See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/361397997

Industry 4.0 Technologies for Maintenance Management – An Overview

Chapter · January 2023

DOI: 10.1007/978-3-031-09382-1_7

CITATIONS READS

3 742

2 authors:

Małgorzata Jasiulewicz-Kaczmarek Katarzyna Antosz

Poznan University of Technology Rzeszów University of Technology
86 PUBLICATIONS 1,220 CITATIONS 82 PUBLICATIONS 825 CITATIONS

SEE PROFILE SEE PROFILE

All content following this page was uploaded by Małgorzata Jasiulewicz-Kaczmarek on 26 December 2022.

The user has requested enhancement of the downloaded file.

Management and Production Engineering Review
Volume 11 • Number 2 • June 2020 • pp. 74–87
DOI: 10.24425/mper.2020.133730

MAINTENANCE 4.0 TECHNOLOGIES – NEW OPPORTUNITIES

FOR SUSTAINABILITY DRIVEN MAINTENANCE
Małgorzata Jasiulewicz-Kaczmarek1 , Stanisław Legutko1 , Piotr Kluk2
1
Poznan University of Technology, Poznan, Poland
2
Zelka Sp. z o.o., Psary Małe, Poland

Corresponding author:
Małgorzata Jasiulewicz-Kaczmarek
Poznan University of Technology
Faculty of Engineering Management
Prof. Jacka Rychlewskiego 2, 60-965 Poznan, Poland
phone: +48 61 6653364
e-mail: [email protected]

Received: 15 November 2019 Abstract

Accepted: 17 May 2020 Digitalization and sustainability are important topics for manufacturing industries as they
are affecting all parts of the production chain. Various initiatives and approaches are set
up to help companies adopt the principles of the fourth industrial revolution with respect
sustainability. Within these actions the use of modern maintenance approaches such as
Maintenance 4.0 is highlighted as one of the prevailing smart & sustainable manufacturing
topics. The goal of this paper is to describe the latest trends within the area of maintenance
management from the perspective of the challenges of the fourth industrial revolution and
the economic, environmental and social challenges of sustainable development. In this work,
intelligent and sustainable maintenance was considered in three perspectives. The first per-
spective is the historical perspective, in relation to which evolution has been presented in the
approach to maintenance in accordance with the development of production engineering. The
next perspective is the development perspective, which presents historical perspectives on
maintenance data and data-driven maintenance technology. The third perspective, presents
maintenance in the context of the dimensions of sustainable development and potential op-
portunities for including data-driven maintenance technology in the implementation of the
economic, environmental and social challenges of sustainable production.
Keywords
Maintenance 4.0, smart maintenance, data-driven maintenance, sustainable maintenance.

Introduction ous aspects are highlighted [3]. In general, Industry

4.0 can be defined as a term collectively describing
Manufacturing companies and equipment man- changes in technological scope and organization of
ufacturers face two major changes affecting their value chains [4]. This definition highlights two main
business: digitalization and the sustainability. From aspects of digital transformation, namely the tech-
the point of view of digitalization in the literature nological aspect and the business aspect. The tech-
on production, the changes are referred to as the nological aspect refers, among other things, to new
next (fourth) industrial revolution, which is often re- possibilities of implementing and monitoring process-
ferred as ‘Smart manufacturing’, ‘Industry 4.0’ and es through the use of digital technologies [5, 6], while
‘Smart Factory’ [1]. Only two years ago, Industry the business aspect includes primarily new business
4.0 was considered the future, today it is a wide- models [7]. In Industry 4.0 environment, manufac-
ly accepted reality that changes the way companies turing systems are able to monitor physical process-
operate and affects almost every industry around es, create a so-called ‘digital twin’ of the physical
the world [2]. The term Industry 4.0 is defined in system, and make smart decisions by real-time com-
literature in many ways. Depending on the direc- munication and cooperation with humans, machines,
tion of the research conducted by the authors, vari- sensors, etc. [8, 9].

74
 Management and Production Engineering Review

The second major change affecting manufactur- From Maintenance 1.0

ers is the sustainable development (SD). Brundtland to Maintenance 4.0
Commission (1987) defined SD as ‘development that
meets the needs of the present without compromis- In the last years, due to the evolution of technol-
ing the ability of the future generation to meet their ogy, machines have become more and more complex
own needs’. In sustainable development environment, and they also became more critical in terms of reli-
there has been an increased pressure on manufac- ability and availability. To reduce the risk and mini-
turing companies to think beyond traditional eco- mize the consequences of unexpected stops and dis-
nomic measure and evaluate environmental and so- ruptions in digitalized manufacturing, maintenance
cial effects of the business. As described by [10] sus- must take a key role [13]. Over time, maintenance
tainable manufacturing seeks to ensure that produc- has evolved from reactive (Maintenance 1.0 – M1.0)
tion will be performed economically, considering re- to preventive (Maintenance 2.0 – M2.0) and then to
sources use, and securing social standards. condition based (Maintenance 3.0 – M3.0), to current
In the Industry 4.0 context, sustainable manu- predictive and prescriptive approach which is usually
facturing definition and approach can be linked with denoted as Maintenance 4.0 – M4.0 (Fig. 1).
production systems developed in order to be con-
scious, transparent, intelligent, efficient, flexible, ag-
ile, collaborative and responsive [11]. Digitalization
and sustainability are important topics for manufac-
turing industries as they are affecting all parts of the
production chain. According to [11] ‘both approach-
es present practices’ convergence, such as: design for
disassembly, remanufacturing, and recycling applied
in the life cycle management; reverse logistics for cir-
cular economy, ‘lean and green management’ for re-
source efficiency; sustainable design reducing safety
risks for workers’ and consumers’ eliminating the use
of toxics parts in the product and production pro-
cesses’.
In such a context, various initiatives and ap-
proaches are set up to help companies adopt the prin- Fig. 1. Development of industrial maintenance.
ciples of the fourth industrial revolution with respect
sustainability. Within these actions the use of mod- During the first generation (Corrective mainte-
ern maintenance approaches such as Maintenance 4.0 nance or Maintenance 1.0), the machines were slow
(also called Smart Maintenance) is highlighted as one and simple to work and were simple in design and
of the prevailing smart & sustainable manufacturing easy for repairing. Machine operators were responsi-
topics [12, 13]. ble for equipment maintenance. Maintenance actions
The goal of this paper is to describe the lat- were based on solving the faults that have already
est trends within the area of maintenance manage- happened. As the complexity of the machines grew
ment from the perspective of the challenges of the and the maintenance operations increased, enterpris-
fourth industrial revolution and the economic, envi- es started to include maintenance departments in
ronmental and social challenges of sustainable deve- their structure. The objective of maintenance depart-
lopment. ment was to reduce the number of corrective main-
The rest of the paper is as follows. Firstly (chap- tenance actions applied through periodic checks and
ter 2), a short literature review related to evolution replacement of worn parts. The concept of a system
on maintenance is introduced. In the next chapter, of planned preventive repairs has appeared (Main-
the evolvement history of maintenance data is re- tenance 2.0). Its essence is servicing machines and
viewed and date driven maintenance technologies are devices at predetermined time intervals while often
presented. The fourth chapter is devoted to issues of making use a checklist of original equipment manu-
sustainable maintenance. The fifth chapter presents facturers (OEM) recommendations.
the potential applications of Maintenance 4.0 tech- The start of automation or more complex systems
nology in relation to the economic, social and en- paved the way for maintenance to next generation –
vironmental challenges of sustainable development. Maintenance 3.0 (also called Condition Based Main-
Finally, the main conclusion is presented. tenance – CBM). The expectations of maintenance

