applied

sciences
Review
On Predictive Maintenance in Industry 4.0: Overview, Models,
and Challenges
Mounia Achouch 1,2,3, *, Mariya Dimitrova 1 , Khaled Ziane 3 , Sasan Sattarpanah Karganroudi 1,4 ,
Rizck Dhouib 1 , Hussein Ibrahim 1,3 and Mehdi Adda 2

1 Institut Technologique de Maintenance Industrielle ITMI, 175 rue de la Vérendrye,

Sept-Îles, QC G4R 5B7, Canada
2 Département de Mathématique, Informatique et Génie, Université du Québec à Rimouski,
Rimouski, QC G56 3A1, Canada
3 Centre de Recherche et D’innovation en Intelligence Énergétique CR2Ie, 175 rue de la Vérendrye,
Sept-Îles, QC G4R 5B7, Canada
4 Department of Mechanical Engineering, Université du Québec à Trois-Rivières,
Trois-Rivières, QC G8Z 4M3, Canada
* Correspondence: mounia.achouch@cegepsi.ca

Abstract: In the era of the fourth industrial revolution, several concepts have arisen in parallel with
this new revolution, such as predictive maintenance, which today plays a key role in sustainable
manufacturing and production systems by introducing a digital version of machine maintenance.
The data extracted from production processes have increased exponentially due to the proliferation of
sensing technologies. Even if Maintenance 4.0 faces organizational, financial, or even data source and
machine repair challenges, it remains a strong point for the companies that use it. Indeed, it allows
for minimizing machine downtime and associated costs, maximizing the life cycle of the machine,
and improving the quality and cadence of production. This approach is generally characterized
Citation: Achouch, M.; Dimitrova, M.;
by a very precise workflow, starting with project understanding and data collection and ending
Ziane, K.; Sattarpanah Karganroudi,
with the decision-making phase. This paper presents an exhaustive literature review of methods
S.; Dhouib, R.; Ibrahim, H.; Adda, M.
On Predictive Maintenance in
and applied tools for intelligent predictive maintenance models in Industry 4.0 by identifying and
Industry 4.0: Overview, Models, and categorizing the life cycle of maintenance projects and the challenges encountered, and presents the
Challenges. Appl. Sci. 2022, 12, 8081. models associated with this type of maintenance: condition-based maintenance (CBM), prognostics
https://doi.org/10.3390/app12168081 and health management (PHM), and remaining useful life (RUL). Finally, a novel applied industrial
workflow of predictive maintenance is presented including the decision support phase wherein
Academic Editors: Sławomir
Nowaczyk, Mohamed-Rafik
a recommendation for a predictive maintenance platform is presented. This platform ensures the
Bouguelia and Hadi Fanaee management and fluid data communication between equipment throughout their life cycle in the
context of smart maintenance.
Received: 27 June 2022
Accepted: 10 August 2022
Keywords: Industry 4.0; predictive maintenance (PdM) and challenges; condition-based maintenance
Published: 12 August 2022
(CBM); prognostics and health management (PHM); remaining useful life (RUL); predictive maintenance
Publisher’s Note: MDPI stays neutral workflow; artificial intelligence; decision making
with regard to jurisdictional claims in
published maps and institutional affil-
iations.

1. Introduction
In the current economic context marked by fierce globalization and increasingly de-
Copyright: © 2022 by the authors.
manding markets, industries are driven to improve the performance and efficiency of their
Licensee MDPI, Basel, Switzerland.
production lines to strengthen their competitiveness and satisfy their customers. Connectiv-
This article is an open access article ity, data, new devices, inventory reduction, customization, and controlled production have
distributed under the terms and given birth to what is called Industry 4.0, which today seems unstoppable [1]. This implies
conditions of the Creative Commons the need to apply automation techniques to integrate all the new technologies that will sub-
Attribution (CC BY) license (https:// sequently increase productivity [2]. The technologies of the Internet of Things (IoT) and Big
creativecommons.org/licenses/by/ Data, and the integration of artificial intelligence (AI) methods and cyber-physical systems
4.0/).

Appl. Sci. 2022, 12, 8081. https://doi.org/10.3390/app12168081 https://www.mdpi.com/journal/applsci

Appl. Sci. 2022, 12, x FOR PEER REVIEW 2 of 23

Appl. Sci. 2022, 12, 8081 2 of 22

Things (IoT) and Big Data, and the integration of artificial intelligence (AI) methods and
cyber-physical systems (CPS) play an important role in this context by introducing cogni-
tive automation and, consequently, implementing the concept of intelligent production,
(CPS)
leadingplayto an important
intelligent role in this
products andcontext
services.byThis
introducing
innovativecognitive
approach automation and, conse-
leads companies to
quently, implementing the concept of intelligent production, leading to intelligent products
meet the challenges of a much more dynamic environment. In this regard, companies are
and services. This innovative approach leads companies to meet the challenges of a much
able to maximize the life of their equipment while avoiding unplanned downtime and
more dynamic environment. In this regard, companies are able to maximize the life of their
minimizing energy consumption and costs through the application of predictive mainte-
equipment while avoiding unplanned downtime and minimizing energy consumption and
nance [3]. Predictive maintenance has become a promising approach, providing solutions
costs through the application of predictive maintenance [3]. Predictive maintenance has
for the remaining life of equipment through the prediction of data collected by various
become a promising approach, providing solutions for the remaining life of equipment
sensors on equipment [4]. It has reached critical importance for industries due to the in-
through the prediction of data collected by various sensors on equipment [4]. It has reached
creasing complexity of interactions between different production activities in increasingly
critical importance for industries due to the increasing complexity of interactions between
large manufacturing ecosystems. Figure 1 shows the global trend towards the application
different production activities in increasingly large manufacturing ecosystems. Figure 1
of this type of smart maintenance with a prediction of 2022 to 2030. In general, the con-
shows the global trend towards the application of this type of smart maintenance with a
temporary maintenance approaches vary depending on the different learning models
prediction of 2022 to 2030. In general, the contemporary maintenance approaches vary
used and the
depending ondifferent problems
the different learningencountered
models used by and
the machines/equipment.
the different problemsHowever,
encounteredthe
fault diagnosis and prognosis step in predictive maintenance must
by the machines/equipment. However, the fault diagnosis and prognosis step in predictivebe very precise and
clear [5]. Given
maintenance mustthebegoal
veryofprecise
building andanclear
intelligent manufacturing
[5]. Given system, the
the goal of building detection,
an intelligent
interpretation and prediction of failures that occur in equipment
manufacturing system, the detection, interpretation and prediction of failures that are based on data ac-
occur
quired from sensors on the equipment [4]. However, adopting
in equipment are based on data acquired from sensors on the equipment [4]. However,these technological ad-
vances does
adopting nottechnological
these come alone. Itadvances
is important
doestonot have a good
come ideaItofisthe
alone. benefits to
important and chal-
have a
good idea of the benefits and challenges of applying Maintenance 4.0 whether it is ondata
lenges of applying Maintenance 4.0 whether it is on the financial, organizational, the
source, ororganizational,
financial, equipment repair side.
data Predictive
source, maintenance
or equipment repairindeed consists ofmaintenance
side. Predictive data mining
for the consists
indeed formulation of machine
of data mining for learning models that
the formulation managelearning
of machine to gain knowledge
models thatand pre-
manage
dict the state of health of equipment. In this regard, predictive maintenance
to gain knowledge and predict the state of health of equipment. In this regard, predictive offers meth-
ods such as Condition-Based
maintenance offers methods suchMaintenance (CBM), Prognostics
as Condition-Based Maintenanceand Health
(CBM),Management
Prognostics
(PHM), and Remaining Useful Life (RUL).
and Health Management (PHM), and Remaining Useful Life (RUL).

Figure 1.
Figure 1. Size of Maintenance 4.0 market worldwide in 2020 and 2021 with forecast
forecast for
for future
future years
years
indexed by
indexed by ** (from
(from 2022
2022 to
to 2030)
2030) [6,7].
[6,7].

This
This article
article aims
aims atat presenting
presenting anan exhaustive
exhaustive review
review of of methods
methods andand tools
tools used
used inin
smart
smart maintenance
maintenance to to offer
offer an academic
academic and technical reference
reference presenting
presenting challenges
challenges and
and
opportunities
opportunities in this field.
field. With
With this
this aim,
aim, the
the article
article is
is divided
divided into
into nine
nine sections,
sections, starting
starting
with
with an
an introduction
introduction in in Section
Section 11 and
and exploring
exploring inin Section
Section 22 the
the concept
concept of
of Industry
Industry 4.0
4.0 as
as
the latest technology to evolve industrial domains, considering the safety
the latest technology to evolve industrial domains, considering the safety and human chal- and human
challenges. Section
lenges. Section 3 illustrates
3 illustrates the the evolution
evolution of in-plant
of in-plant maintenance
maintenance overover
the the years
years andandfo-
focuses
cuses on predictive maintenance, and its hardware and tools. Section 4 presents the
on predictive maintenance, and its hardware and tools. Section 4 presents the
challenges faced when applying this intelligent maintenance while Section 5 reveals its
workflow. Section 6 focuses on the models used in the application of Predictive Mainte-
nance 4.0. Section 7 presents a PdM case study on an industrial centrifugal compressor.
Appl. Sci. 2022, 12, x FOR PEER REVIEW 3 of 23

