector SDT270DU also allowed 

for the implementation of: 

• An energy-saving policy (detection of compressed air leaks, 

control of steam traps). 

• Control of tubeblowers (detection of leaks on steam valves). 

• Preventive maintenance of high voltage electric systems (corona, 

tracking, arcing). 


Be a LUBExpert 

® 

A COMPLETE ULTRASOUND SOLUTION TO MANAGE YOUR ACOUSTIC LUBRICATION PROGRAM 

Poor greasing practices are 

a leading cause of bearing failure. 

Many lube departments re-grease on a wasteful 

calendar-based schedule. This leads to over and 

under greased bearings that fail to deliver their 

engineered value. 

LUBExpert tells us when to grease... 

and when to stop. 

Grease reduces friction in bearings. Less friction 

means longer life. LUBExpert alerts you when 

friction levels increase, guides you during 

re-lubrication, and prevents over and under 

lubrication. 

Grease Bearings Right 

Right Lubricant 

Right Location 

Right Interval 

Right Quantity 

Right Indicators 

Ultrasound Soluons 

sdtultrasound.com/lubexpert


RESONANCE - 

The Hidden Threat 

Text: Adash Ltd. 

You have done proper balancing (twice for sure), you have done alignment, you 

have checked the mountings and your machine is still vibrating like an old washing 

machine for no obvious reason… The reason is probably resonance. 

MECHANICAL RESONANCE is the tendency of a mechanical 

system to respond at a greater amplitude when the frequency 

of its oscillations matches the system's natural vibration frequency 

than it does at other frequencies. 

For every mechanical object, there are natural frequencies 

at which that object vibrates more easily and harder than at 

other frequencies. 

You can see this in everyday life. For example, there might 

be something in your car that does not vibrate very much, but 

if you make a small change in engine RPM, you can hear much 

stronger vibrations. 

This is an example of where the engine RPM is near the 

natural frequency of the thing that is vibrating. 

It is very dangerous to operate machines near their natural 

frequencies because even a small unbalance can generate extremely 

high vibrations. This can destroy the machine very easily. 

We usually encounter the resonance problem on the machine 

foundation. When the machine speed is near the natural 

frequency, then we measure high vibrations without a visible 

reason. The maintenance team usually carries out all the 

standard procedures like balancing, alignment and bearing 

mounting checks but vibrations still remain high. The resonance 

problem is the reason. 

Now I would like to describe to you how to use the bump 

test measurement. It is the perfect measurement for situations 

where you suspect a resonance problem. We used a steel beam 

for this simple demonstration. Imagine that it is a machine 

foundation. 

We used a standard 100 mV/g accelerometer and a hammer. 

The Adash VA4Pro and VA5Pro vibration analyzers contain 

a super easy bump test mode. There is no need for any settings. 

Just place the sensor on the object to be measured and hit it 

with a hammer. 

Let's look at the final graph. [1] 

High peaks on the spectrum represent natural frequencies, 

in our case 100 Hz and 280 Hz. There will be a resonance problem 

if the machine speed is near these two frequencies. 

We can move the natural frequency to solve the problem by 

reinforcing the construction in order to change the natural frequency. 

For example, we could add another pillar in the middle 

and the natural frequencies will decrease. [2] 

A fixed pillar would be welded to the machine foundation in 



Graph 1: initial spectrum 

Graph 2: changed spectrum 



Figure 1. Every mechanical object has its mode shapes. 

Figure 2. The length of each arrow is 

proportional to the g value at that point. 

Figure 3. The first natural frequency is 10 Hz. 

Figure 4. Second natural frequency. 

the real world and natural frequencies would not only be 

reduced but also re-tuned. 

Every mechanical object has its mode shapes. I will 

explain it on this simple free beam (Figure 1). 

The first mode shape is this: we can see two nodes and 

three anti nodes. The next mode shapes have more nodes 

and more anti nodes. But for now, we will only consider 

the first one, whose natural frequency is the lowest 

natural frequency from the measured graph. We marked 

several points on our steel beam and measured the amplitude 

on each mark. 

The length of each arrow is proportional to the g value 

at that point. Now you can see the first mode shape, 

which we have got from real measurements (Figure 2). 

For simple objects you can calculate the mode shapes, 

but for a complicated construction it is not possible, you 

have to measure it. 

We analyzed the frame by hitting it with hammer. 

When the machine is operating, you can also measure 

the vibration levels at every point. In this case the frame 

is not excited by the hammer but by operational speed. 

The vibration levels will not be the same on all points of 

30 maintworld 3/2019

the machine. Measure all of them and draw the arrows 

again, you will get the first operational deflection shape 

of the machine. For finding the next operational deflection 

shapes, you have to know the spectrum of vibration 

on each point. Knowing the machine shapes is important 

for machine understanding. 

The ADASH analyzers contain the ADS mode. It enables 

you to measure these shapes very simply and then 

illustratively animate the results. 

In the next example I show you why it is important to 

know the mode shapes which are the cause of the vibration 

problem. We used the shaker and the rubber cord. 

The first natural frequency is 10 Hz and you can see the 

first mode shape (Figure 3). 

If I need to decrease the vibration level, then I can add 

the pillar to many places and it will work. 

But sometimes the second mode shape could be the 

problem rather than the first. Now you can see the second 

natural frequency (Figure 4). 

The location of the pillar is now much more important. 

If I add it in the middle, then the vibration remains 

unchanged. 

Back to our first example with the steel beam. Initial 

overall vibration was 6.34 g. We added a pillar in the middle 

and the main natural frequency on 100 Hz decreased 

approximately 4 times. But the second natural frequency 

on 280 Hz decreased only about 2 times and now is influencing 

our frame almost as much as the first frequency. 

The overall vibration is now 3.19 g. 

Then we moved the pillar from the middle to 1/3 of 

the way between the end pillars. The new natural frequencies 

look like this. [3] 

You can see that the first frequency remained the 

same, but the second was more reduced. 

Overall vibration decreased to 2.56 g. 

Graph 3: final spectrum 

BUMP TEST 

MEASUREMENT 

IS THE PERFECT 

MEASUREMENT FOR 

SITUATIONS WHERE 

YOU SUSPECT A 

RESONANCE PROBLEM.


How Predictive 

Maintenance 

Enhances 

Plant Safety 

without sacrificing productivity 

ADRIAN MESSER, 

CMRP 

adrianm@uesystems.com 

Ultrasonic sensors 

improve safety by 

allowing assets to be 

inspected at a distance 

An effective predictive maintenance strategy 

leverages technology and analytic data to allow for 

optimized scheduling of corrective maintenance tasks. 

The goals of these programs are to reduce asset 

downtime, prevent unexpected failures, promote 

productivity and increase the safety of personnel. 

IN THE PAST, safety investments often 

meant a reduction in overall productivity 

or an increase in cost structure. However, 

modern technology has created 

new opportunities for facility managers 

to maintain or even increase productivity 

levels as the plant implements new 

safety protocols. 

How maintenance impacts 

facility safety 

Maintenance work can be dangerous, 

especially when assets fail in unexpected 

or catastrophic ways. In fact, a 

report from BLR (Business & Legal Resources) 

revealed that between 25 and 

30 percent of workplace deaths in the 

manufacturing industry are related to 

maintenance activities. Shocks, burns 

and injury from moving parts are all 

common causes of fatal accidents. 

A predictive maintenance strategy 

seeks to reduce or completely 

eliminate unexpected failures. Using 

technology such as ultrasound sensors, 

stakeholders can detect minute 

changes in sonic output to determine 

when an asset is likely to malfunction. 