Volume 11 • Number 2 • June 2020 75

Management and Production Engineering Review

were of higher equipment availability and reliabil- Predictive maintenance employs the use of sen-
ity, better product quality, long equipment life and sors to precisely collect data describing manufac-
great cost effectiveness. The development of automa- turing equipment’s condition and overall operational
tion gave the ideas for developing more maintenance state. The data can then be analysed to predict when
models, which would contribute the production and failure events will occur [23]. The key technologies
profit. According to [14], CBM is a maintenance pro- involved in predictive maintenance are data collec-
gram that recommends maintenance actions (deci- tion and analysis technologies, such as Internet of
sions) based on the information collected through Thinks (IoT), cloud computing, predictive analysis
condition monitoring process. (such as fuzzy logic, neural networks, evolutionary
With the Industry 4.0, new maintenance algorithms, machine learning, probabilistic reason-
paradigm, innovative methods and tools have to be ing), and equipment repair technologies [24–26]. Gru-
developed. Maintenance has to change towards the bic [27] suggests that the use of predictive mainte-
requirements of Industry 4.0 to become an enabler nance strategy is stimulated by servitization.
for the smart factory [15]. In the context of Indus- At the top level of Maintenance 4.0 (Fig 1), the
try 4.0, the maintenance function is often denoted as use of advanced data analytics methods allows to not
Maintenance 4.0 or Smart Maintenance [16] and is only predict when a failure occurs, but also by us-
defined as: ing libraries of standard maintenance tasks, prescribe
• ‘a subset of the smart manufacturing system recommendations to avoid such a failure and opti-
represented by self-learning and smart machines mize maintenance schedulers and resources. Thus,
that predicts failure, makes diagnosis and triggers the concept of prescriptive maintenance goes far be-
maintenance actions’ [17]; yond simply predicting failures [28]. Based on the
• ‘is the application of machine learning, automat- analysis of historical data and real-time data on the
ed processes and robotics/drones to reliability and state of the machine, required maintenance measures
maintenance activities’ [18]; are predicted by a system and a course of action is
• ‘is about predicting future failures in assets and ul- prescribed. Prescriptive maintenance means chang-
timately prescribing the most effective preventive ing the paradigm and moving from planned pre-
measure by applying advanced analytic techniques ventive maintenance to proactive and smart main-
on big data about technical condition, usage, envi- tenance planning [29].
ronment, maintenance history, similar equipment
elsewhere and, in fact, anything possibly relating Data-driven maintenance
to the performance of an asset’ [19].
According to [20], ‘Smart Maintenance stands for Maintenance data from time perspective
an intelligent and learning maintenance management For any scientific maintenance practices, data
focusing on permanent improvement’. According to are one of the most important requirements. In
[21] ‘Maintenance 4.0 does predictive analytics and the Maintenance 1.0 age, because of manufacturing
suggests feasible solution, with major application in equipment was simply, maintenance activities were
Industry 4.0 and especially on those maintenance as- of low complexity. As a result, the data generated
pects that deals with collection of data, its anal- in the maintenance tasks was limited, as it existed
ysis and visualization and asset decision-making’. mostly in the form of equipment operator experience.
Recently [22] developed a conceptual definition of Machine operators and storage in operators’ memory
Smart Maintenance as ‘an organizational design for collected the maintenance data manually.
managing maintenance of manufacturing plants in In the Maintenance 2.0 age, the way data was ac-
environments with pervasive digital technologies’ quired and processed has changed. The increase in
and defined the four underlying dimensions: data- demand for products has led, among other things, to
driven decision-making, human capital resource, in- an increase in mechanization. Availability, durabili-
ternal integration, and external integration. ty and costs were recognized as important factors for
Given the above, Smart Maintenance or Mainte- achieving business goals. Enterprises began to estab-
nance 4.0 describes a set of techniques to monitor the lish specialized technical services (separate organiza-
current condition of machines with the goal to pre- tional units) to carry out maintenance and repair
dict upcoming machine failure by using automated tasks, and machine and device operators in prac-
(near) real-time analytics and supervised or unsu- tice did not participate in these activities and had
pervised machine learning, and to prescribe optimal no impact on their scope. Maintenance data was in-
course of action in real time, analyse potential deci- creasingly handled by maintenance managers. Main-
sions and interaction between them. tenance managers began to employ more systemat-

76 Volume 11 • Number 2 • June 2020

 Management and Production Engineering Review

ic methods to document and analyse maintenance computer systems and managed by information sys-
data. The raw data was recorded in written docu- tems. In addition, the effectiveness of data analysis
ments rather than stored in machine operator mem- has also increased due to the use of computational
ory. Machine-related data was used to support de- models. Still, in the decision-making process, the re-
cisions concerning machine maintenance, repair, and sults of the analysis required interpretation by heads
replacement. In particular, statistical models were in- of maintenance. Due to implementation costs and
troduced to analyse failure rate and spare parts con- competences necessary to maintain maintenance IT
sumption. Nevertheless, despite the fact that a larger systems, many manufacturing companies (especial-
quantity of maintenance data was analysed through ly small and medium-sized enterprises) still found
scientific methods, data was still handled manual- it difficult to benefit from the value of maintenance
ly by maintainers. Therefore, the utilization rate of data.
maintenance data remained relatively low. In recent years, due to the significant increase
With the introduction of the next industrial rev- in digitization and automation, as well as the com-
olution (referred to in the literature as the informa- plexity of production equipment, requirements for
tion age), the role of information technologies and maintenance management have changed [15]. To-
the scope of their application in production process- day’s maintenance managers face great challenges to
es increased. Consequently, the companies gained increase output, to reduce equipment downtime, to
the ability to obtain a large amount of data on lower costs, and to do it all with less risk to safety and
both production processes and maintenance process- the environment. Thanks to new technologies of In-
es. Many factors influenced this ability. First, in or- dustry 4.0 (such as the Internet of Things and cloud
der to facilitate maintenance management in produc- computing), the possibility of collecting and storing
tion enterprises, IT systems, e.g. CMMS (Computer as well as their processing and analysis has signifi-
Maintenance Management System), have been used. cantly increased. As a result, heads of maintenance
Secondly, machine and device manufacturers have departments, and consequently business managers,
started to use computer systems such as computer- can start to benefit from the value of data. Effec-
aided design (CAD) and computer aided manufac- tive analysis of data enables equipment manufactur-
turing (CAM) to modify and optimize new machines. ers and machines users to deepen their understanding
Thirdly, electronic devices and computers began to of equipment, processes, services, employees, suppli-
be used to automatically control production devices. ers, and regulators requirements. The comparison of
Data from the processes of use and maintenance pro- maintenance data in different maintenance ages is
cesses of machines and devices began to be stored in shown in Table 1.