challenges faced when applying this intelligent maintenance while Section 5 reveals its
Appl. Sci. 2022, 12, 8081 workflow. Section 6 focuses on the models used in the application of Predictive Mainte-
3 of 22
nance 4.0. Section 7 presents a PdM case study on an industrial centrifugal compressor.
Section 8 covers discussions and recommendations of PdM based on technical and re-
search
Sectionexperiments, and finally,
8 covers discussions and Section 9 presents of
recommendations a conclusion
PdM basedof
onthis research
technical andwork.
research
experiments, and finally, Section 9 presents a conclusion of this research work.
2. Industry 4.0
2. Industry 4.0
When computers were introduced in Industry 3.0, the addition of a whole new tech-
nology Whenhad acomputers
disruptivewere effect [8]. Today,inand
introduced in the future
Industry 3.0, theinaddition
Industryof4.0, computers
a whole and
new tech-
industrial
nology had equipment
a disruptive areeffect
connected and communicate
[8]. Today, and in the futurewithin each other to
Industry ultimately
4.0, computers make
and
decisions
industrialwithout
equipment human intervention.
are connected and The combination
communicate withofeachcyber-physical systems,make
other to ultimately the
decisions
Internet ofwithout human
Things (IoT), intervention.
and the InternetThe combination
of Systems makeof cyber-physical
Industry systems,
4.0 possible and thethe
Internet
smart of Things
factory (IoT),
a reality. Byand the Internet
supporting of machines
smart Systems make Industrysmarter
that become 4.0 possible
as more anddata
the
smart
is factory
accessed, a reality.
factories willBybecome
supporting moresmart machines
efficient that become
and productive andsmarter
produce asless
more data
waste.
is accessed,itfactories
Ultimately, will become
is the network of these more efficient
machines thatandareproductive and produce
digitally connected less waste.
and create and
Ultimately, it is the network of these machines
share information that gives the true power of Industry 4.0. that are digitally connected and create and
shareIndustry
information that gives the true power of Industry 4.0.
4.0 is revolutionizing the way companies make, improve, and distribute
their Industry
products.4.0 is revolutionizing
It has the waythe
radically transformed companies
industrialmake, improve, and distribute
and manufacturing world by
their products.
enabling It has radicallybetween
intercommunication transformed the industrial
equipment throughand themanufacturing
Internet of Things, worldBig by
enabling
Data, intercommunication
computer intelligence, and between equipment through
decision-making systemsthe Internet
[9]. Indeed, of this
Things, Big tech-
digital Data,
computer
nology willintelligence,
allow companies and decision-making
to react faster tosystems
market[9]. Indeed,
changes, thismore
offer digital technology
personalized
will allow companies to react faster to market changes, offer
products, and increase operational efficiency thanks to the informed Big Data that more personalized products,
helps
and increase operational efficiency thanks to the informed
produce goods more efficiently and productively along the value chain [10]. These Big Data that helps produce
pro-
goods
vide more efficiently
real-time details onand theproductively along the
status of machines, suchvalue chain [10].
as leakage These
location provide
and real-
operating
time details
speed. on the status
This technology of machines,
enables such of
the deployment as smart
leakage location[11]
industries and operating
since speed.
it reproduces
This technology enables the deployment of smart industries [11]
the information received in real-time throughout the production and supply chain. In or- since it reproduces the
information received in real-time throughout the production and
der to benefit from these improvements, several components such as Industrial Internet supply chain. In order to
benefit from these improvements, several components such as Industrial
of Things (IIoT) systems and physical network systems are essential for the collection, Internet of Things
(IIoT) systems
processing, andand physical
storage network
of data [12].systems
To gainaretheessential
advantages for the
andcollection,
achieve an processing, and
efficient fac-
storage of data [12]. To gain the advantages and achieve an efficient factory, the Industry 4.0
tory, the Industry 4.0 model proposes to use multidisciplinary technologies. Although
model proposes to use multidisciplinary technologies. Although some of them have been
some of them have been studied for a long time, they are not yet ripe for mass industrial
studied for a long time, they are not yet ripe for mass industrial deployment [13]. In fact,
deployment [13]. In fact, Industry 4.0 devices can automatically communicate with each
Industry 4.0 devices can automatically communicate with each other, allowing them to
other, allowing them to coordinate with each other and with other remote systems over
coordinate with each other and with other remote systems over the Internet. Figure 2
the Internet. Figure 2 provides an overview of the components of Industry 4.0.
provides an overview of the components of Industry 4.0.

Figure 2. Components of Industry 4.0 technologies in the context of intelligent manufacturing.

Figure 2. Components of Industry 4.0 technologies in the context of intelligent manufacturing.
Applying the components of this fourth industrial revolution brings a maintenance
Applying the to
strategy that tries components
extend theof this fourth
useful life of industrial
the equipmentrevolution bringsthe
and reduce a maintenance
costs thanks
strategy that tries to extend the useful life of the equipment and reduce
to continuous and instantaneous communication between different machines/equipment the costs thanks
to continuous
either and instantaneous
in the production communication
or the supply chain. One between
of thedifferent
pillars ofmachines/equipment
this last industry is
either in the
predictive production which
maintenance, or the supply chain.the
tries to apply One of thetechnologies
recent pillars of this last industry
to change is pre-
the scenarios
dictive
and avoidmaintenance,
any type of which tries to or
breakdown apply the recent
anomaly technologies
through prediction,tothe
change the scenarios
reduction of costs,
and the reduction of downtimes.
Regarding the presented basic understanding of the fourth industrial revolution and
some of the factors that characterize it, it is important to investigate the reasons for the security
challenges that stand in the way of Industry 4.0 and the human aspect of Industry 4.0.
Appl. Sci. 2022, 12, 8081 4 of 22

2.1. Security Challenges in the Context of Industry 4.0

Technological evolution has led to significant changes in the way organizations operate
on a daily basis, creating unprecedented pressure for efficiency and performance. Indeed,
organizations rely heavily on the performance of their information systems to develop their
activities, due to their comfort and the emergence of new technologies [14]. However, cloud-
based systems, the Internet of Things (IoT), and the interconnectedness of smart industries
have led to a significant increase in unexpected security breaches [15]. Industry 4.0 is more
vulnerable to cyber-espionage or cyber-sabotage due to digitalized and connected business
processes. Currently, we are witnessing the development of well-organized groups of cyber
criminals with excellent skills and accustomed to targeting specific industries, with the
aim of hacking sensitive information and intellectual property. The problem associated
with this phenomenon is not limited to its impact on sales, but also includes damage to the
organization’s image, loss of knowhow, and reduction in the level of competitiveness of
affected organizations [16,17].
One of the characteristics of Industry 4.0 is the ability to connect across organizational
environments, which has the potential to make the AP provisioning chain more efficient.
However, supply chain systems have inherent security vulnerabilities that are exploited by
attackers. One such security vulnerability is at the supplier level, which is vulnerable to
phishing attacks and theft of privileged credentials, resulting in massive data exposure. The
main vulnerability lies at the top of the supply chain and affects the rest of the organizational
processes through the actors that depend on it [16]. Security awareness, access control
through authentication mechanisms, cryptographic processes, and behavioral analysis are
the security mechanisms that can help prevent supply chain hacking [14]. Denial of service
(DoS) is the act of making a system or application unavailable. For example, a DoS attack
can be achieved by bombarding a server with a large number of requests to consume all
available system resources, passing malformed input data to the server that can crash a
process, infiltrating a virus, or destroying or disabling a sensor in a system, not allowing it
to function normally [16]. Industry 4.0 relies on a large number of interconnected systems
and processes, and DoS attacks are a very significant threat in such environments [18].
The transition to Industry 4.0 is a monumental task that will impact many areas of
today’s manufacturing industry, including security. The majority of manufacturing com-
panies are not fully aware of the security risks associated with adopting the Industry 4.0
paradigm [15]. Normally, they only address security issues when a serious incident oc-
curs. Therefore, it is critical and essential that organizations adopt the development of
a strategy to deploy and manage the security compliance processes that Industry 4.0
requires, including reducing the organization’s exposure and effectively managing the
mitigation process [14].

2.2. Human Aspects in the Context of Industry 4.0

To address the human-related aspect in the context of Industry 4.0, there is an ever-
increasing interest in research and industrial practices where humans are placed at the
center of design in all disciplines [19]. Human intelligence and intervention continue
to play a key role due to the safety, security, and social aspects and the uncertainties
posed by these autonomous and intelligent systems. In addition, and parallel with the
advanced technologies of these intelligent systems, the role of humans has evolved from
low-level operations that can be dangerous, difficult, and boring to highly specialized
and safe tasks [20]. However, humans may feel that they are easily changed due to the
implementation of technology. In addition to technical skills, it has been pointed out
that human work in the manufacturing sector increasingly requires technological skills,
social and communication skills, as well as team skills and self-management skills [19,21].
The essential skills to perform the tasks must be identified and training provided to meet
the requirements. The person should have more opportunities for autonomous decision-
making, diversity in the workplace, and social interaction [18]. He is also seen with his
 cation skills, as well as team skills and self-management skills [19,21]. The essential skills
to perform the tasks must be identified and training provided to meet the requirements.
The person should have more opportunities for autonomous decision-making, diversity
in the workplace, and social interaction [18]. He is also seen with his values, attitudes, and
Appl. Sci. 2022, 12, 8081 respect for others, which separates him from technological devices, and this must 5 of 22 be em-
phasized in the management processes [22].

3.values,
Evolution of Industrial
attitudes, and respectMaintenance
for others, which separates him from technological devices,
and As
this explained
must be emphasized in the management
in the previous processes
section, the concept[22].
of Industry 4.0 leads to a data-
driven connected
3. Evolution factory.Maintenance
of Industrial Based on this concept, the dominant trend in maintenance is to
move away from costly reactive maintenance to preventive and predictive maintenance,
As explained in the previous section, the concept of Industry 4.0 leads to a data-
called
drivenalso smart maintenance.
connected factory. Based on Over
thisthe course
concept, theofdominant
industrial revolutions,
trend as shown
in maintenance is to in Fig-
ure
move3, maintenance
away from costly strategies
reactive have undergone
maintenance a gradual
to preventive andevolution
predictiveand it is currently a
maintenance,
continuous process
called also smart [23]. Indeed,
maintenance. thethe
Over philosophy of reactiverevolutions,
course of industrial or corrective maintenance
as shown in is
more
Figurecommon in manufacturing
3, maintenance plants
strategies have that are
undergone understaffed
a gradual andand
evolution unable to retaina skilled
it is currently
continuous process
maintenance [23]. Indeed,
personnel. the philosophy
Industries have struggledof reactive or corrective
for years to abandonmaintenance is
this maintenance
more common in manufacturing plants that are understaffed and unable to
philosophy because it is costly and often results in significant unplanned downtime and retain skilled
maintenance personnel. Industries have struggled for years to abandon this maintenance
increased costs [24]. Preventive maintenance is a set of actions aimed at preventing fail-
philosophy because it is costly and often results in significant unplanned downtime and
ures, reducing the risk of failure and the number and duration of unscheduled shutdowns,
increased costs [24]. Preventive maintenance is a set of actions aimed at preventing failures,
which
reducingimplies anofextension
the risk failure andofthe
the equipment’s
number life and
and duration consists of shutdowns,
of unscheduled interveningwhichin a system
before a failure occurs [25].
implies an extension of the equipment’s life and consists of intervening in a system before
a failure occurs [25].

Figure 3. Evolution of maintenance activities and methods.

Figure 3. Evolution
3.1. Predictive of maintenance activities and methods.
Maintenance
Predictive maintenance (PdM) is a recent preventive maintenance approach that
3.1. Predictive
consists Maintenance
of improving the performance and efficiency of the manufacturing process by
increasing the life
Predictive span of equipment
maintenance (PdM) and ensuring
is a recent sustainable
preventive operational management.
maintenance approach that con-
This implies, on the one hand, a decrease in downtime and the number
sists of improving the performance and efficiency of the manufacturing process of unnecessary stops, by in-
accompanied by a reduction in repair costs, by offering the possibility
creasing the life span of equipment and ensuring sustainable operational management. of interventions
through the prediction of failures [26]. Intelligent predictive maintenance strategies are
This implies, on the one hand, a decrease in downtime and the number of unnecessary
now being implemented by manufacturing companies. This implementation is done by
stops, accompanied by a reduction in repair costs, by offering the possibility of interven-
evaluating the remaining life of the elements responsible for the failure and by allowing
tions through
the remote andthe prediction
real-time of failures
monitoring [26]. Intelligent
of equipment predictive
failures. The maintenance
latter need strategies
detection and
are now being implemented by manufacturing
diagnosis in order for the equipment to function properly. companies. This implementation is done
by evaluating
Predictivethe remaining
maintenance lifelatest
is the of theform
elements responsible
of maintenance, for the
offering the failure
longest and by allow-
life and
ing the remote
highest and
reliability real-time monitoring
of equipment of equipment
(shown in Figure 4), and thefailures. The latter need
most environmentally detection
sound
and cost-effective solutions [27]. The maintenance method
and diagnosis in order for the equipment to function properly. used to troubleshoot by going
down to the source is called proactive maintenance. This maintenance method, which
is very effective when applied in conjunction with predictive maintenance, is becoming
increasingly popular [28].
 creasingly popular [28].
Predictive maintenance is the latest form of maintenance, offering the longest life and
highest reliability of equipment (shown in Figure 4), and the most environmentally sound
and cost-effective solutions [27]. The maintenance method used to troubleshoot by going
down to the source is called proactive maintenance. This maintenance method, which is
Appl. Sci. 2022, 12, 8081 6 of 22
very effective when applied in conjunction with predictive maintenance, is becoming in-
creasingly popular [28].