Given enough data, stakeholders can 

determine expected life spans for all 



facility assets and build a maintenance 

schedule around this information. This 

way, maintenance personnel can power 

down assets during a period that is not 

likely to interfere with the facility’s 

productivity goals. They can complete 

maintenance work well before an asset 

begins to behave erratically, reducing 

the risk of severe injury. 

Combined with safety training and 

other fail-safes, a predictive maintenance 

program gives facility managers 

the ability to mitigate risk with precision. 

Predictive maintenance can improve 

asset uptime without sacrificing safety. 

Why predictive solutions 

optimize risk management 

Reactive maintenance programs carry 

a lot of financial risk. According to the 

International Society of Automation, 

PREDICTIVE MAINTENANCE 

REQUIRES FORETHOUGHT, 

STRATEGY AND INTELLIGENT 

TECHNOLOGY INVESTMENTS. 

manufacturers across all industries 

lose approximately $647 billion annually 

to asset downtime, thereby losing 

out on a corresponding $13 trillion in 

production value. To put those numbers 

in context, ISA explained that the 

average cement mill loses roughly $7 

million per year in lost production. 

Traditionally, matters of financial 

risk and safety risks have been a balancing 

act. More safety measures often 

meant fewer resources available for 

production. Predictive maintenance 

changes this paradigm significantly. In 

a predictive scheme, both productivity 

and safety increase with the strategic 

scheduling of maintenance tasks. The 

program not only allows maintenance 

staff to know when an asset is likely to 

fail, but also specifically how the asset 

is likely to deteriorate. Combined, this 

knowledge gives stakeholders an unprecedented 

strategic advantage. 

At the end of the day, safety issues 

and maintenance issues stem from the 

same problem: a lack of planning and 

analysis. Both types of risk are much 

easier to manage when stakeholders 

have the resources to plan for contingencies 

and eliminate the potential for 

risk before it manifests in a workplace 

accident. 

How technology improves 

safety and productivity 

An effective predictive maintenance 

strategy begins with good data. According 

to Control Engineering, this 

data can come from multiple sources, 

such as thermal readings and remote 

ultrasound sensors. The more performance 

indicators a facility manager 

has to work with, the more optimized 

the maintenance strategy. 

For example, say a facility manager 

knows one of his or her assets enters 

a fail state approximately every six 

months. The manager could schedule 

maintenance every five months to prevent 

failure. A smarter approach might 

be to place sensors along the moving 

parts of the asset and continually 

monitor decibel readings for changes. 

These sensors can show maintenance 

staff exactly which part of the asset 

is beginning to fail, so they can take 

targeted action in a timely manner. 

Over the years, the system would 

improve continually as stakeholders 

understand exactly when and how an 

asset needs to be serviced for optimal 

performance. 

Predictive maintenance requires 

forethought, strategy and intelligent 

technology investments. 

Sensors can be 

permanently 

mounted into 

an asset for an 

easy remote 

inspection 

The 4Cast monitors 

assets 24/7, taking 

decibel readings and 

sound recording 



Root Cause of an Electrical 

Problem, Did You Find the 

Systematic Problem to Solve? 

Root cause failure analysis 

is a common term used 

within reliability and 

maintenance. Working 

with reliability and 

maintenance, we see 

organizations do root 

cause analyses but very 

few leads to corrective 

action and improvements. 

So why don’t we solve 

problems? 

A GOOD ROOT CAUSE elimination program 

needs a process, practical training 

in critical thinking, and coordination 

and follow-up of actions. IDCON has 

developed a process called Root Cause 

Problem Elimination (RCPE) where we 

emphasize solving the problem, documenting 

and executing tangible actions 

and visible results. 

I’ll give you a real-world example of a 

facilitated Root Cause Problem Elimination 

event. 

Wednesday at 08:42 AM Paper Machine 

#8 shutdown due to power loss in 

the press section. The paper machine 

was down for more than 9 hours before 

the circuit breaker was replaced and 

started up. 

The suggested approach is to use the 

same tools as in a murder investigation, 

because the circuit breaker was murdered! 

We started by collecting the data 

for the investigation. The data included: 

• Understanding how this equipment 

works 

• What happened, where, when, and 

similar objects 

• Changes in time – before, during 

and after the paper machine shut 

down? 

• Physical evidence - gathered all 

OWE FORSBERG, 

Senior Management 

Consultant with 

IDCON INC. 

Figure 1: Failed Power Circuit break for 

Paper machine press section. 

Figure 2: The How Can diagram using 

Post-it® notes. All you need is a wall, no 

software needed. 

the parts of the breaker, took pictures, 

and did a forensic analysis 

• Conducted interviews with personnel 

involved 

As mentioned earlier we train people 

to eliminate problems using critical 

thinking tools and a structured method. 

Much like RCA, the process starts with 

the trigger. In this case, the trigger was 

defined as 

“machine downtime event >30-minutes 

then initiate formal root cause analysis” 

The next step is to clearly state the 

problem. The problem statement should 

follow the rule “one object and one problem” 

in this case “circuit breaker to press 

section shorted” 

The problem was now identified. The 

next step was to determine “How Can” 

the circuit breaker short. To find alternatives 

that may have caused the problem, 

we use a tool called the How-Can Diagram 

(Figure 3). 

Start from the right, spell out the trigger, 

problem statement and then you 

ask the questions “how-can the circuit 

breaker short? Answers “phase to phase” 

or “phase to ground” 

Next question How-Can this short 

happen? “Dust on the terminal connects 

(stabs)” or “Corrosion on the terminal 

connections (stabs)” and keep going until 

you have exhausted the alternatives. 

Most important, provide all alternatives 

that make sense but don’t jump to conclusion. 

The best way to start the creative 

process is not to use a spreadsheet or software 

but post-it notes on the wall. The 

post-it notes engages the problem-solving 

team and keeps them actively involved – 

trust us on this one! 

Next step is to check the facts and find 

the most likely cause, in this way you can 

eliminate or confirm parts of the How- 

Can diagram. State each fact for the each 

of the boxes in the How-Can Diagram and 

ask the question “This is a fact because?” 



Figure 3: The How-Can diagram for 

this investigation 

Example the dust and dirt on the terminal 

connects (stabs) is a fact because we could 

see it and confirmed that it was present 

on other circuit breakers too. We could 

not confirm that there was any mechanical 

damaged or alignment problem of the 

terminal connects (stabs) of the circuit 

breaker. The Electrician and Electric Engineer 

confirmed that the arcing occurred 

between the breaker phase terminal 

connects (stabs) and not to ground. The 

investigation confirmed that the Technical 

Cause for the breaker to short is the 

missing dust and chemical filters. 

There were other causes we needed 

to figure out – How Can a filter not be in 

place? What we found was that the filters 

weren’t in stock because they weren’t approved 

for purchase! The cost for the filters 

were $50K each. It was deemed too 

expensive to the maintenance budget. 

The Human Cause is that the maintenance 

team should have known the 

impact of not replacing the filters to save 

$100k. The decision to save $100K on the 

filters, ended up costing them a lot more 

to repair the “murdered” circuit breaker. 

The Systematic Cause is the lack of 

training for how the filters impact the 

long-term reliability of the MCC room 

electrical equipment. The other systematic 

issue, changes to the equipment 

should be reviewed and approved by the 

qualified technical expert through the 

Management of Change process before 

being implemented. 