Table 1
Comparison of maintenance data in different maintenance ages.
Maintenance 1.0 Maintenance 2/0 Maintenance 3.0 Maintenance 4.0
Data source Operator experience Maintainer and ma- Operator, main- Operator, maintain-
chines tainer, machines, er, information sys-
information and tems, OEM and sup-
computer sys- pliers data
tems
Data collection Manual collection Manual collection Semi-automated Automated collection
collection via sensors and IoT
Data storage Operator memory Written documents Databases Cloud services
Data analysis Arbitrary Reliability theory Conventional al- Fuzzy logic, neutral
based on Bathtub gorithms networks, evolution-
curve assumption ary algorithms, ma-
chine learning
Data transfer Verbal communication Written documents Digital files Digital files
Data management N/A Human operators Information sys- Cloud and artificial
tems intelligence

Volume 11 • Number 2 • June 2020 77

Management and Production Engineering Review

Data-driven innovation in maintenance predictive way than before. However, due to a lack
of knowledge and understanding, data from machine
The term ‘data-driven’ means the fact that imple-
use and operation processes is often left unused be-
mented activities and processes are primarily stim-
cause people simply do not know how to extract use-
ulated by data, not by intuition or experience. In-
ful information and/or knowledge from data, or do
creasing easier access to data and awareness of the
not recognize the potential that is hidden in all col-
possibilities offered by data in the decision-making
lected data. To explore data, advanced data analysis
process drives enterprises to shift towards a new type
is required. Runkler [37] defines data analytics as the
of maintenance strategy called data-driven mainte-
use of mathematical methods to obtain information
nance [30–33]. Research conducted by [34] show, that
from data in order to optimize processes and sup-
among 14 most important innovations in mainte-
port decision-makers in the decision-making process.
nance till 2020 five (smart sensor, big data, integrat-
Big data analysis (BDA) is the sub-area of big da-
ing asset management IT systems, mobile solution
ta concerned with adding structure to data to sup-
and 3D design/virtual reality) are primarily data-
port decision-making as well as supporting specific
driven, where several of the process-driven innova-
usage scenarios. From the point of view of mainte-
tions, such as CBM, are also strongly data-driven
nance management, BDA can help maintenance de-
(Fig. 2).
partments in the company and OEM to better un-
derstand the open and hidden information contained
within the data and enables identification of the data
which from future decision-making perspective (e.g.
on investments, changes of service strategy etc.) are
the most important [38, 39]. Karim et al. [40] devel-
oped the concept for Maintenance Analytics. This
concept based on four phases (Fig. 3): descriptive
analytics, diagnostic analytics, predictive analytics
and prescriptive analytics.

Fig. 2. Interdependencies between the ‘Top 14’ mainte-

nance innovations [34].

Data is the key to intelligent maintenance. Un-

til recently, the main problem for maintenance man-
agers was the lack of information sources. Today
the situation has changed. Over the past ten years,
due to the intense development of information and
communication technologies and their applications
in production systems, and the development of sen-
sor technology (e.g. smart sensors that allow, among
others, digital signal processing and wireless data
streaming) have caused that the maintenance sys-
Fig. 3. Maintenance analytics phases.
tem managers have gained a lot new data sources.
These new data sources are rapidly generating large
amounts of different types of data, known as big da- Descriptive analytics answers the question ‘What
ta. That data are available for maintenance decision happened?’ by providing information about previ-
makers and provide opportunities for enhancing the ous maintenance operations. Diagnostic data analy-
performance of maintenance processes [35, 36]. Big sis can respond to ‘Why it happened?’ by identifying
data has been often described as the next frontier causes. Predictive analytics estimates future events
for innovation, competition, and productivity. The (what will happen, when?) by learning from histor-
use of data allows a better understanding of fac- ical maintenance data (possibly in real-time). Pre-
tors affecting the operation of individual machines scriptive analytics can respond to ‘What should be
and entire systems and provide more opportunity to done?’ by providing actionable recommendations for
predict upcoming issues in an equipment or system. decision making and improving and/or optimizing
Thanks to this, the implementation of maintenance forthcoming maintenance processes. Both descriptive
activities will be able to be carried out in a more and diagnostic analytics methods are reactive while