Figure 4. Potential failure diagram presenting inspection intervals and predictive maintenance.

3.2. Predictive Maintenance Tools and Materials

At4.
Figure
Figure 4. the beginning
Potential
Potential failure of the 21st
failure diagram
diagram century,
presenting
presenting and in
inspection
inspection the era
intervals
intervals andofpredictive
and the fourth
predictive industrial revolut
maintenance.
maintenance.
computational and advanced visualization tools based on the latest technologies have
3.2. Predictive Maintenance Tools and Materials
3.2. Predictive
come the main Maintenance Tools and
and necessary Materials
components of digital transformation in Industry 4.0. T
At the beginning of the 21st century, and in the era of the fourth industrial revolution,
have been
At adopted by
the beginning manufacturing
of the companies
21st century, and in the era ofin
themultiple industrial
fourth industrial
computational and advanced visualization tools based on the latest technologies have
applications a
revolution,
computational
more and
specifically, advanced visualization
in necessary
predictivecomponents tools
maintenance, based on
named the latest technologies
maintenance have be- In the
4.0 [29,30].
become the main and of digital transformation in Industry 4.0.
come
lowing the main and
subsections,necessary components
thebymain of
technologicaldigital transformation
tools in
applied in Industry 4.0. They
They have been adopted manufacturing companies multipleinindustrial
maintenance 4.0 is presen
applications
have been adopted
and, more by manufacturing
specifically, companies innamed
in predictive maintenance, multiple industrial applications
maintenance 4.0 [29,30]. Inand,the
more specifically,
following in
subsections,predictive
the main maintenance,
technological named
tools maintenance
applied in 4.0
maintenance [29,30].
4.0 is In the fol-
presented.
3.2.1. Cyber-Physical Systems
lowing subsections, the main technological tools applied in maintenance 4.0 is presented.
3.2.1.The most recent
Cyber-Physical advancement in intelligently connected production devices and s
Systems
3.2.1. Cyber-Physical
sors, The
andmost
autonomous Systemsintelligent
recent advancement in monitoring, control, sensing,
intelligently connected production and diagnostic
devices and sen-systems
known as “cyber-physical systems (CPS),” which are outfitted with
sors, and autonomous intelligent monitoring, control, sensing, and diagnostic systemssen-
The most recent advancement in intelligently connected production a
devices variety
and of compu
are
sors,
tional and
knownand autonomous intelligent
as “cyber-physical
physical methods systems monitoring,
and(CPS)”,
toolswhichcontrol, sensing,
are outfitted
that are perfectly and
withdiagnostic
a variety
suited systems
of computa-
to meeting are
human ne
known
tional as “cyber-physical
and physical methods systems
and (CPS),”
tools that which
are are outfitted
perfectly suited towith a variety
meeting human of needs
computa-
[31].
[31]. Five-stage CPS architecture (5C architecture) was proposed by [32] (see Figure
tional and physical
Five-stage methods(5C
CPS architecture andarchitecture)
tools that arewas perfectly suited
proposed to meeting
by [32] human
(see Figure 5). needs
These
These stages provide a simpler technique to design and practice a step-by-step CPS fr
[31].
stagesFive-stage
provide a CPS architecture
simpler technique(5C architecture)
to design was proposed
and practice by [32]
a step-by-step CPS(see
from Figure 5).
the data
the data
These
collection collection
stages to thestage
provide
stage afinal to the
simpler final
technique
analysis analysis
to design
and value and
andvalue
generation stage.generation
practice stage.
a step-by-step CPS from
the data collection stage to the final analysis and value generation stage.

Figure 5. CPS Architecture levels [33].

5. CPS
Figure 5.
Figure CPSArchitecture
Architecturelevels [33].[33].
levels
3.2.2. Industrial Internet of Things
Connecting machines, devices, and systems is the most fundamental step in imple-
menting Internet of Things (IoT) applications [31]. The IoT concept provides convenience
in industrial environments, where it is called Industrial Internet of Things (IIoT) [26]. IIoT
is considered the main factor behind the principle of Industry 4.0 [32]. It is a network
 Connecting machines, devices, and systems is the most fundamental step in imple-
menting Internet of Things (IoT) applications [31]. The IoT concept provides convenience
in industrial environments, where it is called Industrial Internet of Things (IIoT) [26]. IIoT
Appl. Sci. 2022, 12, 8081 is considered the main factor behind the principle of Industry 4.0 [32]. It is a network 7 of 22 that
connects cyber-physical systems and provides interconnection and interaction between
physical devices in the process, enabling the automatic collection and retrieval of a huge
flow
thatof data [8].
connects This constitutes
cyber-physical the notion
systems of Big interconnection
and provides Data. IIoT alsoand
offers the possibility
interaction be- of
transmitting data via the Internet, and it is the atmosphere that allows
tween physical devices in the process, enabling the automatic collection and retrieval direct access to
process data,
of a huge flowvirtualization of resources,
of data [8]. This constitutesinterconnection,
the notion of Big cooperation,
Data. IIoT alsointercommunica-
offers the
possibility of transmitting data via the Internet, and it is the atmosphere
tion, and machine-to-machine interaction in a transparent manner and without that allows directhuman
access to process
intervention [33]. data, virtualization of resources, interconnection, cooperation, intercom-
munication, and machine-to-machine interaction in a transparent manner and without
human intervention [33].
3.2.3. Big Data
Collecting,
3.2.3. Big Data processing, and analyzing real-time Big Data from cyber-physical systems
is a strategic phase
Collecting, for the and
processing, intelligent
analyzingtransformation of the
real-time Big Data frommaintenance
cyber-physicalfunction,
systems espe-
cially with respect
is a strategic phase to
forfailure prediction,
the intelligent planning,ofand
transformation risk management
the maintenance function,[34]. This is done
especially
with respect to failure prediction, planning, and risk management [34].
through the planning and optimization of interventions using artificial intelligence This is done tools
through the planning and optimization of interventions using artificial
and techniques such as machine learning and deep learning or through statistical intelligence toolsmodels
and techniques such as machine learning and deep learning or through statistical models
and approaches based on the data and information collected by the different sensors [10].
and approaches based on the data and information collected by the different sensors [10].
The characterization of massive data or Big Data is usually done according to three “V’s”,
The characterization of massive data or Big Data is usually done according to three “V’s”,
the
theV’s
V’sofofVolume, Varietyand
Volume, Variety andVelocity,
Velocity,
to to which
which other
other complementary
complementary “V’s”“V’s” are added,
are added,
such as Value and Veracity/Validity (See
such as Value and Veracity/Validity (See Figure 6).Figure 6).

Figure 6. 3V model extended to the 5V of Big Data.

Figure 6. 3V model extended to the 5V of Big Data.
3.2.4. Digital Twin
3.2.4. Digital Twin
A Digital Twin (DT) is a digital or virtual copy of physical assets or products. The
termA Digital Twincoined
was originally byaDr.
(DT) is Michael
digital or Grieves
virtual in 2002of
copy [35]. NASA assets
physical was oneorofproducts.
the first The
to use the technology for space exploration [36]. DTs connect the real and virtual world
term was originally coined by Dr. Michael Grieves in 2002 [35]. NASA was one of the first
by collecting real-time data from the installed sensors. The collected data is either locally
to use the technology for space exploration [36]. DTs connect the real and virtual world
decentralized or centrally stored in a cloud. The data is then evaluated and simulated
byincollecting real-time
a virtual copy data[37,38].
of assets from the installed
After sensors.
receiving The collected
the information from data is either locally
the simulation,
decentralized
the parameters or are
centrally
appliedstored
to realinassets.
a cloud.
TheThe data is then
integration evaluated
of data in real and simulated in
and virtual
a representation
virtual copy of assets
helps [37,38]. After
in optimizing receiving the
the performance information
of real assets. from the simulation, the
parameters are applied to real assets. The integration of data in real and virtual represen-
3.2.5.helps
tation Augmented Reality the performance of real assets.
in optimizing
Augmented reality (AR) is an emerging technology developed on the basis of virtual
reality (VR), which generates three-dimensional virtual information through a computer
system, including virtual scenes, virtual objects, etc. [39,40], and then superimposes this in-
formation into the real scene to realize the function of real-world enhancement and improve
the user’s perception of the real world. Although developed based on VR technology, AR
 information into the real scene to realize the function of real-world enhancement and im
prove the user’s perception of the real world. Although developed based on VR technol
ogy, AR does not require rendering of the natural environment like VR technology [41,42]
AR has been applied to support various processes on the shop floor, such as assembly
Appl. Sci. 2022, 12, 8081 maintenance, etc. Since various manufacturing processes require high quality 8 of and
22 near
zero error rates to ensure end-user requirements and safety, AR can also equip operator
with immersive interfaces to gain productivity, accuracy, and autonomy in quality [43].
does not require rendering of the natural environment like VR technology [41,42]. AR has
been applied to support various processes on the shop floor, such as assembly, maintenance,
3.2.6. Artificial Intelligence
etc. Since various manufacturing processes require high quality and near-zero error rates
toArtificial intelligence
ensure end-user (AI) isand
requirements thesafety,
keyword in the
AR can alsotransition to Industry
equip operators 4.0; it is a pow
with immersive
interfaces to gain productivity, accuracy, and autonomy in quality [43].
erful technology that compensates for the deficiencies and ineptitude of traditional tech
niques and approaches practiced in industry [44]. It has emerged as a powerful tool fo
3.2.6. Artificial Intelligence
developing intelligent predictive algorithms in many applications. AI approaches can
Artificial intelligence (AI) is the keyword in the transition to Industry 4.0; it is a
handle multidimensional
powerful technology that and multivariate
compensates for thedata and extract
deficiencies hidden relationships
and ineptitude of traditional in data
in complex and dynamic environments [45]. AI is strongly related to
techniques and approaches practiced in industry [44]. It has emerged as a powerful and appropriate
tool to
Big for
Data for answering
developing critical
intelligent questions,
predictive addressing
algorithms weaknesses,
in many applications. AIand shedding
approaches can light on
key process issues, especially in the analysis and processing phase of Big Data. in
handle multidimensional and multivariate data and extract hidden relationships in data
complex and dynamic environments [45]. AI is strongly related to and appropriate to Big
Data for answering critical questions, addressing weaknesses, and shedding light on key
3.2.7. Machine Learning and Deep Learning
process issues, especially in the analysis and processing phase of Big Data.
Machine Learning (ML) is a subfield of AI that has evolved from pattern recognition
3.2.7. Machine
to analyzing dataLearning and Deep
structures Learning
and integrating them into models that users can understand
Machine Learning (ML) is a subfield of AI
and regenerate [46]. Figure 7 identifies all ML categories,that has evolved from pattern
methods, recognition
and models applicable
to analyzing data structures and integrating them into models that users
to maintenance-related projects [47]. Furthermore, ML is classified into four categoriescan understand
and regenerate [46]. Figure 7 identifies all ML categories, methods, and models applicable
namely supervised learning, unsupervised learning, reinforcement learning, and deep
to maintenance-related projects [47]. Furthermore, ML is classified into four categories,
learning.
namelyThe types oflearning,
supervised supervised and unsupervised
unsupervised learning intended
learning, reinforcement learning, to
andpredict
deep or de
scribe existing
learning. Therelationships in a dataset
types of supervised are said to learning
and unsupervised be supervised
intendedwhen the dependen
to predict or
variable is available
describe and unsupervised
existing relationships when
in a dataset they
are said to are not, whilewhen
be supervised reinforcement learning i
the dependent
variable is available
a computational and unsupervised
approach that learnswhen fromtheytheare not, while reinforcement
interaction learning is which
with the environment,
a computational approach that learns from the interaction with the environment, which
means determining how the actors in a system can perform actions in their environmen
means determining how the actors in a system can perform actions in their environment to
to maximize the cumulative rewards.
maximize the cumulative rewards.