Eliminating the problem 

The RCPE team presented the investigation 

to the mill leadership and put a 

plan in place that would eliminate the 

systematic cause, the human cause and 

the technical cause. A training plan was 

put in place so that everyone understood 

how important the filters were to the reliability 

of the plant and a MOC process 

was put in place ensuring that no changes 

were made without proper approval. 

Reveal Your Potential 

Get a Reliability and Maintenance Assessment 

Call us +1 919-847-8764

EVENT 

The Day After Tomorrow 

in Asset Performance 

Peter Hinssen is an 

entrepreneur, who has 

focused on startups for 

almost 20 years. He is 

a technologist at heart. 

Peter will be talking at the 

Asset Performance 4.0 

Conference on September 

16th in Ghent about how 

companies and technical 

services can prepare for 

the future. 

PETER, YOU WILL BE PRESENT AS A 

KEYNOTE SPEAKER AT THE ASSET PER- 

FORMANCE AWARDS. CAN YOU EXPLAIN 

WHERE YOUR INTEREST IN THE INDUS- 

TRY COMES FROM? 

It is a little bit personal because my father 

worked in the oil and gas industry 

his entire life, specifically Maintenance 

and everything that deals with process 

control. So, when I was a kid, it was all I 

heard from my dad coming home. And I 

think the evolution that you see in this 

industry is fascinating. New technologies 

are changing, in my opinion, tremendously: 

dealing with assets, managing 

performance and thinking about prediction 

is going to change tremendously. 

So, I am very excited to be part of this. 

Can you give some examples of technologies 

that will impact our world? 

Big Data. I mean, this is an industry 

that has always been interested in information. 

But now Big Data is becoming 

abundant. We have technologies to deal 

with that. We have machine learning, 

artificial intelligence, all these mechanisms 

of connectivity. I think if you put 

it all together, it is piling up technology 

upon technology that is fundamentally 

changing how we think about how to 

deal with data. And I think it will have a 

tremendous impact on this industry. 

PETER HINSSEN, 

Author of The Day 

After Tomorrow and 

keynote speaker at the 


Conference in Belgium. 

WHAT DO YOU THINK THE MAIN CHAL- 

LENGE OF THE INDUSTRY TODAY IS? 

We are currently in a disruptive era. I use 

this word carefully, but it indicates a constant 

acceleration and the need to follow 

that speed. Lots of companies see a huge 

conflict between possibilities and reality. 

So this gap and tension between what is 

possible and what you do day-to-day is 

a big challenge. We need to take a huge 

leap in skills and technology. This is also 

an opportunity to become more critical 

of your company. Performance plays an 

important role. And the reason why your 

company exists is absolutely core. But be 

careful what you wish for, because once 

you enter the spotlight, you have got to 

deliver. Take up your role and realise it. 

WHAT MAKES IT SO DIFFICULT TO TAKE 

UP THIS ROLE? 

Being able to tell the story and carry it 

out. Storytelling is key. IT people should 

be rockstars, but most of the time they 

are not so communicative. That is because 

they don't have the skills to tell 

their story. If you go from predictive 

maintenance to Asset Performance in a 

connected world, then you have so many 

touch-points, that you have to broaden 

your gaze. You need more skills and 

competences. Your suppliers change. 

Your partners change. And everything 

becomes more fluid. 

IN YOUR BOOK ‘THE DAY AFTER TOMOR- 

ROW’, YOU'RE TALKING ABOUT WHAT IS 

GOING WRONG IN COMPANIES TODAY. 

WHAT IS YOUR VISION? 

Well, I have a very simple idea of how 

much time companies spend on today, 

tomorrow, and the day after tomorrow. 

Most companies are very busy with today. 

And when they look at the future, 

they often extrapolate today, they think 

that tomorrow is approximately the 

same. But we are now facing so many 

different changes that there might be 

changes in business models or in technologies 

or new players coming onto the 

market. We have to think about this disruption, 

'this is the day after tomorrow', 

and how you deal with that. When I talk 

about today, tomorrow, and the day after 

tomorrow, many people say they dedicate 

70-20-10 percent of their time on it. 

The reality is we spend 93 percent of our 

time on today, maybe 7 percent thinking 

about tomorrow and virtually none 

on the day after tomorrow. And I think 

in many industries, this was okay and in 

the 20th century. But we are now fully in 

the 21st century. That doesn't work anymore. 

We have to be much more flexible 

and agile. And that is why the day after 

tomorrow is more important than ever 

before. 

YOU WILL ALSO TALK ABOUT TWO IN- 

TERESTING CONCEPTS: STAYING ESSEN- 

TIAL AND STAYING RELEVANT. HOW CAN 

WE ACHIEVE THAT? 

Of course you want to be essential. You 

want to do something that makes sense. 

If you do predictive maintenance, that 

is essential. If you work for customers, 

you are hoping that you are vital for that 

customer. But the other question is, how 

relevant are you? And I think there is a 

very clear difference between essential 

and relevant. Think about the telecom 

industry. If you look at telecom 10 years 

ago, a telecom operator was essential. 

You needed a SIM card, and they were 

relevant, they gave you added value. Today, 

in this world, they are still essential, 

because you still need that SIM card. But 

the relevance has dropped. And therefore, 

if whatever capacity you have in an 


EVENT 


Conference & Exhibition 

• Asset Performance 4.0 Conference, 

15-17 September 2020, 

ICC Ghent, Belgium 

• More info and registrations : 

www.assetperformance.eu 

organization, whatever position you have 

in dealing with the outside world, that 

is the core question, are you essential? I 

hope you are. But how can you make sure 

that your relevance doesn't go down? 

AND THAT BRINGS US TO THE MAINTE- 

NANCE AND QUALITY DEPARTMENT. 

THEY DON'T ADD VALUE DIRECTLY TO 

THE PRODUCT. THE CUSTOMER DOESN'T 

PAY FOR MAINTENANCE THAT WAS NEC- 

ESSARY TO PRODUCE HIS PRODUCT. BUT 

IT IS ESSENTIAL. SO WHAT WOULD YOUR 

TIP BE TO STAYING RELEVANT? 

Well, I think it is that we are in an age 

where everything is interconnected. 

So, if you look at an organization, they 

are not silos anymore. We are in this 

network age, everything is connected 

to everything else. So when you say that 

your customer doesn't pay for the maintenance 

directly, that is true, but your 

customer will feel, see and understand 

whether this is something which is integral 

in terms of quality thinking or performance 

management. And in the end, 

if your company wants to be flexible and 

fast and agile, you have to incorporate 

that into every part of the organization. 

Every fibre, every node, every element 

has to understand that you are part of 

a bigger picture, and you have to keep 

reinventing yourself to be both essential 

and relevant for the outside world. 

THE DAY AFTER TOMORROW 

IS MORE IMPORTANT THAN 

EVER BEFORE. 

THIS CONNECTIVITY IS ENTERING A LOT 

OF FACTORIES. THEY ARE EXPERIMENT- 

ING, BUT WE SEE SOME RELUCTANCE 

AND DIFFICULTIES TO SCALE UP. HOW 

CAN YOU SOLVE THAT? 

Well, I think we are in a phase where a 

lot of the technologies emerging take 

something like AI or machine learning 

that is relatively new. Most people 

don't understand it very well, there 

is a huge skill gap that we need to fill, 

because we need to train and prepare 

people for that. But a lot of things are 

just trying out, companies are experimenting 

and figuring out how to apply 

this, but it is very early in the game. 

If you compare that to the PC industry, 

this was the time where we had 

Commodores and Ataris, and not the 

established industry like we have it 

today. We are going through that phase. 