78 Volume 11 • Number 2 • June 2020

 Management and Production Engineering Review

predictive and prescriptive analytics approaches are benefits that AR could provide to maintenance, re-
proactive. pair and assembly tasks have been analysed by [51,
Analysing the literature, it can be stated that 52]. Webel et al. [53] developed a method for multi-
Big Data analytics in maintenance has opened new modal AR-based training of maintenance skills. Ac-
opportunities to support maintenance managers in cording to [54], AR technology in maintenance, vi-
the decision-making process, while for scientists it sualizing digital instruction in real time on the real
has opened new research areas. For example, [41] de- working area, can potentially lead to many advan-
veloped an industrial big data pipeline architecture, tages, such as: ‘employ less-skilled operators; data
which is designed to meet the needs of data-driven in- are up to date; time and cost saving; error rate re-
dustrial analytics applications focused on equipment duction; knowledge is retained in the system and not
maintenance in large-scale manufacturing. Solution in people; the information level can be adapted to
presented in the paper is based on real-world require- the user skills’. Masoni et al. [55] present a solu-
ments obtained from manufacturing facility. Cortadi tion for remote maintenance based on off-the-shelf
et al. [42] proposed solution for the predictive main- mobile and AR technologies. Manuri et al. [56] pro-
tenance problem in a real machining process. The posed a system for supporting maintenance proce-
authors developed a decision-making application to dures through AR. The system consists a computer
provide a visual analysis of the Remaining Useful Life vision algorithm, which is able to evaluate, at each
(RUL) of the machining tool. Truong [43] used Big step of a maintenance procedure, if the user has cor-
Data Cloud and IoT to provide a predictive analytics rectly completed his task, or not. The areas with
approach for maintenance. On the other hand, many a great number of applications of AR in maintenance
new challenges have been raised. One of the gaps in processes are: aerospace [57–59], automotive [60–62]
the existing literature on the analysis of large data and industrial plants [4, 63]. Due to the increas-
sets in maintenance is that the proposed concepts ing complexity of maintenance processes, various as-
and solutions are either only useful for some types sistants (e.g., tablets with smart software, smart-
of maintenance problems, or are not detailed enough phones, and virtual assistants) increasingly support
and do not describe the procedures for analysing data employees of technical departments. Using an AR ap-
and components needed to develop specific data anal- plication on smartphones or tablets supports main-
ysis solutions in maintenance systems. Therefore, in tenance technicians in making informed decisions
order to effectively apply the analysis of large data about maintenance and repair activities and their
sets in maintenance systems and support decision- safe implementation.
makers in the decision-making process, it is neces-
In the context of Industry 4.0, a digital machine
sary to integrate skills and knowledge in the field
is not only the material result of the production pro-
of information and communication technologies with
cess. The digital machine is also an intelligent source
engineering knowledge and expert knowledge.
of data obtained from the process of its use. These
An important aspect of using large data sets is data allow physical machines to gain a new virtual
the visualization of analysis results, including the dimension by building their digital equivalent called
presentation of trends and other forecasts using ap- ‘digital twin’ [64–66]. According to [67], ‘A digital
propriate visualization tools [44]. Due to the com- twin is a virtual representation of a physical object
plexity of large data sets, conventional data visual- called a Physical Twin. The physical and the digi-
ization tools and techniques such as tables, bars or tal twin may be connected to each other. A digital
line charts are insufficient. Visualizing big data re- twin can provide more information about its physical
quires some innovative approaches. The main pur- twin than the physical twin itself can provide’. By us-
pose of modern methods of data representation is ing cloud-connected sensors embedded in machines,
to improve the forms of images, diagrams or ani- it is possible to send data from the operational le-
mations so that they are useful for decision-makers vel in real time, and this allows you to create cur-
without forgetting that human perception is, howe- rent virtual simulations of real machines (real-world
ver, limited. machines). One of the areas of application of digi-
According to [45], the trend recognized in visu- tal twin technology is and will be in the near future
alization of big data sets is implementation of aug- to monitor the operational status and functionality
mented reality (AR). AR visualization is a popular of complex and critical machines, especially in indus-
visualization technique that combines the real world tries where an emergency event can have catastroph-
and virtual objects. The literature on AR identifies ic consequences for people and the environment. Ac-
maintenance service as one of the growing applica- cording to [65] and [68] digital twin can be used
tion areas [46–50]. A set of possible applications and to predict of the remaining useful life (RUL) of the

Volume 11 • Number 2 • June 2020 79

Management and Production Engineering Review

physical machine by using a combination of physics- OEMs it is possible to reduce the total cost of own-
based models and data-driven analytics. Wang et al. ership and reduce the risk to customers [74].
[69] presents a digital twin reference model for rotat-
ing machinery fault diagnosis. Cattaneo and Mac- Sustainability-driven maintenance
chi [70] developed a maintenance digital twin solu-
tion for a drilling machine with low availability of
In the last few years, research has focused on
run-to-failure data. Research conducted among oth-
a sustainable manufacturing paradigm, which aims
ers by [64, 66, 71] indicate that the use of digital
to develop sustainable production processes, innova-
twin technology gives a number of possibilities in
tive technologies, and new tools for evaluating eco-
the field of simulation and optimization of mainte-
nomic, environmental, and social impacts of industri-
nance processes, including but not limited to: eval-
al assets. According to [75], ‘The maintenance activ-
uation of machine conditions based on descriptive
ity is by nature an important lever for action on the
methods and machine learning algorithms, identifi-
sustainability of production systems’. As described
cation and evaluation of potentially applicable main-
by [76], ‘maintenance as part of the circular econ-
tenance methods as well as integration, analysis and
omy can be considered, first, as an enabling sys-
management of data from machines and production
tem to sustain the artefact throughout its life cycle,
processes and their processing at equal stages of the
then as a key tool to keep the regeneration poten-
machine / technical system life cycle. In general, the
tial of this artefact, and finally, as a target system
far-reaching goal of research is to launch a digital
that must be sustainable’. In this context ‘mainte-
twin for any real technical system. One of the im-
nance function, necessary to ensure the availability,
portant factors enabling the implementation of this
reliability, and safety of industrial assets, could be-
goal is the completeness of the database necessary to
come one of the main pillars for sustainable man-
build such models and then supply them with oper-
ufacturing’ [12]. As such, sustainability goals must
ational data that would allow updating the status of
be included in conventional maintenance processes.
the digital twin. The challenge, therefore, is the in-
Jasiulewicz-Kaczmarek and Żywica [77] defined Sus-
tegration of real-time data streams into simulation-
tainable Maintenance as ‘a set of proactive technical,
based and digital models of machines for real-time
economic and management activities implemented
(re) configuration and online directing of machines.
throughout the whole life-cycle of a technical facili-
The next of the most frequently mentioned tech- ty aimed at realizing functions of a technical facility,
nologies supporting Maintenance 4.0 are a group ensuring at the same time the achievement of goals
of technologies referred to as a common name and the ability to create the economic, environmental
Additive Manufacturing. According to ISO/ASTM and social value for all stakeholders in the long-term
52900:2015, Additive Manufacturing (AM) is ‘the horizon’.
process of joining materials to make objects from 3D In the last years, the role of maintenance as con-
model data, usually layer upon layer, as opposed to tributing to the sustainable manufacturing has at-
subtractive and formative manufacturing methodolo- tracted more attention [12, 78, 79]. Hennequin and
gies’. From the point of view of maintenance, the aim Restrepo [80] proposed a fuzzy system to estimate
is to utilize 3D printing technology to reduce stock the hedging point and preventive maintenance peri-
levels and optimize all of the logistics, which sur- od values taken into account the economic cost, an
round maintenance activities. According to [72], 3D environmental impact corresponding to greenhouse
printing ‘will have a significant impact on the spare gas emissions and a social impact corresponding to
parts business. 3D printing will enable suppliers to machine ergonomics and incidents. Afrinaldi et al.
increase the availability of spare parts, reduce lead [81] developed a mathematical model optimizing the
time, and decrease costs’. preventive replacement schedule to minimize the to-
In summary, data-driven technologies of Industry tal economic and environmental impacts of an as-
4.0 provide a set of main directions and suggestions set. Hoang et al. [82] proposed the Residual Ener-
for implementing data-driven maintenance strate- gy Efficiency Life concept, to estimate the time left
gies. The incentive for the implementation and ap- before the object loses its energy efficiency prop-
plication of new technologies by both machine users erty. Ighravwe and Oke [83] based on four of the
and their manufacturers is a set of benefits, among sustainability criteria (economic, environmental, so-
which the most frequently mentioned are [73]: im- cial and technical) proposed the structure of mainte-
proving the efficiency and availability of production nance system sustainability for manufacturing con-
equipment, reducing costs, flexibility in approaching cerns. The authors developed the idea of selecting
customer requirements. In addition, in the case of the proper maintenance strategy based on integrat-