Figure 7. Classification of data-driven techniques and machine learning categories [47].

Figure 7.Deep
Classification of data-driven techniques and machine learning categories [47].
learning (DL) belongs to artificial neural networks (ANNs). It is a large group
of techniques in many fields, which can be applied to both supervised and unsupervised
learning. ANNs are inspired by brain function, with the primary goal of learning from
unstructured or unlabeled data, using one or more layers to extract higher-level features step
by step from raw input. Deep learning techniques can be applied to industrial equipment
in different situations such as fault detection, failure prediction, etc.
Appl. Sci. 2022, 12, 8081 9 of 22

4. Challenges of Predictive Maintenance

Even though adopting predictive maintenance in an industrial context is inevitable,
it is surrounded by challenges that hinder the application and collective adoption of this
smart maintenance approach. Despite the availability of predictive maintenance algorithms,
companies that want to benefit from Industry 4.0 still have to trade off the opportunities
of predictive maintenance against the capital expenditure required to purchase necessary
instrumentations, software, and expertise. This disadvantage is more important in the early
stages of predictive maintenance development when actual data on normal and abnormal
equipment behavior is lacking or scarce, and in the case of new systems, when there is
no experience with their operation. This situation can lead companies to invest more in
predictive maintenance solutions [48]. In the list of challenges encountered in the scientific
literature, four groups can be distinguished and will be considered, namely financial and
organizational limits, data source limits, machine repair activity limits, and limits in the
deployment of industrial predictive maintenance models.

4.1. Financial and Organizational Limits

For-profit companies inevitably consider the expected costs of any new investment.
Predictive maintenance efforts, such as sensor installation, information retrieval, model
preparation and maintenance, and maintenance activities generate costs for the companies
in which predictive maintenance methods are introduced. These costs can vary depending
on multiple factors, such as the type and complexity of equipment and corresponding
sensors, the cost of consulting, installation, and knowledge extraction, and whether the
necessary expertise can be found internally or externally [49]. One method of assessing
whether the introduction of predictive maintenance can be beneficial is to create a projected
return on investment (ROI) [50]. The projection of the predictive ROI should consider the
value of predictive maintenance results, the payback time, and the described costs. The
financial rationale for the use and applicability of predictive maintenance also depends on
the size and type of business in which it is introduced [51].

4.2. Data Source Limits

The availability of relevant data is essential for the creation of a production process
management model. However, companies rarely have all the relevant data at the beginning
of the introduction of production process management [30]. After using the data that is
already available, it is necessary to identify the gaps and aim to resolve them. Furthermore,
the quality of the existing information sources may not meet the required needs. If only
part of the data is affected by unsatisfactory quality, this can be overcome during data
preparation, as long as the amount of data points is sufficient to achieve statistical signifi-
cance and as long as defect detection can successfully isolate machine-critical points [52].
The company using predictive maintenance methods may then face challenges when the
necessary confidence in the data does not hold true, i.e., if sensors, controllers, or other
data sources provide inaccurate or incorrect measurements. This can result in incorrect
predictions and missed maintenance urgency or false alarms. An additional challenge for
sensor technology is that sensors currently tend to operate offline without contributing
to online data. In addition, sensors are subject to downtime, instrument degradation,
noise, or simply the sensor may fail. It is then important to clean the data before applying
the predictive maintenance algorithm in order to predict the true reality and not distort
the results.

4.3. Machine Repair Activity Limits

By being able to predict the remaining life of a component, maintenance times can
be determined, but the actual maintenance of a component still faces challenges related
to the dependence on human interactions and the lack of self-maintenance [53]. In fact,
the effectiveness of maintenance depends on the quality of human management and
skills, given that machine components currently depend on human operators for control
Appl. Sci. 2022, 12, 8081 10 of 22

and maintenance. Industrial machines particularly work by executing commands in a

reactive manner and do not question the plan for them. However, human task planning
is based on data and experience, which the machine might also be able to retrieve. Thus,
an intelligent component could autonomously propose or even initiate actions that are
beneficial to system health, asset throughput, or product quality. A further step toward
asset autonomy relies on asset awareness and autonomous maintenance. A self-aware asset
can assess its conditions based on data that is currently extracted and stored in a predictive
maintenance system and can recognize critical conditions up to the point of autonomous
definition of maintenance decisions. Unlike a central system controlling one or more
assets, all the information needed to make predictive maintenance decisions, as well as
the degradation and prediction model, would be distributed and available at a component
level. Machines can then plan maintenance programs for themselves. However, currently,
industrial machines do not have this level of self-awareness and self-maintenance.

4.4. Limits in the Deployment of Industrial Predictive Maintenance Models

Generally, there are three challenging steps after the development of intelligent failure
prediction models: their integration, monitoring, and updating. Model integration in the
industry is a challenge because this task is often performed by an information technology
(IT) team which is usually dissociated from the team of researchers and developers who
developed the predictive maintenance models. Building such an IT infrastructure to
maintain the data pipelines can be laborious and is not usually factored into the project
planning. Regarding the monitoring step, it consists of ensuring that the model is updated.
To do this, a feedback loop is added to the model so that the new incoming data are
learning inputs. This continuous re-training of the prediction models has the disadvantage
of weakening the reliability of the results. Indeed, neither the integrity nor the relevance
of the data is verified in production, which allows the introduction of outliers and thus
distorts predictions in the long run. Finally, as for the updating of the models, it is necessary
in order to avoid the conceptual drift phenomenon that affects machine learning models.
To update the prediction models, the company must modify the code, the model, and the
data at the same time. Compared to traditional enterprise software updates, this cycle of
improving predictive maintenance models is much more complex [54].

5. Predictive Maintenance Workflow

In order to properly plan a predictive maintenance project, a life cycle is followed
Appl. Sci. 2022, 12, x FOR PEER REVIEW 11 of 23
containing five (5) essential steps. These are the approaches to structure the solution of
problems that require data science and machine learning. Figure 8 illustrates the life cycle
and workflow of a predictive maintenance project [55,56]:

Figure 8. Workflow of predictive maintenance.

Figure 8. Workflow of predictive maintenance.

Step 1. Understanding the project’s needs:

The first step consists in understanding the business elements and problems of the
project as well as the constraints to overcome. In this step, it is necessary to fully under-
Appl. Sci. 2022, 12, 8081 11 of 22

Step 1. Understanding the project’s needs:

The first step consists in understanding the business elements and problems of the
project as well as the constraints to overcome. In this step, it is necessary to fully understand
the system and the equipment that are of interest to solve the project as well as the operation
of the equipment. This implies the definition of the physical quantities to be measured, the
choice of the sensors, and their installations if needed. In this step, we must also define a
list of types of failures that we can face.
Step 2. Data collection, understanding, and preparation:
Data collection: The sensors available in the equipment have the capacity to collect
data and transfer them to the database.
Understanding: This phase involves determining precisely what data to analyze,
identifying the quality of the available data, and relating the data to its meaning.
Preparation: This sub-step includes elements such as selecting related data; integrating
data by merging datasets; cleaning and managing missing values by deleting missing values
or imputing them with related data; managing erroneous data by deleting erroneous data;
checking outliers and processing them; using feature engineering to build new data and
obtain new features from existing data; formatting the data into the desired structure; and
removing unnecessary columns and features. Data preparation is the most time-consuming
step, accounting for 70–90% of the total project time, but it is the most important step in the
entire life cycle.
Step 3. Data modeling:
Data modeling is considered the heart of data analysis. The model takes the data
prepared in the previous step (data preparation) as input and provides the required output.
This step involves choosing the right type of algorithm, whether it is a classification problem,
a regression problem or a clustering problem. The testing and parameterization of different
chosen algorithms constitute a model.
Step 4. Evaluation and deployment:
• Step 4.1—Model Evaluation: Ultimately, we need to evaluate the model by measuring
accuracy (how well the model works, i.e., does it accurately describe the data) and rel-
evance (does it answer the original question that needs to be answered). We also need
to ensure that there is a good balance between performance and generalization, which
means that the model created should not be biased; it should be a generalized model.
• Step 4.2—Deploying the model: The evaluated model is finally deployed in the
required format and channel. This is the last step in the predictive maintenance life
cycle that is related to the data. Each stage of the life cycle explained below should be
carefully considered. If one step is not executed well, it will affect the next step and all
the effort will be wasted. For example, if data is not collected properly, information
will be lost, and a representative model cannot be created. If the data is not properly
cleaned, the model will not work properly. If the model is not evaluated correctly, it
will fail to give a perfect output in the real world. From understanding the project to
deploying the model, proper attention, time, and energy must be given to each step.
Step 5. Decision making:
In general, the decision-making process helps operators solve problems by deciding
on the best path forward. Using a step-by-step approach is an effective way to make
thoughtful, informed decisions that have a positive impact on short- and long-term goals.
• Step 5.1—Identifying the decision: The first step in making the right decision is to
recognize the problem. In this phase, several possible intervention scenarios are
developed with associated repair times and costs.
• Step 5.2—Action: After the identification of the possible scenarios, we choose an
alternative or combine them in order to find the one that verifies the minimum costs
and delays. The days of repair are planned after checking the availability of manpower
and spare parts.
 Appl. Sci. 2022, 12, 8081 12 of 22

• Step 5.3—Review: This step is important because it allows us to evaluate the effective-
ness of the decision taken; the life cycle of predictive maintenance is repetitive, so it
allows us to improve future interventions.

6. Predictive Maintenance Models

As mentioned in previous sections, predictive maintenance approaches are developed
to help industrial sectors based on their needs and maintenance requirements. Depending
on the technical and digital maturity level, different types of PdM models can be offered.
Among others, three main PdM models are presented in the following subsections.

6.1. Condition-Based Maintenance

Condition-based maintenance (CBM) is a management philosophy in which repair or
replacement decisions are made based on the current or future condition of equipment [57].
It is defined as a maintenance program that recommends maintenance solutions based on
information gathered from condition monitoring and consists of three main steps: data
collection, data processing, and maintenance decision-making [58]. CBM is an extended
version of predictive maintenance where automatic alarms are activated before a failure oc-
curs. Automatically triggered alarms are activated before any failure is obtained. Complex
multi-variable methods and algorithms are used to satisfy the application requirements of
CBM [59]. The objective of CBM is to minimize the overall cost of inspections and repairs
by collecting and interpreting intermittent or continuous data about the operating status of
critical components [60].
CBM can take many forms, from simple to complex. However, the most common form
adopted by most industries is the one shown in Figure 9 where the focus is on data collec-
tion, prediction, and correction with varying degrees of automation [57]. The starting point
is to monitor a set of indicators representative of the health of the equipment over time.
When one or more of these indicators reach a predetermined level of deterioration, mainte-
Appl. Sci. 2022, 12, x FOR PEER REVIEW 13 of 23
nance actions are taken to return the equipment to the desired state [61]. This means that
equipment is only taken out of service when there is direct evidence of deterioration [62].