And if you are too early, you are going 

to burn a lot of money and not get a 

lot of results. But if you wait too long, 

you probably run the risk of becoming 

completely obsolete. I think it is making 

sure that you are constantly in tune that 

you are constantly alert that you follow 

this as closely as possible and make the 

right move at the right time. But you 

can only do that if you are prepared. 

HOW CAN PEOPLE PREPARE FOR THIS 

SKILL CHALLENGE? 

I think they have to make time for it. 

Time is the biggest issue. To put your 

day-to-day work at the side is difficult, 

but you really have to invest in these 

skills. Experiment at first, like tinkering 

with fuel until somethings blows 

up. There are so many possibilities, 

also online, to test and try out different 

stuff. Everybody talks about life long 

learning, but most managers don't do it 

themselves. 

WHY SHOULD PEOPLE ATTEND YOUR 

KEYNOTE AT THE ASSET PERFORMANCE 

4.0 CONFERENCE? 

I think this is one of the most fascinating 

industries that for a long time, has 

already worked with data. But it's now 

making a quantum leap. I'd love to talk 

about how I see that evolving, I hope to 

inspire you to maybe even do more than 

what you're doing today. But above all, 

to prepare ourselves for, I think, a very 

disruptive wave that is going to affect 

everyone. And I think if we understand 

this, we can all actually come out even 

better as a result. 



A standardised methodology 

with factory specific outcome 

Multi-site approach with VDM XL 

Every factory is unique. Think of differences in 

product and manufacturing process, the technical 

condition of the assets or the way we do maintenance. 

Then it appears to be impossible to implement one 

standardised improvement method still enabling each 

Technical Services Department to add value to the 

operating result. It is possible though, with VDM XL . 

VDM XL STANDS for Value Driven Maintenance 

and Asset Management. VDM XL 

explains how to extract maximum economic 

value from an existing plant, fleet 

or infrastructure using a professional 

management approach. This worldwide 

recognised method was developed by 

Mark Haarman and Guy Delahay from 

consultancy firm Mainnovation. With 

this methodology capital-intensive companies 

can professionalise their Technical 

Services Department and transform 

it from a cost centre into a business 

function that continuously improves 

business performance. 

Customisation 

What do you need, to improve Maintenance 

& Reliability in your organisation? 

How to create value with asset 

management? How do you manage your 

maintenance organisation and make 

sure your decisions benefit the company? 

“The answers to these questions 

vary per factory”, says Mark Haarman, 

managing partner from Mainnovation. 

“We have applied the VDM XL method in 

factories in various industries like Food 

& Beverage, Life Science and (Petro) 

Chemicals. But also in Energy & Utilities 

and Fleet & Transportation you need 

to manage your assets, preferably in a 

way that creates value for the company.” 

Haarman explains how every factory, 

every client has specific needs because of 

the uniqueness of the assets. “Working 

with a standardised method and making 

sure that every specific factory executes 

maintenance in the same way, seems impossible. 

But we provide a solution with 

VDM XL . Our standard approach can be 

customised when it comes down to implementing 

improvements. We present 

a plant-specific solution, with a focus on 

the most dominant value driver per factory. 

VDM XL is a standardised methodology, 

but the outcome is always factory 

specific.” 

Value drivers 

VDM XL distinguishes four axes on which 

the Maintenance & Asset Management 

organisation can add value with an existing 

installation. They are called the four 

value drivers. Haarman: “With an audit 

we can measure the current performance 

and maturity levels of the Technical 

Services Department and determine 

MULTI-SITE APPROACH : 

THE MOST DOMINANT VALUE driver 

varies per factory. “But every factory 

can start with the same method”, 

Haarman explains. That's why VDM XL 

is the right decision for a multi-site 

approach. The method has already 

proven itself at large companies with 

multiple site locations. “By using one 

method, it's possible to compare sites, 

while each factory derives its own 

action plan. A strategy that creates 

value per factory and creates opportunities 

for continuous improvement. 

And I can tell you: that makes both 

senior management and the Technical 

Services Department happy.” 

what would be the winning Maintenance 

and Asset Management strategy for the 

future. This strategy describes the improvements 

in processes, organisation, 

IT systems, data and performance management 

needed to create maximum 

economic value for the business. Now 

we know on which value driver we need 

to focus: should the Technical Service 

Department be managed based on cost 

reduction, increased uptime, safety improvement 

or lifetime extension?” 

MAINNOVATION 

☏ +31 (0)78 614 67 24 

info@mainnovation.com 

www.mainnovation.com 



Viewing Maintenance 

as a System to 

Optimize Performance 

Tracy T. Strawn, 

Strategic Advisor, 

Marshall Institute 

In 1958, Mao Zedong of China ordered all sparrows killed because they were eating 

grain necessary for people, and he thought killing the sparrows would result in 

surplus food for 60,000 people. This campaign seemed successful, as the sparrow 

was nearly made extinct in China. Unfortunately, Mao did not realize that sparrows 

were natural predators to locusts and other insects. With the sparrows gone, the 

locusts multiplied, devastating Chinese agriculture. The ecological imbalance helped 

spur on massive food shortages and the death of an estimated 30 million people. 

WHY DID THIS HAPPEN? Mao didn’t have an appreciation of a 

system which maintained ecological balance. Once upset, the 

unintended consequences resulted in millions of deaths. 

Ecological systems and their mismanagement are only one 

facet of the study of systems. Systems or systems theory is an 

interdisciplinary field that studies the nature of systems—from 

simple to complex—in nature, society, engineering, technology 

and science. Some areas of study include systems engineering, 

systems analysis and systems thinking. This article will focus 

specifically on how systems concepts apply to the maintenance 

organization and why we should be concerned about it. 

What is a system? 

• A system is a group of interacting or interrelated entities 

that form a unified whole. A system is delineated by its 

spatial and temporal boundaries, surrounded and influenced 

by its environment, described by its structure and 

purpose and expressed in its functioning. Systems are 

the subjects of study of systems theory. ¹ 

From this we can assume a system is comprised of smaller subsystems 

with a purpose or goal. Systems science can apply to a 

business or organization. 

• Blanchard defined system as “…a set of interrelated components 

working together with the common objective of 

fulfilling some designated need”. 2 

When applied to businesses, we can conclude that these “components” 

are working together to produce something of value 

to the user, and that their efficiency and effectiveness are 

dependent on how well they work together. If a system is inadequately 

designed or poorly connected and integrated, it most 

likely will be unable to achieve its goals. 

Symptoms of broken systems: 

• Silo mentality: an inward mindset that resists sharing 

information/resources with others 

• Processes plagued by waste and inefficiency due to poor 

workflow design, broken customer/supplier relationships 

and poor decision making 

• Variability in meeting customer requirements due to 

poor system design and standardization 

• Components or subsystems of an organization are not 

aligned with a clear purpose, characterized by inability 

to execute strategy and lack of understanding of what 

matters to performance. 

• 

These symptoms can lead to financial ruin. 

Business systems are frequently identified by department 

names: Procurement, Engineering, Finance or Human Resources. 

Their workflows, connectivity and relationships result 

in producing something of value. If their workflows, connectivity 

and relationships are optimum, the value they produce 

should meet or exceed the goals of the business. 

Systems and processes are the essential building blocks of 

a company. Every facet of business - storeroom, workshop, 

production - is part of a system that can be managed to produce 

something of value. The details of each business system vary 

by company, but the fundamentals remain the same. 