80 Volume 11 • Number 2 • June 2020

 Management and Production Engineering Review

ed fuzzy axiomatic design (FAD) principle and fuzzy- nies’ ability to leverage their data assets for decision
TOPSIS. Boral et al. [84] proposed a hybrid artificial making, planning, and executing maintenance activ-
intelligence based conceptual decision-making model ities.
to solve sustainable maintenance strategy selection From the point of view of sustainable production,
problems. Singh and Gupta [85] identified fourteen it is also important to note that none of the compa-
maintenance factors for sustainable performance im- ny’s organizational functions and no process add val-
provement. By using ISM (Interpretive structural ue on its own (independently). Maintenance serves
modelling) and fuzzy MICMAC (Matriced’ Impacts several different stakeholders, each with their own
Croisés Appliquée á un Classement) the authors de- focus. Generally, these are production, business, and
veloped a framework for sustainable performance society. The challenge for the maintenance manag-
improvement and ranking the major driving fac- er is to balance the interests of production (uptime,
tors by TOPSIS approach. According to the authors overall equipment effectiveness), business (spent as
top management support and commitment, strategic a percentage of the total asset value), and society
planning and implementation, continuous upgrada- (environment, health & safety). The typical trade-
tion of maintenance system to reduce manufacturing off choices in maintenance arise from trying to pro-
lead-time and cost are major factors to ensure the vide the maximum value to stakeholders. From the
sustainable competitive advantage. one hand companies want to maximize quality (e.g.,
Based on literature review maintenance contri- repair quality, doing it right the first time), service
bution to business competitive priorities and more level (e.g., prevention of failures), output (e.g., relia-
sustainable manufacturing processes has two main bility and uptime) and at the same time, they want
dimensions: sustainability dimension (represented by to minimize time (e.g., time and mean time to repair
the three sustainability aspects: economic, environ- – MTTR), costs (e.g., cost per unit output) and risk
mental and social) and life-cycle dimension (repre- (e.g., predictability of unavoidable failures) [91].
sented by three life-cycle phases: beginning of life
(BOL), middle of life (MOL) and end of life (EOL)). Smart & sustainable maintenance
Regarding the economic aspect of maintenance con-
tribution, there are four relevant economic factors
affected by the maintenance function: quality and According to [92], the enabling technologies of the
productivity, delivery on time, innovation and cost Maintenance 4.0 could become key-drivers in pursuit
[86]. With reference to the social aspects, according of sustainable maintenance and asset life-cycle man-
to [87], in maintenance management, ‘social impli- agement. Digital technologies integrated within the
cations’ should be made ‘mandatory’ instead of ‘if Maintenance 4.0 concept enable real-time access to
applicable’. Social sustainability of maintenance pro- detailed information on the status, availability and
cesses involves wider social benefits that can be de- current location of the technical facility. From the
rived from delivering high quality maintenance ser- point of view of managing the life cycle of techni-
vices. This means investing to maximize contribu- cal facilities and meeting the challenges of sustain-
tions to people’s health and safety, development of able maintenance, this is very important. It increases
their competences, satisfaction from work, etc. Fi- the transparency of information about the real con-
nally, environmental sustainability can be achieved dition of a technical object throughout its life cycle
by resource efficiency (water, air, energy, spare parts and enables appropriate actions to be taken to ex-
and materials), prevention of environmental dam- tend the life cycle by the OEM or service provider
age, emission reductions and land conservation [22, [93]. In addition, making decisions regarding main-
88, 89]. tenance based on data instead of relying on people’s
The perspective of the life cycle of manufactur- experience can increase the credibility of decisions,
ing equipment has prompted the redefinition of the and thus increase the effectiveness of ongoing main-
maintenance role as being ‘a prime method for life tenance activities and the efficiency of related human
cycle management whose objective is to provide so- and material resources (spare parts and auxiliary ma-
ciety with the required functions while minimizing terials).
material and energy consumption’ [90]. In Sustain- The literature analysis shows that deploying
able Maintenance, the perspective of life cycle man- data-driven maintenance approach creates many new
agement focuses on the management of information opportunities for improving maintenance processes.
along the equipment life cycle. Effective and effi- The improvements concern all dimension of sustain-
cient maintenance processes depend upon compa- ability (Table 2).

Volume 11 • Number 2 • June 2020 81

Management and Production Engineering Review

Table 2
Benefits from implementation of new technologies in Maintenance confronted with SD dimensions – examples.
Potential benefits Description References
Improves economic effi- Predictive maintenance can reduce machine
ciency. downtime and the cost of unplanned down-
time. Regular maintenance of machines and [1, 15, 25, 34, 42, 70, 84, 85, 94, 95]
systems can increase their service life.
Economic dimension

Reduces maintenance Continuously evaluation of the captured data

time makes it possible to determine the best time
for an upcoming maintenance. Automatic re-
ports for maintenance scheduling and proac-
tive repairs reduce maintenance time and de-
creases overall maintenance costs.
Improves machine per- The permanent analysis of the collected data
formance makes it possible to improve the performance
of the machine and achieve higher productivity
in the long run.
Decreases spare parts 3D printing can provide benefits in spare parts
inventories creating, particularly it is good solution when
parts that are discontinued are needed.
Decreases spare parts With condition-based, predictive and main-
and lubricant utiliza- ly prescriptive maintenance worn equipment
tion. parts are replaced only when necessary, lubri- [1, 13, 15, 18, 34, 38, 42, 84, 94, 96]
cants are changed only as needed, rather than
Environmental dimension

on a fixed schedule for planned or preventive

maintenance.
Improves environmen- Breakdowns of machinery can lead to catas-
tal safety trophic events. By predicting issues before
they escalate, it will be able to reduce envi-
ronmental impact.
Minimizes end of life Predictive maintenance promoted by big data
waste analytics extends the lifespan of machinery.
Optimizes energy con- Enhancing ecological footprint by better gaug-
sumption ing and controlling energy consumption and
environmental conditions for energy conserva-
tion.
Implements new edu- Through virtual reality, it is possible to ed-
cational model. ucate operators, by teaching the right opera-
tions to do for maintenance or machine setup. [12, 72, 73, 75, 78, 97, 98]
The augmented reality system aims to replace
old paper manuals that are difficult to under-
stand.
Social dimension