Figure 9. The seven modules of a conditional maintenance system [57].

Figure 9. The seven modules of a conditional maintenance system [57].

The modules of a conditional maintenance system can be presented as follows:

Module 1: The sensor module provides the CBM system with digitized data from the
sensor or transducer.
Module 2: The signal processing module receives signals and data from the sensor
Appl. Sci. 2022, 12, 8081 13 of 22

The modules of a conditional maintenance system can be presented as follows:

Module 1: The sensor module provides the CBM system with digitized data from the
sensor or transducer.
Module 2: The signal processing module receives signals and data from the sensor
module or other signal processing modules. The output of the signal processing module
includes digitally filtered sensor data, frequency spectra, virtual sensor signals, and other
CBM features. The signal processing module may consist of an AI-ESTATE (Artificial
Intelligence and Expert System Tie to Automatic Test Equipment).
Module 3: The status monitor receives data from the sensor module, the signal
processing module, and other status monitors. Its main purpose is to compare the data
with the expected values. The status monitor must also be able to generate alerts based on
predefined operational limits. This function can be very useful for rapid fault development.
Module 4: This module receives data from various status monitors or other health
assessment modules. The main purpose of the health assessment module is to determine
if the health status of the monitored component, subsystem, or system has degraded.
The health assessment module is able to generate diagnostic records and propose failure
possibilities. The diagnosis is based on trends in health status history, operational status,
and loading and maintenance history.
Module 5: The prognostic module has the ability to take into account data from all
previous layers. The main objective of the prognosis module is to calculate the future health
status of an asset, taking into account future usage profiles. The module should indicate
the future health status at a given time or the remaining useful life (RUL).
Module 6: The decision support module receives data from the health assessment
module and the prognosis module. Its main purpose is to generate recommended actions
and alternatives. The actions can be in the area of maintenance, but also in the area of
operating the asset until the current mission is completed without a failure occurring.
Module 7: The presentation module should present the data from all the previous
modules. The most important layers to present are, of course, the data from the health
assessment, prognosis, and decision support modules, as well as the alerts generated by
the status monitors. However, the ability to lock in even further down the layer should be
a possibility. The presentation module could be integrated into a regular machine interface.

6.2. Prognostics and Health Management

The concept of Prognostics and Health Management (PHM) appeared in the 1990s with
the launch of the US Army’s Joint Strike Fighter (JSF) project [63]. The initial application
of PHM is therefore in the field of military aviation. Given the accelerated development
of sensor technology and predictive algorithms, practitioners have more opportunities
to monitor and predict system states. This allows system actors to take proactive mea-
sures to avoid serious accidents. For this reason, PHM is currently popular in a growing
number of fields [64].
The objective behind the implementation of a PHM architecture includes the dynamic
monitoring of the system state for the purpose of a predictable type of maintenance [65,66].
In this respect, the prognostic activity is considered a key process; unlike diagnostics, which
concerns the ability to detect and isolate the cause of an existing error, PHM has the ability
to assess the development of future degradation or errors of a system: it guarantees the
operation of the system and is an important step before being able to describe the different
maintenance scenarios used for the prediction and prevention of malfunctions [67,68].
Figure 10 [69] shows the variation in the number of publications over the last 20 years on
the topic of prognosis and health management of industrial equipment. The total number
is 373, calculated on the basis of a Web of Science search result. The number of publications
has increased rapidly since 2006. The total number of publications from 1999 to 2010 was
100, while the number of publications in the last five years was 198, which is much larger
than the total number in the first ten years.
 guarantees the operation of the system and is an important step before being able to de-
scribe the different maintenance scenarios used for the prediction and prevention of mal-
functions [67,68]. Figure 10 [69] shows the variation in the number of publications over
the last 20 years on the topic of prognosis and health management of industrial equip-
ment. The total number is 373, calculated on the basis of a Web of Science search result.
The number of publications has increased rapidly since 2006. The total number of publi-
Appl. Sci. 2022, 12, 8081 14 of 22
cations from 1999 to 2010 was 100, while the number of publications in the last five years
was 198, which is much larger than the total number in the first ten years.

Figure
Figure10.
10.Publications
Publicationsandand
Citations related
Citations to PHM
related themetheme
to PHM (August 2020) [69].
(August 2020) [69].

The
ThePHM
PHMlife lifecycle
cyclecan
canbebeillustrated
illustratedin in
Figure 11,11,
Figure wherein the the
wherein PHM cycle
PHM is com-
cycle is composed
posed of eight steps [50]. PHM methods can be classified into
of eight steps [50]. PHM methods can be classified into three categories three categories as shown
as shown in
in Figure 12 [63]. These categories are model-based approaches, data-based approaches
Figure 12 [63]. These categories are model-based approaches, data-based approaches and
and hybrid approaches that combine the advantages of the two previous approaches. The
hybrid approaches that combine the advantages of the two previous approaches. The main
main objective of these approaches is to develop a model suitable for RUL evaluation un-
objective of these approaches is to develop a model suitable for RUL evaluation under a
der a wide range of operating conditions and at any time during the life cycle of a compo-
nent orrange
wide
Appl. Sci. 2022, 12, x FOR PEER REVIEW
of operating
subsystem. conditions
The guidelines for and
PHMatareanyselected
time during
based the lifescope
on the cycle of
of its
a component
use,
15 of 23
or
subsystem.
accuracy The
of the guidelines
results, for
the cost, and PHM are selected
the complexity of based on the scope of its use, accuracy of
the operation.
the results, the cost, and the complexity of the operation.
Appl. Sci. 2022, 12, x FOR PEER REVIEW 15 of 23

Figure11.
Figure Steps
11.Steps in in
PHMPHM [50].
[50].
Figure 11. Steps in PHM [50].

Figure 12. PHM methods [70].

Figure 12. PHM methods [70].
Figure 12. PHMUseful
6.3. Remaining methods
Life [70].
The remaining useful life (RUL) is the period of time that a piece of equipment is
6.3. Remaining
likely to operateUseful
beforeLife
it needs to be repaired or replaced. Depending on the system, this
period canremaining
The be represented in days,
useful miles, cycles
life (RUL) is theorperiod
any other
of quantity.
time thatService lifeof
a piece predic-
equipment is
tion provides
likely early
to operate warnings
before of failure
it needs to beand has become
repaired a key component
or replaced. Dependingof prognostica-
on the system, this
tion and systems health management [71]. It enables maintenance planning, optimizes
 Appl. Sci. 2022, 12, 8081 15 of 22

6.3. Remaining Useful Life

The remaining useful life (RUL) is the period of time that a piece of equipment is likely
to operate before it needs to be repaired or replaced. Depending on the system, this period
can be represented in days, miles, cycles or any other quantity. Service life prediction
provides early warnings of failure and has become a key component of prognostication and
systems health management [71]. It enables maintenance planning, optimizes operating
efficiency, and avoids unplanned downtime [72]. The estimation of RUL is a real challenge
Appl. Sci. 2022, 12, x FOR PEER REVIEW 16 of 23
because the relevance and effectiveness of maintenance actions depend on the accuracy
Appl. Sci. 2022, 12, x FOR PEER REVIEW 16 of 23
and precision of the results obtained RUL = tf − tc. A confidence measure should also be
constructed to indicate the degree of certainty of the RUL as presented in Figure 13.

Figure 13. Representation of the residual life.

Figure 13. Representation of the residual life.
In the last decade, many tools and methods have been proposed as shown in Figure
In the
In the last
14. Generally, decade,
lasttwo typesmany
decade, many tools
toolsand
of methods and methods
are methods
used to have
have been
been
predict proposed
proposed
equipment aslife:
shown
as shown in Figure 14.
in Figure
physics-based
Generally,
14. Generally,
methods two types of methods
two typesmethods
and data-based are
of methods used
[73].are to predict
Theused equipment life:
to predict equipment
physics-based physics-based
approach uses methods
life: mathematical
physics-based
and data-based
methods
principles such asmethods
statistics[73].
and data-based and The
methods physics-based
[73]. Thewhich
probability, approach
attempt touses
physics-based mathematical
approach
create principles
uses mathematical
accurate mathemati-
such
cal as
principles statistics
models suchfrom as and probability,
statistics
prior which
and probability,
knowledge attempt
to predict which to
equipment create
attempt accurate
life.toHowever, mathematical
create accurate
relying onmodels
mathemati-
prior
from
cal prior
models knowledge
from prior to predict
knowledge equipment
to predict life. However,
equipment life.
knowledge can lead to insufficient generalization. Data-driven methods aim to explore relying
However, on prior knowledge
relying on prior
can lead to insufficient
knowledge can lead to generalization.
insufficient Data-driven Data-driven
generalization. methods aimmethods to explore thetopotential
aim explore
the potential relationship between monitored sensor data and their RUL value based on
relationship
the potential between monitored sensor data sensor
and theirdataRUL valueRULbased on historical
historical data.relationship
The RUL ofbetween
equipment monitored
is a random variable and
thattheir
depends on value
thebased on
current
data. The
historical RUL of equipment
data. The RUL of equipment is a random variable
is ainformation. that
random variable dependsthat on the
depends current
on the age of a
age of a machine/equipment and its health It gives the remaining timecurrent
for a
machine/equipment
age of a machine/equipment and its healthitsinformation. It gives the remaining time for atime machine,
machine, component or systemand beforehealth
it is noinformation. It gives
longer functional. Inthe
theremaining
research, there for
hasa
component
machine, or system
component orbefore
systemit is no
before longer
it is functional.
no longer In the
functional. research,
In the there
research,has beenhas
there an
been an interest in the use of remaining life estimates within industries [74]. In the follow-
interest
been in the use of remaining life estimates within industries [74]. In the following, we
ing, weanwill
interest
presentin the use of
articles remaining
that have dealt lifewith
estimates within industries [74]. In the follow-
this subject.
will present articles that have dealt with this subject.
ing, we will present articles that have dealt with this subject.