¹ Wikipedia, Systems 

² Systems Engineering Management, 2nd Edition, B. Blanchard, 199 



The Key Concepts of Systems: 

1. Systems are composed of interconnected parts 

2. Inter-connected parts are interdependent 

3. Every system has an aim 

4. The structure of a system determines its behavior 

5. How well the parts cooperate to support the aim determines 

how efficient and effective the system functions 

6. Ultimately we seek synergy in which “the whole is greater 

than the sum of the parts 

CORPORATE 

OBJECTIVE 

MAINTENANCE 

OBJECTIVE 

PLANT 

OBJECTIVE 

Is Maintenance a System? 

Based on definitions, maintenance is a system: usually a subsystem 

of the corporation, made up of a collection of elements 

organized to achieve a purpose. How well the elements are integrated 

and interact determines the efficiency and effectiveness 

of the maintenance system. 

Figure 1 is a simple depiction of a system view of maintenance. 

The maintenance objective will reflect and align with 

corporate and plant objectives, considering the plant structure, 

while defining equipment strategies for ensuring the level of 

reliability required. Equipment strategies will define spares 

policy and outline resource structure needed to plan, schedule 

and execute the workload. The administrative structure will 

define and support personnel policies and determine budgets/ 

controls to manage costs. Subsystems will be reviewed/improved 

to optimize their contribution to the systems aim and 

goals: achieving the desired level of reliability while meeting 

cost and safety targets. 

MAINTENANCE 

CONTROL 

ADMIN 

STRUCTURE 

REVIEW AND 

IMPROVE 

RESOURCE 

STRUCTURE 

PLANT 

STRUCTURE 

EQUIPMENT 

STRATEGIES 



VIEWING AND UNDERSTANDING MAINTENANCE 

AS A SYSTEM WITH AN AIM AND PURPOSE 

IS THE FIRST STEP IN DESIGNING AND 

DEVELOPING A MAINTENANCE SYSTEM. 

Figure 2 depicts maintenance as a system. This example 

shows how three sub-systems working as a system contribute 

to achieving optimum inherent availability. Three subsystems 

in this example are materials management, resource management, 

and reliability management. Materials management 

and resource management aid in optimizing the repair process. 

Both subsystems are critical in identifying and procuring 

spares required for the repair, planning/scheduling the repair, 

and mobilizing the resources to complete the repair. To ensure 

repair is made in the shortest time and at the lowest cost, 

information and communication must flow seamlessly and 

continuously between the two subsystems. The metric used to 

measure the repair process is ‘mean time to repair’ or MTTR. 

The third subsystem in the maintenance system example 

is reliability management, responsible for establishing the 

equipment strategies for achieving optimum reliability while 

considering safety and cost. Equipment strategies are defined 

by manufacturers’ recommendations or a risk based approach 

like reliability centered maintenance. The metric used to 

measure reliability performance is ‘mean time between failure’ 

or MTBF. MTTR and MTBF will be used as illustrated in Figure 

2 to calculate inherent availability. 

In order to realize the goal, achieving the desired inherent 

availability, all three subsystems must work together. 

Achieving a systems aim must be managed with attention to 

the entire system. When we optimize subcomponents of the 

system, we don’t necessarily optimize the overall system. Suboptimization 

is the practice of focusing on one part of a system 

and making changes intended to improve that subsystem while 

ignoring the effects on other subsystems. This will lead to suboptimization 

of the whole system leading to waste, delays, and 

inefficiencies resulting in lost profits and lower plant throughput. 

Optimizing system performance should begin in the system 

design phase. 

8 Characteristics of a Good System Design: 

1. Designed with the customer (internal and external) in mind 

• Work products and services are handed off to internal 

customers who must meet their requirements. 

The objective is to prevent the internal customer 

from reworking or worse, passing through product 

that is fails to meet specifications. 

2. Represents your best known way of doing something 

• A well defined system should be documented with 

workflows of each subsystem and where the work is 

performed and handoffs are made, clearly describing 

roles and responsibilities. 

3. Has one primary aim, goal or purpose 

• Primary/secondary goals should be clearly defined 

and communicated to stakeholders. 

4. Has an owner, accountable for/reporting on system results 

5. Is as simple as possible, documented, understood by 

workers, and repeatable 

• System users should be trained/coached on subsystems 

and processes. 

6. Has performance standards and results are measured. 

• System should be thoroughly implemented and capable 

of meeting performance standards and goals. 

System users understand performance standards 

and can identify out of compliance conditions. Measures 

are monitored by all team members. 

7. Workers get ongoing feedback about system performance 

and are recognized for good results. 

8. Has sufficient focus on system details to eliminate most 

bottlenecks, inefficiencies, waste, and rework. 

Optimizing Maintenance System Performance 

These steps will aid in optimization of existing maintenance 

organizations and system with every process having an input 

from a supplier and an output to a customer. Process stakeholders 

understand how they add value to the goal of the system. 

A robust system will have clear specifications for each 

product handed off to internal customers along with feedback 

to suppliers. 

1. Process map and document your system 

• Identify your processes 

• Show how the processes work together to produce 

value and their interconnectivity 

• Ensure roles and process steps are clear 

2. Identify your products and services for each process 

3. Understand customer/supplier specifications/requirements 

4. Identify the suppliers/customers for each product/service 

5. Communicate process requirements to suppliers 

6. Identify customer specifications 

7. Demonstrate the process is capable/meets specifications 

8. Achieve a thorough implementation 

9. Continuously improve 

Summary 

The complexity of maintenance systems increases as new technologies 

are introduced. In today’s environment, there is an 

increasing need to develop/produce systems that are robust, reliable, 

high quality, supportable and cost effective. Viewing and 

understanding maintenance as a system with an aim and purpose, 

rather than a collection of disparate parts, is the first step 

in designing and developing a maintenance system that can be 

managed and optimized for sustained long term performance. 



Use of High-speed 

Thermography 

in Laser High-temperature 

Capillary Gap Brazing 

Lasers are extremely versatile tools in industry and manufacturing technology. 

Due to their flexibility, they serve as a key technology for implementing 

the goals of industry 4.0. Although laser cutting and welding are nowadays 

regarded as turnkey technologies, most laser applications, for example 

joining of hybrid materials, 3D printing or ultra-short pulse processing, 

still require considerable research and development. 

Text: M. HOFELE, D. KOLB, S. RUCK, H. RIEGEL, LaserApplikationsZentrum of the Hochschule Aalen; InfraTec GmbH Infrarotsensorik und Messtechnik 

Photos: LASERAPPLIKATIONSZENTRUM OF THE HOCHSCHULE AALEN 

THE LASERAPPLICATIONCENTER (LAC) 

of Aalen University intensively researches 

and develops new methods of laser 

material processing. Thus, innovative 

materials for Additive Manufacturing 

are developed and investigated within 

public R&D projects, including magnetic 

materials or electrical energy storage materials 

for electromobility. Another focus 

is lightweight construction. Here, among 

other things, mixed metallic compounds 

and hybrid lightweight structures 

made of aluminium and CFRP for CO₂efficient 

mobility concepts are investigated. 

The newly developed processes 

aluminium laser polishing and high-temperature 

capillary gap brazing are already 

being used in industrial projects. 

Making Heat Flow Visible 

Laser processes are highly dynamic 

thermally induced processes that cannot 

be detected with the naked eye. 