Improves worker safety Breakdowns of machinery can lead to catas-

trophic events and harm workers. By predict-
ing issues before they escalate, it will be able
to reduce accidents and boost team morale.
Improves working con- Through the application of virtual reality it is
dition possible to obtain additional information and
to proactively assess different variants of main-
tenance processes realization to optimize the
key factors of the given operation of manual
work, visibility, accessibility, usability of equip-
ment, comfort and risk factors.
Improves workers satis- Work performed in safe and healthy condi-
faction tions improves the efficiency of the mainte-
nance staff and increases their motivation and
efficiency.

Some studies have described servitization as outcomes of this study suggested that a data-driven
a useful business model to address environmental maintenance strategy had a positive effect on profit
and social demands [99]. Rodseth et al. [94] present- loss indicator values, which can be analysed for long-
ed a structured approach for data-driven predictive term sustainability. Zhang et al. [100] proposed BDA
maintenance in terms of profit loss indicator. The architecture for maintenance processes of complex

82 Volume 11 • Number 2 • June 2020

 Management and Production Engineering Review

products to make better cleaner production decisions which evolution has been presented in the approach
based on lifecycle data. According to [101] usage of to maintenance in accordance with the development
BDA can significantly enhance the ability to predict of production engineering. The next perspective is
failures for key spare parts. By applying predictive the development perspective, which presents histor-
maintenance service, the reliability of machines can ical perspectives on maintenance data and data-
be increased and empty load energy consumption due driven maintenance technology. The third perspec-
to stopping and restarting of equipment and down- tive, on the other hand, presents maintenance in the
time can be reduced. Furthermore, by using the spare context of the dimensions of sustainable development
part prediction service, the inventory cost and mate- and potential opportunities for including data-driven
rial consumption can also be reduced. Bevilacqua et maintenance technology in the implementation of the
al. [102] proposed a data analytic model for IoT, in economic, environmental and social challenges of sus-
order to integrate the data collected from different tainable production.
sources (e.g., workstations energy consumption, ma- The amount of dynamically changing data gener-
terial delivery date from suppliers, working time and ated over the entire life cycle of technical objects is
manufacturing cycle) and to improve energy-aware growing. Data-based production technologies are an
decision-making. Macchi et al. [64] suggested digital inspiration for using data-based maintenance. A set
twin modelling as full of promises about the lifecy- of benefits resulting from such an approach, such as
cle management of assets. Bevilacqua et al. [66] pro- improving the efficiency and availability of the com-
posed a reference model for the implementation of pany’s technical resources, reducing costs, or flexibil-
Digital Twin models with the purpose of enhancing ity in approaching clients’ requirements is an incen-
the safety level of employees in the workplace. Ac- tive for the implementation and application of new
cording to the authors, the developed Digital Twin technologies, by both machine users and their manu-
model will enable virtual modelling of maintenance facturers. The collected data can be used not only to
processes, thus preventing high-risk events for oper- increase the efficiency of production machinery and
ators. equipment, and thus to achieve economic goals, but
In summary, maintenance management today is also to more efficient use of resources (technological
experiencing a real change in both human and tech- media, consumables and spare parts), and thus sup-
nological organizational level. Maintenance function port the enterprise in achieving environmental and
taking on ever-increasing importance within corpo- social. Maintenance of machinery and equipment is
rate functions. Now, it is not only simple production therefore considered in an increasingly broader con-
index with an unavoidable cost generation. Today text.
maintenance is a competitive tool and is considered
a profit centre in all respects. References
[1] Buchi G., Cugno M., Castagnoli R., Smart factory
Conclusions
performance and Industry 4.0, Technological Fore-
casting & Social Change, 150 119790, 2020.
For many years, maintenance was considered as
nonvalue-adding activity with a low level of automa- [2] Krdžalić A., Hodžić L., Sustainable engineering
tion and digitization. However, the last decade of de- challenges towards Industry 4.0: A comprehensive
review, Sustainable Engineering and Innovation, 1,
velopment in the area of intelligent technologies and
1, 1–23, 2019.
models for analysing large data sets has created new
opportunities not only in the scope of increasing the [3] Saucedo-Martinez J.A. et al., Industry 4.0 frame-
reliability, availability and efficiency of using techni- work for management and operations: a review,
cal objects, but also in the scope of challenges of envi- Journal of Ambient Intelligence and Humanized
ronmental and social implementation of sustainable Computing, 9, 789–801, 2018.
development. Today, maintenance is closely related [4] Sanna A. et al., Using Hand-Held Devices To Sup-
to the activity of a production company aiming to port Augmented Reality-Based Maintenance And
produce high quality products. The quality of main- Assembly Tasks, IEEE International Conference on
tenance operations determines the current quality of Consumer Electronics (ICCE), 178–179, 2015.
production means, i.e. devices and machines, which
[5] Alcácer V., Cruz-Machado V., Scanning the Indus-
largely determines the quality of products. try 4.0: A Literature Review on Technologies for
In this work, intelligent and sustainable mainte- Manufacturing Systems, Engineering Science and
nance was considered in three perspectives. The first Technology, an International Journal, 22, 3, 899-
perspective is the historical perspective, in relation to 919, 2019.