14.AAbrief
Figure14.
Figure briefexplication
explicationofofRUL
RULmodels.
models.
Figure 14. A brief explication of RUL models.
In order to improve the prediction of RUL, Kitai et al. [75] used convolutional neural
In order to improve the prediction of RUL, Kitai et al. [75] used convolutional neural
networks (CNN)
In order and hierarchical
to improve Bayesian
the prediction regression.
of RUL, Kitai et al.The
[75]conclusion is improved
used convolutional by
neural
networks (CNN) and hierarchical Bayesian regression. The conclusion is improved by de-
networks
fining (CNN)scaling
a min-max and hierarchical Bayesian
for the RUL regression.
and giving a goodThe conclusion
prediction is improved
accuracy by de-
of the CNN.
fining a min-max scaling for the RUL and giving a good prediction accuracy
However, the combination of CNN with hierarchical Bayesian regression gave a higher of the CNN.
However, the combination of CNN with hierarchical Bayesian regression
rate if just CNN is used for RUL prediction. Erpolat Taşabat et al. [76] opted to use thegave a higher
rate iflong-term
LSTM just CNNshort-term
is used formemory
RUL prediction.
for motorErpolat Taşabat
prediction; et al. [76]
the results giveopted to userate
a success the
Appl. Sci. 2022, 12, 8081 16 of 22

Appl. Sci. 2022, 12, x FOR PEER REVIEW 17 of 23

defining a min-max scaling for the RUL and giving a good prediction accuracy of the CNN.
However, the combination
motors to predict of CNN
their remaining with The
lifetimes. hierarchical
results of Bayesian
the MAE and regression gave a higher
RMSE metrics
wereifcompared
rate just CNNtois three other
used fortopologies. Here, theErpolat
RUL prediction. author found thatet
Taşabat theal.recurrent
[76] optedneural
to use the
network
LSTM model outperformed
long-term the otherfor
short-term memory three topologies
motor for the
prediction; thefirst dataset
results used
give while rate of
a success
for the entire
91/100 second
for failure dataset, theIndeed,
prediction. error was withintheir
during the acceptable
experiments,rangethefor authors
the proposed
of [77] used
topology.
three neural networks that differ by the number of layers of LSTM used for the same dataset.
They found that adding an LSTM layer increases the accuracy of the training and validation
7. Predictive Maintenance Case Study on a Centrifugal Compressor
set. The use of deep learning methods has therefore become essential in the last decade.
In this section, a practical case study based on a PdM approach is presented to esti-
The author of [78] used two datasets to test neural network models on over 100 motors to
mate the remaining life of a centrifugal compressor. Compressors are used throughout
predict their remaining lifetimes. The results of the MAE and RMSE metrics were compared
industry to supply air to shops or instruments, power air tools, paint sprayers and sand-
toblasting
three other topologies. Here, the author found that the recurrent neural network model
equipment, dephase refrigerants for air conditioning and refrigeration, propel
outperformed theetc.
gas in pipelines, other
[79].three topologies
Therefore, for the
they play first
a key dataset
role in theused while for
production line.the entire
This re- second
dataset, the error was within the acceptable range for the proposed topology.
quires a study on the remaining life of this equipment in order to predict future failures
and avoid them while applying machine learning methods. Figure 15 represents the com-
7.ponents
Predictive
of theMaintenance Case Study
CBM/PHM approach for an on a Centrifugal
industrial Compressor
compressor [80].
Nordal
In and El-Thalji
this section, [81] propose
a practical a predictive
case study based onmaintenance (PdM) evaluation
a PdM approach matrix
is presented to estimate
for remaining
the overcominglifecentrifugal compressor
of a centrifugal failures that
compressor. highlight theare
Compressors linkused
between the com-industry
throughout
tobination
supplyofairseveral sensoror
to shops signals and the ability
instruments, powerto detect, diagnose,
air tools, paintand predictand
sprayers the future
sandblasting
evolution of failures. Ali [82] implemented a redundancy system with
equipment, dephase refrigerants for air conditioning and refrigeration, propel gas in two additional
compressors that are used when the main compressor fails or is under scheduled mainte-
pipelines, etc. [79]. Therefore, they play a key role in the production line. This requires a
nance. From a general point of view, the objective is to minimize the number of possible
study on the remaining life of this equipment in order to predict future failures and avoid
interruptions, hence the redundancy system, which a plant will gladly invest in, instead
them while applying machine learning methods. Figure 15 represents the components of
of an unproven predictive system. However, the application of predictive maintenance
the CBM/PHM approach
can be a great advantage forfor
thean industrial
plant, becausecompressor [80]. it brings.
of the many benefits

Figure 15. Components of the CBM/PHM approach for a compressor [80].

Figure 15. Components of the CBM/PHM approach for a compressor [80].
8. Discussions and Recommendations
Nordal and El-Thalji [81] propose a predictive maintenance (PdM) evaluation matrix
Predictive maintenance
for overcoming centrifugal iscompressor
a technique failures
that usesthat
toolshighlight
and condition monitoring
the link betweentech-
the combi-
niques to monitor the performance and health state of a structure or equipment during
nation of several sensor signals and the ability to detect, diagnose, and predict the future
operation in a sustainable manner [83–86]. However, it can be noticed in the literature that
evolution of failures. Ali [82] implemented a redundancy system with two additional
the application of maintenance 4.0 is mostly focused on a specific machine or industrial
compressors that are used when the main compressor fails or is under scheduled mainte-
equipment. The idea of creating a user-friendly and multifunctional platform, as depicted
nance. From a general point of view, the objective is to minimize the number of possible
in Figure 16, that integrates different types of sensors and enables in-situ PdM on different
interruptions, hence the redundancy system, which a plant will gladly invest in, instead of
an unproven predictive system. However, the application of predictive maintenance can be
a great advantage for the plant, because of the many benefits it brings.
Appl. Sci. 2022, 12, x FOR PEER REVIEW 18 of 23
Appl. Sci. 2022, 12, 8081 17 of 22

types of equipment
8. Discussions in real-time can be considered revolutionary in the field [87]. This
and Recommendations
platform highlights support in maintenance management and decision-making based on
Predictive maintenance is a technique that uses tools and condition monitoring tech-
acquired data and developed models of PdM. It allows users and the maintenance team,
niques to monitor the performance and health state of a structure or equipment during
depending on their predefined access level to the platform, to manipulate and modify
operation in a sustainable manner [83–86]. However, it can be noticed in the literature that
proposed decisions anytime and at any step of the maintenance planning process. The
the application of maintenance 4.0 is mostly focused on a specific machine or industrial
platform gives remote access via user authentication protected by a VPN (private virtual
equipment. The idea of creating a user-friendly and multifunctional platform, as depicted
network). Thus, a cloud infrastructure is provided that allows mobile and web connec-
in Figure 16, that integrates different types of sensors and enables in-situ PdM on different
tions in order to receive notifications received by the alarms. Apart from remote connec-
types of equipment in real-time can be considered revolutionary in the field [87]. This
tivity, this platform will provide real-time on-site data monitoring collected by machines
platform highlights support in maintenance management and decision-making based on
and equipment in the form of a dashboard that calculates key performance indicators and
acquired data and developed models of PdM. It allows users and the maintenance team,
supports API (application programming interface) protocols for data customization and
depending on their predefined access level to the platform, to manipulate and modify
alarm notifications.
proposed decisions This provides
anytime and atremote plant
any step of monitoring from planning
the maintenance any browser and also
process. The
ensures high security against attacks by preserving the integrity and confidentiality
platform gives remote access via user authentication protected by a VPN (private virtual of
information.
network). Thus, a cloud infrastructure is provided that allows mobile and web connections
This to
in order platform
receive will help operators
notifications work
received more
by the efficiently,
alarms. Apartsafely
from and
remotesaveconnectivity,
money by
reducing downtime
this platform and costs.
will provide It actson-site
real-time as an HMI
data operator
monitoringinterface where
collected all necessary
by machines and
information from the equipment can be viewed in real-time through
equipment in the form of a dashboard that calculates key performance indicators the data acquisition
and sup-
and transfer
ports system. Then
API (application it allows the
programming supervision
interface) of allfor
protocols thedata
installed machinesand
customization andalarm
also
allows following the operations remotely in addition to keeping the history
notifications. This provides remote plant monitoring from any browser and also ensures and future
predictions
high securitythanks to attacks
against the application of AI.the integrity and confidentiality of information.
by preserving

Figure 16.
Figure Theproposed
16. The proposedmultifunctional
multifunctionalplatform
platformof
ofpredictive
predictivemaintenance
maintenancebased
basedon
onindustrial
industrial
asset management.
asset management.

This platform will help operators work more efficiently, safely and save money by
9. Conclusions
reducing downtime and costs. It acts as an HMI operator interface where all necessary
This article explored an exhaustive literature review on methods and tools in smart
information from the equipment can be viewed in real-time through the data acquisition
and prognostic industrial
and transfer system. Then maintenance,
it allows thecovering
supervisionthe main
of allarticles on intelligent
the installed machines predictive
and also
maintenance. As a result, it was possible to identify each proposed approach
allows following the operations remotely in addition to keeping the history and future as address-
ing specific equipment
predictions so application
thanks to the that it becomes more difficult to compare it to other techniques.
of AI.
In addition, it is possible to notice that this intelligent maintenance itself has emerged as
a9.new tool for handling maintenance events. Indeed, after the advance of Industry 4.0,
Conclusions
Maintenance 4.0 explored
This article is becoming more and literature
an exhaustive more feasible
review and
on promising.
methods and The priority
tools of
in smart
adopting intelligent predictive maintenance in the maintenance routines of
and prognostic industrial maintenance, covering the main articles on intelligent predictive manufactur-
ing sectors is recognized
maintenance. As a result,by industrial
it was possiblecompanies.
to identifyIn thisproposed
each article, aapproach
novel multifunctional
as addressing
platform of industrial predictive maintenance based on asset management
specific equipment so that it becomes more difficult to compare it to other techniques. and smart In
maintenance
addition, it is possible to notice that this intelligent maintenance itself has emerged asaa
planning approaches is presented. This platform aims at implementing
plug-and-play type ofmaintenance
new tool for handling maintenanceevents. hardware
Indeed,wherein different
after the advancetypes of sensors
of Industry and
4.0, Main-
maintenance approaches are integrated for diverse types of industrial
tenance 4.0 is becoming more and more feasible and promising. The priority of adopting machines and
equipment. The platform
intelligent predictive is endowed
maintenance in thewith smart prognostic
maintenance routines ofalgorithms featuring
manufacturing a
sectors
Appl. Sci. 2022, 12, 8081 18 of 22

is recognized by industrial companies. In this article, a novel multifunctional platform of

industrial predictive maintenance based on asset management and smart maintenance plan-
ning approaches is presented. This platform aims at implementing a plug-and-play type of
maintenance hardware wherein different types of sensors and maintenance approaches
are integrated for diverse types of industrial machines and equipment. The platform is
endowed with smart prognostic algorithms featuring a prescriptive maintenance model.
An industrial case study on a centrifugal compressor is also presented as the implemen-
tation of our proposed platform. The results are promising, considering the fact that the
breakdown and defect prediction for the compressor followed the real maintenance timing,
allowing better planning with respect to the maintenance team and spare part preparation.
In terms of challenges and future directions, there are several steps to consider in
verifying this new development. Generally, an intelligent predictive maintenance project
is dependent on the following activities: modeling, simulation and experimental vali-
dation, instrumentation of the system to be studied, creation of a failure database, data
processing and cleaning, analysis of the main failure modes, decision support, anticipation
of cyber-attacks, and presentation of the project results in the form of an HMI (human-
machine interface). The future research work can take into consideration these steps in
different types of industrial equipment and validate smart decision-making for industrial
maintenance planning.

Author Contributions: Conceptualization, M.A. (Mounia Achouch), H.I., M.A. (Mehdi Adda), S.S.K.,
M.D., R.D. and K.Z.; methodology, M.A. (Mounia Achouch), M.D., K.Z., H.I., S.S.K. and R.D.;
validation, H.I., M.D., K.Z., R.D. and S.S.K.; formal analysis, H.I., M.D. and S.S.K.; writing—original
draft preparation, M.A. (Mounia Achouch), R.D., M.D. and K.Z.; writing—review and editing, H.I.,
K.Z., M.D., M.A. (Mehdi Adda), R.D. and S.S.K.; visualization, M.A. (Mounia Achouch), K.Z., R.D.
and M.D.; supervision, H.I., M.A. (Mehdi Adda), M.D. and S.S.K.; project administration, H.I. and
M.A. (Mehdi Adda). All authors have read and agreed to the published version of the manuscript.
Funding: This research received no external funding.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Conflicts of Interest: The authors declare no conflict of interest.