High-speed visual cameras that are 

often used are not capable of visualis- 

ing the heat flow in the component. A 

contacting temperature measurement 

of the moving very small liquid metal is 

not possible. In addition, the processing 

zone should remain free of influences 

from the measurement system. This is 

exactly what thermographic cameras 

do, which provide high frame rates with 

high spatial resolutions at the same 

time. 

Specially Configured 

Thermographic Camera within 

Laser Material Processing 

Laser-based production involves special 

requirements on the use of a thermographic 

camera. One reason for this are 

the processing temperatures of typically 

500 °C to 2,000 °C. In addition, the components 

of the camera must be protected 

against sputters, caused by the machining 

process. If the laser manufacturing 

processes take place in process chambers 

under a specific atmosphere, the 

measurement section is enriched with a 

gas. Especially the optics of the camera 

must be protected from the reflected 

laser radiation. It is therefore equipped 

with a laser protection lens for solidstate 

lasers and a filter for through glass 

and high-temperature measurement. 

Due to these precautions, the camera can 

be used near the laser beams without any 

problems. 

Configured appropriately, the thermographic 

camera ImageIR® 8300 hp 

from InfraTec supports the LAC with 

its high spatial and temporal resolution. 

Using the camera's MicroScan function, 

images can be taken with a spatial resolution 

of more than one megapixel. The 

10 GigE interface allows fast data transmission 

up to 355 Hz in full frame mode. 

Due to the optical package consisting of 

a telephoto lens with 50 mm focal length 

and the close-up lens for reducing the 

minimum focusing distance down to 170 

mm, the researchers can easily adapt the 

camera to changing working distances 

and sizes of the measured objects. 



Laser camera: ImageIR® 8300 hp 

Fig. 1 (a) Test setup in laser cell 

TLC 1005, (b) 3D model process 

chamber, (c) Dimensions of 

solder sample 

LASERS ARE EXTREMELY 

VERSATILE TOOLS 

IN INDUSTRY AND 

MANUFACTURING 

TECHNOLOGY. 

Analysing the Temperature 

Control Behaviour During 

Laser Beam High-temperature 

Soldering 

The LAC of Aalen University, together 

with its industrial partner conntronic 

Prozess- und Automatisierungstechnik 

GmbH from Augsburg, is investigating 

laser high-temperature capillary gap 

brazing of corrosion-resistant steels 

for tube assemblies in automotive and 

mechanical engineering within the 

framework of the publicly funded research 

project “enAbLe”. In contrast to 

induction and furnace brazing, the laser 

beam serves as a flexible and highly efficient 

tool. The challenge lies on the one 

hand in the required highly pure reduction 

process environment to remove 

the oxide layers for good wetting of the 

copper solder and on the other hand 

in the homogeneous tempering of the 

joining zone. For homogeneous heating, 

the laser beam is controlled to the 

desired process temperature of 1,300 °C 

by means of a coaxially integrated highspeed 

pyrometer with sampling rates of 

several kilohertz. In addition to temperature 

control, the exposure strategy has 

a decisive influence on the formation of 

the temperature zones. Besides the FEM 

simulation, the thermographic camera 

is used for process development in the 

empirical experiments. 

The experiments take place in a sixaxis 

TLC 1005 laser cell with an infrared 

4 kW disc laser TruDisk 4002. The test 

geometry consists of a tube plug connection, 

austenitic chrome-nickel steel 

1.4301, with outer tube diameters of 10 

mm and 7.9 mm. Three weld spots offset 

by 120° fix the pipe-plug connection. The 

solder is pure copper from Voestalpine 

in the form of a solder ring (Fig. 1c). The 

oxygen-reduced process chamber used 

for the tests has a laser-permeable beam 

entry window in the lid. The soldering 

tests are carried out in a forming gas atmosphere 

with a residual oxygen content 

of less than 150 ppm. The atmosphere is 

monitored by means of a residual oxygen 

measuring device. During the process, 

the soldering assembly, clamped in a 

three-jaw chuck, rotates around the pipe 

axis by an external rotary machine axis. 

The laser beam is defocused to a diameter 

of 9 mm and radially tempering the 

outer surfaces of the joining zone (Fig. 

1b). The beam centre is oriented centrically 

to the solder ring. 

The laser soldering process is divided 

into three phases: heating, soldering with 

component rotation and cooling. During 

the heating phase of 10 s (Fig. 2 upper 

row), the laser heats the facing component 

surface to the control temperature 

of 1,300 °C in a stationary manner. During 

the soldering phase (Fig. 2 middle 

row) the assembly performs a complete 

rotation with an angular speed of 540 °/ 

min. After the copper solder depot has 

been molten, the solder gap filling starts 

at 31.9 seconds. Due to the lower emission 

of copper, the forming fillet appears 

cooler than the surrounding steel surface 

of the joining partners. Because of the very 

good thermal conductivity of the solder, 

the through heating of the inner tube also 

starts at this point (difference between 

picture at 16.3 s and picture at 31.9 s in 

Fig. 2). At the end of complete rotation 

and shutdown of the laser, the component 

cools to below 600 °C within 18 s (Fig. 2 

lower row). 

The measurement data of the thermographic 

camera allows a versatile process 

analysis afterwards. The diagram in figure 

3 shows the temperature-time sequence 

of two measurement points, P1 in the laser 

spot centre and P2 on the inner tube. The 

dynamic temperature changes in the gap 

filling process stand out in this context. 

Fig. 2 Process sequence for laser beam high-temperature capillary gap soldering of a 

tube plug-in connector 



Fig. 3 Analysis of the temperature-time sequence on the basis of the thermal image data 

Fig. 4 Cutted joining zone of a lasersoldered 

tube-plug-in connection in 

longitudinal direction. 

Figure 4 shows the longitudinal 

cross section through the faultless laser 

soldered tube plug connection. The presented 

sample shows a complete gap filling 

without porosity. The evenly formed 

grooves on both sides ensure a good 

distribution of force and low-turbulence 

flow inside the pipe. 

Due to the evaluation of further thermographic 

data, the temperature control 

strategy could be further optimised 

and soldering times of less than 10 s 

could be realised. 

Collecting Important Process 

Knowledge 

Regarding laser soldering, thermography 

provides important insights into 

process development. Thus, optimised 

path planning for optimal heating can 

be identified and at the same time 

the thermal load of the surrounding 

zones can be reduced. The LAC aims 

to achieve comparable results with 

similar tasks. With the help of the thermographic 

camera, for example, the 

temperature distribution gets recorded 

in each layer at the 3D metal printing 

process of selective laser melting. The 

focus lies primarily on the heating and 

cooling behaviour of the used materials, 

which has a direct effect on the 

structure quality that is formed.


Predictive Maintenance: 

The Wrong Solution to the 

Right Problem in Chemicals 

WIM GYSEGOM, SVEN HOUTHUYS, and JOEL THIBERT, McKinsey & Company 

Chemicals plants often 

have plenty of good data 

on equipment performance 

and reliability. A predictivemaintenance 

program 

might be the worst way to 

use it. 

IN THE CHEMICALS INDUSTRY, like many 

others, there is considerable excitement 

about the potential of advanced predictive-maintenance 

(PdM) approaches. 

The promise of these new techniques 

is tantalizing. Using machine-learning 

technologies to comb through historical 

performance and failure data, they 

aim to tell operators when and how a 

component is likely to go wrong in the 

future with a high level of predictability. 

This should reduce the impact of equipment 

failures—and the cost of efforts to 

prevent such failures—by turning inefficient, 

unplanned maintenance activities 

into efficient, planned ones. 

At first sight, chemicals plants seem 

like the ideal environment for PdM. 