Volume 11 • Number 2 • June 2020 83

Management and Production Engineering Review

[6] Peruzzini M., Grandi F., Pellicciari M., Benchmark- events/vdm-xl-value-driven-maintenance-asset-ma-

ing of Tools for User Experience Analysis in Indus- nagement-3/.
try 4.0, Procedia Manufacturing, 11, 806–813, 2017.
[20] Kinz A., Bernerstaetter R., Biedermann H., Lean
[7] Ibarra D., Ganzaraina J., Igartua J.I., Business Smart Maintenance –Efficient and Effective Asset
model innovation through Industry 4.0: A review, Management for Smart Factories, MOTSP 2016 –
Procedia Manufacturing, 22, 4–10, 2018. 8th International Scientific Conference, 2016.
[8] Leyh C., Martin S., Schäffer T., Industry 4.0 and [21] Kumar U., Galar D., Maintenance in the Era of In-
Lean Production – A Matching Relationship? An dustry 4.0 : Issues and Challenges, [in:] Quality, IT
analysis of selected Industry 4.0 models, ACSIS and Business Operations: Modeling and Optimiza-
2017, 11, 989–993, 2017. tion, 231–250, 2018.
[9] Wang S. et al., Towards smart factory for Industry [22] Bokrantz J. et al., Smart Maintenance: an em-
4.0: A self-organized multi-agent system with big da- pirically grounded conceptualization, International
ta based feedback and coordination, Computer Net- Journal of Production Economics, 2019.
works, 101, 158–68, 2016.
[23] Jimenez-Cortadi A. et al., Predictive Maintenance
[10] Bonvoisin J., Stark R., Seliger G., Field of Research on the Machining Process and Machine Tool, Ap-
in Sustainable Manufacturing, [in:] R. Stark et al. plied Sciences, 10, 1, 224, 2020.
[Eds], Sustainable Manufacturing, Sustainable Pro-
duction, Life Cycle Engineering and Management, [24] Ganga D., Ramachandran V., IoT-Based Vibration
3–20, 2017. Analytics of Electrical Machines, Internet of Things
Journal IEEE, 5, 6, 4538–4549, 2018.
[11] Machado C.G., Winroth M.P., da Silva E.H.D.R.,
Sustainable manufacturing in Industry 4.0: an [25] Catenazzo D., O’Flynn B., Walsh M., On the use of
emerging research agenda, International Journal of Wireless Sensor Networks in Preventative Mainte-
Production Research 2019. nance for Industry 4.0, ICST, 256-262, 2018.
[12] Franciosi C. et al., Maintenance for Sustainability [26] Chen J., Zhang R., Wu D., Equipment Maintenance
in the Industry 4.0 context: a Scoping Literature Re- Business Model Innovation for Sustainable Compet-
view, IFAC PapersOnLine, 51–11, 903–908, 2018. itive Advantage in the Digitalization Context: Con-
notation, Types, and Measuring, Sustainability, 10,
[13] Jasiulewicz-Kaczmarek M., Gola A., Maintenance
3970. 2018.
4.0 Technologies for Sustainable Manufacturing –
an Overview, IFAC PapersOnLine, 52–10, 91–96, [27] Grubic T., Remote monitoring technology and servi-
2019. tization: Exploring the relationship, Computers in
[14] Jardine A.K.S., Lin D., Banjevic D., A review on Industry, 100, 148–158, 2018.
machinery diagnostics and prognostics implement- [28] Ansari F., Glawar R., Nemeth T., PriMa: a pre-
ing condition-based maintenance, Mechanical Sys- scriptive maintenance model for cyber-physical pro-
tem and Signal Process, 20, 1483–1510, 2006. duction systems, International Journal of Computer
[15] Passath T., Mertens K., Decision Making in Lean Integrated Manufacturing, 32, 4–5, 482–503, 2019.
Smart Maintenance: Criticality Analysis as a Sup-
[29] Matyas K. et al., A procedural approach for real-
port Tool, IFAC PapersOnLine, 52–10, 364–369,
izing prescriptive maintenance planning in manu-
2019.
facturing industries, CIRP Annals – Manufacturing
[16] Fumagalli L. et al., A smart maintenance tool for Technology, 66, 461–464, 2017.
a safe electric arc furnace, IFAC-PapersOnLine, 49,
[30] Antomarioni S. et al., Defining a data-driven main-
3, 19–24, 2016.
tenance policy: an application to an oil refinery
[17] Kans M., Galar D., The Impact of Maintenance 4.0 plant, Int. J. Qual. Reliab. Manag., 36, 1, 77–97,
and Big Data Analytics within Strategic Asset Man- 2019.
agement, [in:] Galar D., Seneviratne D. [Eds], MP-
[31] Sai V.C., Shcherbakov M.V., Tran V.P., Data-
MM 2016, conference proceedings, 96–103, 2017.
driven framework for predictive maintenance in In-
[18] Glazer O., Is there a shortcut to Industrial An- dustry 4.0 concept, Communications in Computer
alytics/Maintenance 4.0 implementation?, 2019, and Information Science, 1083, 344–358, 2019.
https://www.presenso.com/blog/maintenance4dep-
loymentshortcuts. [32] Zhang W., Yang D., Wang H., Data-driven methods
for predictive maintenance of industrial equipment:
[19] Haarman M., Predictive Maintenance 4.0, Main- a survey, IEEE Systems Journal, 13, 3, 2213–2227,
novation 2017 https://www.mainnovation.com/nl/ 2019.

84 Volume 11 • Number 2 • June 2020

 Management and Production Engineering Review

[33] 3 Basciftci B., Ahmed S.. Gebraeel N., Data-driven ence and Computational Intelligence (CSCI) IEEE,
maintenance and operations scheduling in power 1269–1274, 2019.
systems under decision-dependent uncertainty, IISE
Transactions, 52, 6, 589–602, 2020. [46] Porcelli I. et al., Technical and organizational is-
sues about the introduction of augmented reality in
[34] Akkermans H. et al., Smart moves for smart main- maintenance and technical assistance services, 11th
tenance. Findings from a Delphi study on ‘Main- IFAC Workshop on Intelligent Manufacturing Sys-
tenance Innovation Priorities’ for the Netherlands, tems, 257–262, 2013.
Dutch Institute of World Class Maintenance (DI-
WCM), 2016. [47] Palmarini R. et al., A systematic review of augment-
ed reality applications in maintenance, Robotics and
[35] Bokrantz J. et al., Maintenance in digitalised man- Computer-Integrated Manufacturing, 49, 215–228,
ufacturing: Delphi-based scenarios for 2030, Int. J. 2018.
Prod. Econ., 191, 154–169, 2017.
[48] Scurati G.W. et al., Converting maintenance ac-
[36] Razmi-Farooji A. et al., Advantages and potential tions into standard symbols for Augmented Reality
challenges of data management in e-maintenance, applications in Industry 4.0, Computers in Industry,
Journal of Quality in Maintenance Engineering, 25, 98, 68–79, 2018.
3, 378–396, 2019.
[49] Ceruti A. et al., Maintenance in aeronautics in an
[37] Runkler T.A., Data analytics: models and al- Industry 4.0 context: the role of augmented reality
gorithms for intelligent data analysis, 2nd ed., and additive manufacturing, Journal of Computa-
Springer Vieweg: Wiesbaden Germany, 2016. tional Design and Engineering, 6, 4, 516–526, 2019.