Nomenclature and Symbols

ANN Artificial Neural Network

AI Artificial Intelligence
AR Augmented Reality
CBM Condition-Based Maintenance
CNN Convolutional neural networks
CPS Cyber-Physical Systems
DoS Denial of service
DP Deep Learning
DT Digital Twin
HMI Human Machine Interface
IoT Internet of Things
IIoT Industrial Internet of Things
ML Machine Learning
PdM Predictive maintenance
PM Preventive maintenance
PHM Prognostics and Health Management
ROI Return on investment
RUL Remaining Useful Life
VR Virtual Reality
Appl. Sci. 2022, 12, 8081 19 of 22

References
1. Rüßmann, M.; Lorenz, M.; Gerbert, P.; Waldner, M.; Justus, J.; Engel, P.; Harnisch, M. Industry 4.0: The Future of Productivity and
Growth in Manufacturing Industries; Boston Consulting Group: Boston, MA, USA, 2015.
2. Kaczmarek, M.J.; Gola, A. Maintenance 4.0 Technologies for Sustainable Manufacturing—An Overview. IFAC-PapersOnLine 2019,
52, 91–96. [CrossRef]
3. Ran, Y.; Zhou, X.; Lin, P.; Wen, Y.; Deng, R. A Survey of Predictive Maintenance: Systems, Purposes and Approaches. arXiv 2019,
arXiv:1912.07383. Available online: http://arxiv.org/abs/1912.07383 (accessed on 14 October 2021).
4. Tiddens, W.; Braaksma, J.; Tinga, T. Exploring predictive maintenance applications in industry. J. Qual. Maint. Eng. 2020, 28,
68–85. [CrossRef]
5. Blancke, O. Développement D’une Approche de Pronostic Pour les Équipements Complexes Permettant L’application de la
Maintenance Prévisionnelle. Ph.D. Thesis, École de Technologie Supérieure, Montreal, QC, Canada, 2020.
6. Market Research Report, Marketsandmarkets.com. “Predictive Maintenance Market by Component (Solutions, Services), De-
ployment Mode (On-Premises, Cloud), Organization Size (Large Enterprises, SME), Vertical and Region—Global Forecast to
2026”. Available online: https://www.grandviewresearch.com/industry-analysis/predictive-maintenance-market (accessed on
24 July 2022).
7. Predictive Maintenance Market Size Worldwide 2020–2030|Statista. 2022. Available online: https://www.statista.com/statistics/
748080/global-predictive-maintenance-market-size/ (accessed on 24 July 2022).
8. Qu’est ce Que L’industrie 4.0? L’agence Digitale Créative—Les Digital Heroes. 1 October 2021. Available online: https:
//lesdigitalheroes.fr/quest-ce-que-lindustrie-4-0/ (accessed on 13 April 2022).
9. Li, Z.; Wang, Y.; Wang, K.-S. Intelligent predictive maintenance for fault diagnosis and prognosis in machine centers: Industry
4.0 scenario. Adv. Manuf. 2017, 5, 377–387. [CrossRef]
10. Silvestri, L.; Forcina, A.; Introna, V.; Santolamazza, A.; Cesarotti, V. Maintenance transformation through Industry 4.0 technologies:
A systematic literature review. Comput. Ind. 2020, 123, 103335. [CrossRef]
11. Fernandez-Carames, T.M.; Fraga-Lamas, P. A Review on Human-Centered IoT-Connected Smart Labels for the Industry 4.0.
IEEE Access 2018, 6, 25939–25957. [CrossRef]
12. Vaidya, S.; Ambad, P.; Bhosle, S. Industry 4.0—A Glimpse. Procedia Manuf. 2018, 20, 233–238. [CrossRef]
13. Lasi, H.; Fettke, P.; Kemper, H.-G.; Feld, T.; Hoffmann, M. Industry 4.0. Bus. Inf. Syst. Eng. 2014, 6, 239–242. [CrossRef]
14. Bécue, A.; Praça, I.; Gama, J. Artificial intelligence, cyber-threats and Industry 4.0: Challenges and opportunities. Artif. Intell. Rev.
2021, 54, 3849–3886. [CrossRef]
15. Mentsiev, A.U.; Guzueva, E.R.; Magomaev, T.R. Security challenges of the Industry 4.0. J. Phys. Conf. Ser. 2020, 1515, 032074.
[CrossRef]
16. Pereira, T.; Barreto, L.; Amaral, A. Network and information security challenges within Industry 4.0 paradigm. Procedia Manuf.
2017, 13, 1253–1260. [CrossRef]
17. Kashmar, N.; Adda, M.; Atieh, M. From access control models to access control metamodels: A survey. In Proceedings of the
Future of Information and Communication Conference, San Francisco, CA, USA, 14–15 March 2019; Springer: Cham, Switzerland,
2019; pp. 892–911.
18. Pedreira, V.; Barros, D.; Pinto, P. A review of attacks, vulnerabilities, and defenses in industry 4.0 with new chal-lenges on data
sovereignty ahead. Sensors 2021, 21, 5189. [CrossRef] [PubMed]
19. Reiman, A.; Kaivooja, J.; Parviainen, E.; Takala, E.P.; Lauraeus, T. Human factors and ergonomics in manufac-turing in the
industry 4.0 context–A scoping review. Technol. Soc. 2021, 65, 101572. [CrossRef]
20. Neumann, W.P.; Winkelhaus, S.; Grosse, E.H.; Glock, C.H. Industry 4.0 and the human factor–A systems frame-work and analysis
methodology for successful development. Int. J. Prod. Econ. 2021, 233, 107992. [CrossRef]
21. Veile, J.W.; Kiel, D.; Müller, J.M.; Voigt, K.-I. Lessons learned from Industry 4.0 implementation in the German manufacturing
industry. J. Manuf. Technol. Manag. 2019, 31, 977–997. [CrossRef]
22. Pilloni, V. How Data Will Transform Industrial Processes: Crowdsensing, Crowdsourcing and Big Data as Pillars of Industry 4.0.
Future Internet 2018, 10, 24. [CrossRef]
23. Lee, J.; Ni, J.; Singh, J.; Jiang, B.; Azamfar, M.; Feng, J. Intelligent Maintenance Systems and Predictive Manufacturing. J. Manuf.
Sci. Eng. 2020, 142, 110805. [CrossRef]
24. de Faria, H.; Costa, J.G.S.; Olivas, J.L.M. A review of monitoring methods for predictive maintenance of electric power transformers
based on dissolved gas analysis. Renew. Sustain. Energy Rev. 2015, 46, 201–209. [CrossRef]
25. Levitt, J. Complete Guide to Preventive and Predictive Maintenance; Industrial Press Inc.: New York, NY, USA, 2003.
26. Pech, M.; Vrchota, J.; Bednář, J. Predictive Maintenance and Intelligent Sensors in Smart Factory: Review. Sensors 2021, 21, 1470.
[CrossRef]
27. Cakir, M.; Guvenc, M.A.; Mistikoglu, S. The experimental application of popular machine learning algorithms on predictive
maintenance and the design of IIoT based condition monitoring system. Comput. Ind. Eng. 2020, 151, 106948. [CrossRef]
28. Poór, P.; Basl, J.; Zenisek, D. Predictive Maintenance 4.0 as next evolution step in industrial maintenance development. In
Proceedings of the 2019 International Research Conference on Smart Computing and Systems Engineering (SCSE), Colombo, Sri
Lanka, 28 March 2019; pp. 245–253.
Appl. Sci. 2022, 12, 8081 20 of 22

29. Jimenez-Cortadi, A.; Irigoien, I.; Boto, F.; Sierra, B.; Rodriguez, G. Predictive Maintenance on the Machining Process and Machine
Tool. Appl. Sci. 2019, 10, 224. [CrossRef]
30. Maktoubian, J.; Taskhiri, M.S.; Turner, P. Intelligent Predictive Maintenance (IPdM) in Forestry: A Review of Challenges and
Opportunities. Forests 2021, 12, 1495. [CrossRef]
31. Okano, M.T. IOT and Industry 4.0: The Industrial New Revolution. In Proceedings of the ICMIS-17—International Conference on
Management and Information Systems, Bangkok, Thailand, 25–26 September 2017; pp. 75–82.
32. Lee, J.; Ardakani, H.D.; Yang, S.; Bagheri, B. Industrial Big Data Analytics and Cyber-physical Systems for Future Maintenance &
Service Innovation. Procedia CIRP 2015, 38, 3–7. [CrossRef]
33. Lambán, M.P.; Morella, P.; Royo, J.; Sánchez, J.C. Using Industry 4.0 to face the challenges of Predictive Mainte-nance: A Key
Performance Indicators development in a Cyber Physical System. Comput. Ind. Eng. 2022, 171, 108400. [CrossRef]
34. Wang, J.; Xu, C.; Zhang, J.; Zhong, R. Big data analytics for intelligent manufacturing systems: A review. J. Manuf. Syst. 2021, 62,
738–752. [CrossRef]
35. Kaarlela, T.; Arnarson, H.; Pitkäaho, T.; Shu, B.; Solvang, B.; Pieskä, S. Common Educational Teleoperation Plat-form for Robotics
Utilizing Digital Twins. Machines 2022, 10, 577. [CrossRef]
36. Azeez, N.A.; Adjekpiyede, O.O. Digital Twin Technology: A Review of Its Applications and Prominent Challenges. Covenant J.
Inform. Commun. Technol. 2022, 10. Available online: https://journals.covenantuniversity.edu.ng/index.php/cjict/article/view/
2995 (accessed on 10 June 2022).
37. Hosamo, H.H.; Svennevig, P.R.; Svidt, K.; Han, D.; Nielsen, H.K. A Digital Twin predictive maintenance framework of air
handling units based on automatic fault detection and diagnostics. Energy Build. 2022, 261, 111988. [CrossRef]
38. You, Y.; Chen, C.; Hu, F.; Liu, Y.; Ji, Z. Advances of Digital Twins for Predictive Maintenance. Procedia Comput. Sci. 2022, 200,
1471–1480. [CrossRef]
39. Wang, Y.; Martinsen, K.; Yu, T.; Wang, K. Advanced Manufacturing and Automation XI; Springer: Singapore, 2022.
40. Chiang, F.-K.; Shang, X.; Qiao, L. Augmented reality in vocational training: A systematic review of research and applications.
Comput. Hum. Behav. 2021, 129, 107125. [CrossRef]
41. Ho, P.T.; Albajez, J.A.; Santolaria, J.; Yagüe-Fabra, J.A. Study of Augmented Reality Based Manufacturing for Further Integration
of Quality Control 4.0: A Systematic Literature Review. Appl. Sci. 2022, 12, 1961. [CrossRef]
42. Arena, F.; Collotta, M.; Pau, G.; Termine, F. An Overview of Augmented Reality. Computers 2022, 11, 28. [CrossRef]
43. Liu, C.; Zhu, H.; Tang, D.; Nie, Q.; Zhou, T.; Wang, L.; Song, Y. Probing an intelligent predictive maintenance approach with deep
learning and augmented reality for machine tools in IoT-enabled manufacturing. Robot. Comput.-Integr. Manuf. 2022, 77, 102357.
[CrossRef]
44. Daniyan, I.; Mpofu, K.; Oyesola, M.; Ramatsetse, B.; Adeodu, A. Artificial intelligence for predictive maintenance in the railcar
learning factories. Procedia Manuf. 2020, 45, 13–18. [CrossRef]
45. Carvalho, T.P.; Soares, F.A.A.M.N.; Vita, R.; Francisco, R.D.P.; Basto, J.P.; Alcalá, S.G.S. A systematic literature review of machine
learning methods applied to predictive maintenance. Comput. Ind. Eng. 2019, 137, 106024. [CrossRef]
46. Barja-Martinez, S.; Aragüés-Peñalba, M.; Munné-Collado, Í.; Lloret-Gallego, P.; Bullich-Massagué, E.; Villafafila-Robles, R.
Artificial intelligence techniques for enabling Big Data services in distribution networks: A review. Renew. Sustain. Energy Rev.
2021, 150, 111459. [CrossRef]
47. Nacchia, M.; Fruggiero, F.; Lambiase, A.; Bruton, K. A Systematic Mapping of the Advancing Use of Machine Learning Techniques
for Predictive Maintenance in the Manufacturing Sector. Appl. Sci. 2021, 11, 2546. [CrossRef]
48. zu Wickern, V.F.M. Challenges and Reliability of Predictive Maintenance. Master’s Thesis, Faculty of Communication and
Environment, Rhine-Waal University of Applied Sciences, Kleve, Germany, 2019. [CrossRef]
49. Wellsandt, S.; Klein, K.; Hribernik, K.; Lewandowski, M.; Bousdekis, A.; Mentzas, G.; Thoben, K.D. Hybrid-augmented
intelligence in predictive maintenance with digital intelligent assistants. Annu. Rev. Control 2022, 53, 382–390. [CrossRef]
50. Diamond, S. Predictive Maintenance For Dummies®, IBM Limited Edition; John Wiley & Sons, Inc.: Hoboken, NJ, USA, 2013; p. 51.
51. Jin, X.; Weiss, B.A.; Siegel, D.; Lee, J. Present Status and Future Growth of Advanced Maintenance Technology and Strategy in US
Manufacturing. Int. J. Progn. Health Manag. 2016, 7, 12. [CrossRef]
52. Keleko, A.T.; Kamsu-Foguem, B.; Ngouna, R.H.; Tongne, A. Artificial intelligence and real-time predictive maintenance in
industry 4.0: A bibliometric analysis. AI Ethics 2022, 1–25. [CrossRef]
53. Mousavi, S. Simultaneous Control of the Production, Maintenance, and Inspection Strategies for a Failure-Prone Manufacturing
System with Quality-Based Financial Penalties/Incentives. Ph.D. Thesis, École de Technologie Supérieure, Montreal, QC,
Canada, 2021.
54. Paleyes, A.; Urma, R.G.; Lawrence, N.D. Challenges in deploying machine learning: A survey of case studies. ACM Comput. Surv.
(CSUR) 2020. [CrossRef]
55. Sipos, R.; Fradkin, D.; Moerchen, F.; Wang, Z. Log-based predictive maintenance. In Proceedings of the 20th ACM SIGKDD
International Conference on Knowledge Discovery and Data Mining, New York, NY, USA, 24–27 August 2014; pp. 1867–1876.
[CrossRef]
56. Ton, B.; Basten, R.; Bolte, J.; Braaksma, J.; Di Bucchianico, A.; Van De Calseyde, P.; Grooteman, F.; Heskes, T.; Jansen, N.; Teeuw,
W.; et al. PrimaVera: Synergising Predictive Maintenance. Appl. Sci. 2020, 10, 8348. [CrossRef]
Appl. Sci. 2022, 12, 8081 21 of 22