High levels of automation and instrumentation, 

combined with rigorous 

maintenance record-keeping, create the 

rich data that machine-learning systems 

require. Moreover, most plants strive for 

stable operating conditions, potentially 

making it easier to spot patterns and 

trends. There’s also a compelling business 

case for improved reliability. Overall 

equipment effectiveness (OEE) losses 

due to unplanned maintenance range 

from 3 to 5 percent across the industry. 

Predicting Poor Results 

Take a closer look, however, and the 

potential of PdM in chemicals begins 

to evaporate, for four main reasons. 

AUTHORS: 

WIM GYSEGOM is a partner 

in McKinsey’s London office, where 

SVEN HOUTHUYS is an associate 

partner, and JOEL THIBERT is an 

associate partner in the Santiago office. 

• TOO LITTLE DATA. In a chemicals 

plant, predicting failures is harder 

than it first appears. Unplanned 

downtime is typically concentrated 

in a small number of large events. 

That means there are typically too 

few datapoints for PdM systems to 

learn from. 

• TOO LITTLE TIME. Even when it’s possible 

to create models with predictive 

power, they often work over time 

horizons that are too short to be useful 

in chemicals manufacturing. Predicting 

that a part will fail in two days 

or two weeks is useful in a truck or 

machine tool, but it may not help in a 

plant where shutdowns take several 

days and maintenance teams require 

months to plan interventions and 

source spare parts. 

• TOO LITTLE IMPACT. The impact from 

PdM is often low because plants 

operate critical assets with a high 

degree of redundancy and few single 

points of failure. If a pump stops 

unexpectedly, operators can often 

switch to a backup unit with little impact 

on production. 

• Too little savings. Finally, a focus 

on reducing unplanned downtime 

ignores the largest source of throughput 

losses in most plants. Shutdowns 

for planned maintenance events 

cause OEE losses of 5 to 10 percent on 

average, twice as much as unplanned 

stoppages. 

Towards Digital Reliability 

Do these challenges mean analytics 

provides little or no value in efforts to 

improve asset productivity in the chemicals 

sector? No. The industry is achieving 

considerable success with a range of 

digital reliability techniques, many of 

which are far cheaper and less complex 

to implement than advanced PdM. Take 

three prominent examples: 



Condition Monitoring 

Improving condition monitoring 

through better remote sensing can cut 

mean time-to-repair, significantly reducing 

the impact of equipment failures. At 

one chemical plant, a few critical pumps 

suffered repeated failures. No backups 

were available for these units, and the 

issue was a significant source of production 

losses at the plant. 

“We decided we couldn’t wait for the 

plant and reliability engineers to identify 

the root cause, redefine the pump’s technical 

specifications, and then procure 

replacements,” the plant’s maintenance 

manager told us. “So, we focused on mitigating 

the impact of the failures, rather 

than avoiding them.” 

The plant’s reliability team installed 

a handful of new sensors on the pumps 

and started to monitor their condition 

online in real time, allowing them to detect 

imminent failures a few hours before 

they occurred. By enabling maintenance 

personnel to be ready to intervene, this 

intervention reduced the mean time-torepair 

on these pumps from 6.5 2 Predictive 

maintenance: the wrong solution to 

the right problem in chemicals to around 

3 hours, cutting OEE losses by almost 

half and saving approximately 120,000 

US dollars for each failure. 

Smarter Capex Decision– 

Making 

Better data means better investment decisions, 

especially when it comes to the 

allocation of sustaining capex costs—or 

avoiding equipment failure by making 

the right, risk-informed capex decisions. 

Most chemical companies struggle to 

set the right level of sustaining capex, 

as they find it difficult to allocate funds 

across multiple plants and disparate asset 

types. 

This problem is ultimately about ensuring 

that resources are used to their 

maximum potential—which is exactly 

the question that zero-based budgeting 

(ZBB) has successfully addressed, 

through internal disciplines that assess 

all spending in terms of return on investment. 

The same techniques apply 

to capex investments in assets, or “asset 

ZBB,” which combines available historical 

data with local expertise to assess the 

potential impact of either replacing or 

not replacing particular equipment. The 

new approach allows all equipment renewal 

projects to be compared using the 

same yardstick: spend efficiency. 

In the words of a manager responsible 

for running one chemical manufacturer’s 

capital-planning process, “We 

used to have a formal process to capture 

and assess sustaining capex projects, but 

we had no clear way to rank-order projects 

and always ended up prioritizing those 

with immediate, visible impact. Now we 

are able to have a fact-based, data-driven 

discussion about risk and trade-offs, which 

has led us to spend less overall—and to 

manage what we do spend more wisely.” 

Root-Cause Problem Solving 

Better data also means better root-cause 

problem solving. That helps companies 

to prevent the recurrence of failures, to 

improve their failure-modes and-effects 

analysis (FMEA) processes, and to optimize 

preventative-maintenance plans. 

Together, those actions address the critical 

aspects of reliability performance, reducing 

both the impact of failures and the cost 

of preventing them. 

At one chemicals plant, for example, 

failures in a critical piece of equipment 

caused operators to activate an emergency 

shutdown three times in as many months. 

These shutdowns were inconvenient 

enough—but when the site team attempted 

to restart the plant, they found that the 

abrupt shutdown of the unit led to an accumulation 

of solids in key vessels and pipes. 

Fixing that problem led to lengthy delays 

in start-up and significant losses in output. 

To address the issue, the company applied 

a combination of traditional rootcause 

problem solving and smart analytical 

techniques. Analysis of process data helped 

them understand how and why solids were 

accumulating under emergency shutdown 

conditions. The issue was fixed with a 

combination of enhanced monitoring and 

changes to preventative maintenance plans. 

But the data driven insights also allowed 

the plant to revise its emergency shutdown 

procedures to stop the plant safely without 

causing the solids problem. That change reduced 

start-up time after any kind of emergency 

shutdown by 90 percent. 

The potential for digital reliability extends 

far beyond predictive maintenance. 

And for chemicals companies, we believe 

that these other digital approaches are 

both easier to implement and offer greater 

value. The highly instrumented nature of 

most chemical production facilities means 

many companies already have a rich, and 

largely untapped, source of data to support 

digital reliability efforts. For those plants 

that still don’t, then it’s time to “sensor 

up”: better data is the vital first step on the 

digital-reliability journey. 


TECHNOLOGY 

Industrial AI in Maintenance: 

False Hopes or Real 

ACHIEVEMENTS? 

Artificial intelligence (AI) is an umbrella term for a set of technologies in which 

computer systems are programmed to exhibit complex behaviour in challenging 

environments. AI is regarded as the major force driving innovation today. 

Authors: UDAY KUMAR, DIEGO GALAR and RAMIN KARIM, Luleå University of Technology 

FROM AN INDUSTRIAL point of view, AI technologies should be 

understood as methods and procedures that enable technical 

systems to perceive their environments through context and 

situation awareness. They are able to process what they have 

monitored and modelled, solve certain problems, find novel 

solutions never found by humans, make decisions, and learn 

from experience to be better able to manage the processes and 

tasks put under AI supervision, Figure 1. 

Machine learning (ML) is one area of artificial intelligence 

used by industry. Machines need data to learn, either large 

quantities of data for one-time analytical purposes, or streams 

of data from which learning is continuously taking place. Based 

on acquired data either on line or off line, machine learning 

can reduce complexity and detect events or patterns, make 

predictions, or enable actions to be taken without explicit programming 

in the form of the usual ‘if-then’ routines or without 

classic automation and control engineering, Figure 2. 