57. Prabhakar, D.; Raj, V.J. CBM, TPM, RCM and A-RCM-a qualitative comparison of maintenance management strategies. Int. J.
Manag. Bus. Stud. 2014, 4, 49–56.
58. Fernandes, J.; Reis, J.; Melão, N.; Teixeira, L.; Amorim, M. The role of Industry 4.0 and BPMN in the arise of condition-based and
predictive maintenance: A case study in the automotive industry. Appl. Sci. 2021, 11, 3438. [CrossRef]
59. Ogbonnaya, C.; Abeykoon, C.; Nasser, A.; Turan, A. A computational approach to solve a system of transcendental equations
with multi-functions and multi-variables. Mathematics 2021, 9, 920. [CrossRef]
60. Ali, M.H.; Haddad, S. Stratégie pour la maintenance prévisionnelle des systèmes photovoltaïques. J. Renew. Energ. 2020, 23,
59–71.
61. Peng, Y.; Dong, M.; Zuo, M.J. Current status of machine prognostics in condition-based maintenance: A review. Int. J. Adv. Manuf.
Technol. 2010, 50, 297–313. [CrossRef]
62. Bengtsson, M. On Condition Based Maintenance and Its Implementation in Industrial Settings. Ph.D. Thesis, Mälardalens
Högskola, Västerås, Sweden, 2007.
63. Hess, A.; Calvello, G.; Dabney, T. PHM a key enabler for the JSF autonomic logistics support concept. In Proceedings of
the 2004 IEEE Aerospace Conference Proceedings (IEEE Cat. no. 04th8720), Big Sky, MT, USA, 6–13 March 2004; Volume 6,
pp. 3543–3550.
64. Meng, H.; Li, Y.F. A review on prognostics and health management (PHM) methods of lithium-ion batteries. Renew. Sustain.
Energy Rev. 2019, 116, 109405. [CrossRef]
65. Omri, N.; Al Masry, Z.; Mairot, N.; Giampiccolo, S.; Zerhouni, N. Towards an adapted PHM approach: Data quality requirements
methodology for fault detection applications. Comput. Ind. 2021, 127, 103414. [CrossRef]
66. Hu, N.; Su, X.; Liu, B. A Review on Prognostics and Health Management. In Proceedings of the 2018 Second International
Conference of Sensor Network and Computer Engineering (ICSNCE 2018), Xi’an, China, 27–29 April 2018; p. 7.
67. Sanchez, R.E.S. Contribution au Pronostic de Durée de vie des Systèmes Pile à Combustible de Type PEMFC. Ph.D. Thesis,
Université du Québec à Trois-Rivières, Trois-Rivières, QC, Canada, 2016.
68. Zheng, J.; Mu, H.; Wang, X.; Li, T.-M.; Zhang, Q.; Wang, X. An Adaptive Maintenance Policy With Nonlinear Degradation
Modeling Based on Prognostic Information. IEEE Access 2020, 8, 160040–160049. [CrossRef]
69. Peng, C.; Tang, Z.; Gui, W.; Chen, Q.; Zhang, L.; Yuan, X.; Deng, X. Review of Key Technologies and Progress in Industrial
Equipment Health Management. IEEE Access 2020, 8, 151764–151776. [CrossRef]
70. Vogl, G.W.; Weiss, B.A.; Helu, M. A review of diagnostic and prognostic capabilities and best practices for manufacturing. J. Intell.
Manuf. 2019, 30, 79–95. [CrossRef] [PubMed]
71. Pecht, S.K.M. Modeling Approaches for Prognostics and Health Management of Electronics. Int. J. Perform. Eng. 2010, 6, 467.
72. Si, X.-S.; Wang, W.; Hu, C.-H.; Zhou, D.-H. Remaining useful life estimation—A review on the statistical data driven approaches.
Eur. J. Oper. Res. 2011, 213, 1–14. [CrossRef]
73. de Pater, I.; Reijns, A.; Mitici, M. Alarm-based predictive maintenance scheduling for aircraft engines with imperfect Remaining
Useful Life prognostics. Reliab. Eng. Syst. Saf. 2022, 221, 108341. [CrossRef]
74. Zhang, H.; Zhang, Q.; Shao, S.; Niu, T.; Yang, X. Attention-Based LSTM Network for Rotatory Machine Remaining Useful Life
Prediction. IEEE Access 2020, 8, 132188–132199. [CrossRef]
75. Zonta, T.; da Costa, C.A.; Righi, R.D.R.; de Lima, M.J.; da Trindade, E.S.; Li, G.P. Predictive maintenance in the Industry 4.0: A
systematic literature review. Comput. Ind. Eng. 2020, 150, 106889. [CrossRef]
76. Kitai, M.; Kobayashi, T.; Fujiwara, H.; Tani, R.; Numao, M.; Fukui, K.-I. A Framework for Predicting Remaining Useful Life Curve
of Rolling Bearings under Defect Progression Based on Neural Network and Bayesian Method. IEEE Access 2021, 9, 62642–62652.
[CrossRef]
77. Taşabat, S.E.; Aydin, O. Using Long-Short term Memory networks with Genetic Algorithm to predict engine condition. GAZI
Univ. J. Sci. 2021, 35, 1200–1210. [CrossRef]
78. Thakkar, U.R. Remaining Useful Life Prediction of a Turbofan Engine Using Deep Layer Recurrent Neural Networks. Ph.D.
Thesis, Carleton University, Ottawa, ON, Canada, 2021.
79. Zhang, Y.; Xu, S.; Wan, Y. Performance improvement of centrifugal compressors for fuel cell vehicles using the aerodynamic
optimization and data mining methods. Int. J. Hydrogen Energy 2020, 45, 11276–11286.
80. La maintenance Prédictive Intelligente Pour L’industrie 4.0. Techniques de L’ingénieur. Available online: https:
//www.techniques-ingenieur.fr/base-documentaire/genie-industriel-th6/mise-en-uvre-de-la-maintenance-42136210/la-
maintenance-predictive-intelligente-pour-l-industrie-4-0-mt9572/ (accessed on 20 April 2022).
81. Nordal, H.; El-Thalji, I. Assessing the Technical Specifications of Predictive Maintenance: A Case Study of Centrifugal Compressor.
Appl. Sci. 2021, 11, 1527. [CrossRef]
82. Ali, J. Assessing the Impact of Business Model for Predictive Maintenance Scenarios Using Multimethod Simulation: A Case
Study of Centrifugal Compressor. Master’s Thesis, University of Stavanger, Stavanger, Norway, 2020.
83. Gholami, H.; Abu, F.; Lee, J.K.Y.; Karganroudi, S.S.; Sharif, S. Sustainable Manufacturing 4.0—Pathways and Practices. Sustainabil-
ity 2021, 13, 13956. [CrossRef]
84. Aminzadeh, A.; Sattarpanah Karganroudi, S.; Meiabadi, M.S.; Mohan, D.G.; Ba, K. A Survey of Process Monitor-ing Using
Computer-Aided Inspection in Laser-Welded Blanks of Light Metals Based on the Digital Twins Concept. Quantum Beam Sci.
2022, 6, 19. [CrossRef]
Appl. Sci. 2022, 12, 8081 22 of 22

85. Jamil, N.; Gholami, H.; Mat Saman, M.Z.; Streimikiene, D.; Sharif, S.; Zakuan, N. DMAIC-based approach to sus-tainable value
stream mapping: Towards a sustainable manufacturing system. Econ. Res.-Ekon. Istraživanja 2020, 33, 331–360. [CrossRef]
86. Lee, J.K.Y.; Gholami, H.; Saman, M.Z.M.; Ngadiman, N.H.A.B.; Zakuan, N.; Mahmood, S.; Omain, S.Z. Sustainability-oriented
Application of Value Stream Mapping: A review and classification. IEEE Access 2021, 9, 68414–68434. [CrossRef]
87. Flexible Data Communication and IIoT Platform in Industrial Applications—Ewon Flexy. Available online: www.ewon.biz
(accessed on 28 July 2022).