Figure 2: 

Roadmap 

from 

traditional 

automated 

process to 

Industrial AI 

Figure 1: Solution and knowledge extraction form asset data 


TECHNOLOGY 

AI technologies are expected to increase the efficiency 

and effectiveness of industrial processes. The primary goals 

are to reduce costs, save time, improve quality, and enhance 

the robustness of industrial processes. However, AI is not as 

well-used in industry as we might expect, given its potential. 

Enormous changes and high costs are needed to integrate AI 

applications into corporate structures and along the entire 

value-added chain. At this point, AI applications tend to be 

found in the areas of robotics, knowledge management, quality 

control, and maintenance analytics shifting from traditional 

approaches to predictive ones. 

A good field for AI in maintenance in industrial environments 

is the analysis and interpretation of sensor data, distributed 

throughout equipment and facilities. The Internet 

of Things (IoT), i.e. distributed data-suppliers and data-users 

capable of communicating with each other, is the basis for this 

use of AI. IoT acquires the data after pre-processing, records 

the status of all different aspects of the machines, and performs 

actions in process workflows on the basis of its analysis. Its 

central purpose is to identify correlations that are not obvious 

to humans to enable predictive maintenance (Figure 3), for example, 

when complex interrelated mechanical setting parameters 

have to be adjusted in response to fluctuating conditions 

in the environment to avoid compromising the asset’s health. 

Figure 3: 

Predictive 

maintenance 

supported 

by AI 

ASSET RELIABILITY 

PRACTITIONER 

[ARP] Training & Certification 

Improving the reliability and performance of an industrial facility is important. A top performing facility will be 

safer, have fewer environmental incidents, provide for job satisfaction and support financial reward for owners 

and shareholders. 

The Mobius Institute Asset Reliability Practitioner [ARP] training and certification program provides the 

knowledge, qualifications, and growth path to enable a program to be run successfully. 

[ARP-A] 

ARP-Advocate: 

Teaches the big picture 

including terminology. 

[ARP-E] 

ARP-Engineer: 

Educates on technical 

aspects of a reliability 

maintenance program. 

[ARP-L] 

ARP-Leader: 

Trains leaders on how to 

successfully implement 

reliability and improvement 

initiatives involving an 

entire organization. 

Choose the ARP course that is right for you! 

Visit www.mobiusinstitute.com/arp for more information

TECHNOLOGY 

Industrial AI’s capacity to analyze very large amounts of 

high-dimensional data can change the current maintenance 

paradigm and shift from preventive maintenance systems to 

new levels. The key challenge, however, is operationalizing predictive 

maintenance, and this is much more than connecting 

assets to an AI platform, streaming data, and analyzing those 

data. By integrating conventional data such as vibration, current 

or temperature with unconventional additional data, such 

as audio and image data, including relatively cheap transducers 

such as microphones and cameras, Industrial AI can enhance 

or even replace more traditional methods. AI’s ability to predict 

failures and allow planned interventions can be used to 

reduce downtime and operating costs while improving production 

yield. For example, AI can extend the life of an asset beyond 

what is possible using traditional analytics techniques by 

combining data information from designer and manufacturer, 

maintenance history, and Internet of Things (IoT) sensor data 

from end users, such as anomaly detection in engine-vibration 

data, images and video of engine condition. This information 

fusion during the lifecycle of the asset is called product lifecycle 

management (PLM). 

Explainable AI in Maintenance 

Advances in AI for maintenance analytics are often tied to 

advances in statistical techniques. These tend to be extremely 

complex, leveraging vast amounts of data and complex algorithms 

to identify patterns and make predictions. This 

complexity, coupled with the statistical nature of the relationships 

between input data that the asset provides, makes them 

difficult to understand, even for expert users, including the 

system developers, Figure 4. This makes explainability a major 

concern. 

Figure 4: Engineers and data scientist must co-create the AI 

solution for maintenance together 

While increasing the explainability of AI systems can be 

beneficial for many reasons, there are challenges in implementing 

explainable AI. Different users require different 

forms of explanation in different contexts, and different contexts 

give rise to different needs. To understand how an AI 

system works in the maintenance domain, users might wish to 

know which data the system is using, the provenance of those 

data, and why they were selected; how the model and prediction 

work, and which factors influence a maintenance decision; 

and why a particular output is obtained. To understand what 

type of explanation is necessary, careful stakeholder engage- 

ment and well-thought-out system design are both necessary 

as can be seen in figure 5. 

Figure 5: Architecture of explainable AI systems for Maintenance 

Decisions 

There are various approaches to creating interpretable systems. 

Some AI is interpretable by design; these systems tend to 

be kept relatively simple. An issue with them is that they cannot 

get as much customization from vast amounts of data as 

more complex techniques, such as deep learning. This creates a 

performance-accuracy trade-off in some settings, and the systems 

might not be desirable for those applications where high 

accuracy is prized. In other words, maintainers must accept 

more black boxes. 

In some AI systems – especially those using personal data or 

those where proprietary information is at stake – the demand 

for explainability may interact with concerns about privacy. In 

areas such as healthcare and finance, for example, an AI system 

might be analyzing sensitive personal data to make a decision 

or recommendation. In determining the type of explainability 

that is desirable in these cases, organizations using AI will 

need to take into account the extent to which different forms 

of transparency might result in the release of sensitive insights 

about individuals or expose vulnerable groups to harm. 

In the area of maintenance, when the AI recommends a 

maintenance decision, decision makers need to understand 

the underlying reason. Maintenance analytics developers need 

to understand what fault features in the input data are guiding 

the algorithm before accepting auto-generated diagnosis 

reports, and the maintenance engineer needs to understand 

which abnormal phenomena are captured by the inference algorithm 

before following the repair recommendations. 

One of the proposed benefits of increasing the explainability 

of AI systems is increased trust in the system. If maintainers 

understand what led to an AI-generated decision or recommendation, 

they will be more confident in its outputs. But the 

link between explanations and trust is complex. If a system 

produces convincing but misleading explanations, users might 

develop a false sense of confidence or understanding. They 

might have too much confidence in the effectiveness or safety 

of systems, without such confidence being justified. Explanations 

might help increase trust in the short term, but they do 

not necessarily help create systems that generate trustworthy 

outputs or ensure that those deploying the system make trustworthy 

claims about its capabilities. 

REFERENCES: 

Galar, Diego, Pasquale Daponte, and Uday Kumar. Handbook of Industry 4.0 and SMART Systems. CRC Press, 2019. 

Galar, Diego. Artificial intelligence tools: decision support systems in condition monitoring and diagnosis. Crc Press, 2015. 

Galar, Diego, Uday Kumar, and Dammika Seneviratne. Robots, Drones, UAVs and UGVs for Operation and Maintenance. CRC Press, 2020. 


VIBRATION ANALYSIS 

THERMAL IMAGING 

ULTRASOUND 

MEASUREMENT 

eyesight – hearing – sensitivity 

we have in common 

MASTER THE LANGUAGE OF YOUR MACHINERY 

WWW.ADASH.COM

VIBGUARD® IIoT 

The world‘s first and only state-of-the-art solution for 

predicitive maintenance in Industry 4.0 environments 

Online Condition Monitoring System: 

• Available with 6 up to 20 analogue channels 

• Applicable in any Industry 4.0 environment 

• Featuring MQTT protocol for global 

remote status overview 

• Process quality enhancement due to 

seamless integration into control systems 

www.VIBGUARD-IIoT.com

Maintworld 1/2020

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?