[38] Baum J. et al., Applications of big data analytics [50] Gallala A., Hichri B., Plapper P., Survey: the evo-
and related technologies in maintenance – literature- lution of the usage of augmented reality in Industry
based research, Machines, 6, 54, 2018. 4.0, IOP Conf. Series: Materials Science and Engi-
neering, 521, 012017, 2019.
[39] Ansari F., Glawar R., Sihn W., Prescriptive mainte-
nance of CPPS by integrating multimodal data with [51] Henderson S., Feiner S., Exploring the benefits of
dynamic Bayesian networks, [in:] Beyerer J., Maier augmented reality documentation for maintenance
A., Niggemann O. [Eds], Machine Learning for Cy- and repair, IEEE Transactions on Visualization and
ber Physical Systems. Technologien für die intelli- Computer Graphics, 17, 1355–1368, 2011.
gente Automation (Technologies for Intelligent Au- [52] Nakajima C., Itho N.A., Support system for mainte-
tomation), Springer Vieweg, Berlin, Heidelberg, 11, nance training by augmented reality, Proceedings of
1–8, 2020. the 12th International Conference on Image Anal-
[40] Karim R. et al., Maintenance analytics – the new ysis and Processing Italy 17–19 Sept, 2003, doi:
know in maintenance, IFAC-PapersOnLine, 49–28, 10.1109/ICIAP.2003.1234043.
214–219, 2016. [53] Webel S. et al., An augmented reality training plat-
form for assembly and maintenance skills, Robotics
[41] O’Donovan P. et al., An industrial big data pipeline
and Autonomous Systems, 61, 4, 398–403, 2013.
for data-driven analytics maintenance applications
in large-scale smart manufacturing facilities, Jour- [54] Fiorentino M. et al., Augmented reality on large
nal of Big Data, 2, 25, 2015. screen for interactive maintenance instructions,
Computers in Industry, 65, 2, 270–278, 2014.
[42] Cortadi A.J. et al., Predictive maintenance on the
machining process and machine tool, Applied Sci- [55] Masoni R. et al., Supporting remote maintenance
ences, 10, 224, 2020. in Industry 4.0 through augmented reality, Procedia
Manufacturing, 11, 1296–1302, 2017.
[43] Truong H.L., Integrated analytics for IIoT predic-
tive maintenance using IoT big data cloud systems, [56] Manuri F., Pizzigalli A., Sanna A.A., State vali-
2018 IEEE International Conference on Industrial dation system for augmented reality based mainte-
Internet (ICII), Seattle, WA, 109–118, 2018. nance procedures, Applied Science, 9, 2115, 2019.
[44] Bumblauskas D. et al., Smart Maintenance Deci- [57] Haritos T., Macchiarella N.D., A mobile applica-
sion Support Systems (SMDSS) based on corporate tion of augmented reality for aerospace maintenance
big data analytics, Expert Syst. Appl., 90, 303–317, training, 24th Digital Avionics Systems Conference,
2017. 30 Oct. – 3 Nov. 2005 Washington, USA, 2005.

[45] Chandra A.N.R., Jamiy F.E., Reza H., Augment- [58] Crescenzio F.D. et al., Augmented reality for aircraft
ed reality for big data visualization: a review, 2019 maintenance training and operations support, IEEE
International Conference on Computational Sci- Computer Graphics and Applications, 96–101, 2011.

Volume 11 • Number 2 • June 2020 85

Management and Production Engineering Review

[59] Yong S.W., Sung A.N., A mobile application of aug- [72] Geissbauer R., Wunderlin J., Lehr J., The future of
mented reality for aircraft maintenance of fan cowl spare parts is 3D. A look at the challenges and op-
door opening, Int. J. Comput. Netw. Inform. Secur., portunities of 3D printing, PwC, 2017.
6, 38–44, 2019.
[73] Grubic T., Servitization and remote monitoring
[60] Anastassova M., Burkhardt J.M., Automotive tech- technology: A literature review and research agenda,
nicians’ training as a community-of-practice: Impli- Journal of Manufacturing Technology Management,
cations for the design of an augmented reality teach- 25, 1, 100–124, 2014.
ing aid, Appl. Ergon., 40, 4, 713–721, 2009.
[74] Grubic T. et al., The adoption and use of diagnostic
[61] Quevedo W.X. et al., Virtual reality system for and prognostic technology within UK-based manu-
training in automotive mechanics, LNCS, 10324, facturers, Proceedings of the Institution of Mechan-
185–198, 2017. ical Engineers, Part B: Journal of Engineering Man-
ufacture, 225, 8, 1457–1470, 2011.
[62] Faieza A.A., Faid A., Lai L.W., Using marker based
augmented reality for training in automotive indus- [75] Sénéchal O., Performance indicators nomenclatures
try, International Journal of Recent Technology and for decision making in sustainable conditions based
Engineering, 7, 4S2, 118–121, 2018. maintenance, IFAC PapersOnLine, 51–11, 1137–
1142, 2018.
[63] Bottani E., Vignali G., Augmented reality technol-
ogy in the manufacturing industry: A review of the [76] Iung B., Levrat E., Advanced maintenance services
last decade, IISE Transactions, 51, 3, 284–310, 2019. for promoting sustainability, Procedia CIRP, 22, 15–
22, 2014.
[64] Macchi M. et al., Exploring the role of digital twin
for asset lifecycle management, IFAC PapersOn- [77] Jasiulewicz-Kaczmarek M., Żywica P., The concept
Line, 51–11, 790–795, 2018. of maintenance sustainability performance assess-
ment by integrating balanced scorecard with non-
[65] Aivaliotis P., Georgoulias K., Chryssolouris G., The additive fuzzy integral, Eksploatacja i Niezawodność
use of Digital Twin for predictive maintenance in – Maintenance and Reliability, 20, 4, 650–661, 2018.
manufacturing, International Journal of Computer
Integrated Manufacturing, 32, 11, 1067–1080, 2019. [78] Kasava N.K. et al., Sustainable Domain Value
Stream Mapping (SdVSM) framework application in
[66] Bevilacqua M. et al., Digital twin reference mod- aircraft maintenance: a case study, Procedia CIRP,
el development to prevent operators’ risk in process 26, 418–423, 2015.
plants, Sustainability, 12, 1088, 2020.
[79] Franciosi C. et al., Measuring maintenance impacts
[67] Enders M.R., Hoßbach N., Dimensions of digi- on sustainability of manufacturing industries: from
tal twin applications – a literature review, 25th a systematic literature review to a framework pro-
Americas Conference on Information Systems, Can- posal, J. Clean. Prod., 260, 121065, 2020.
cun 2019, https://pdfs.semanticscholar.org/bef1/
dbb393baa428cbf90aaea645a4de6fb2adfe.pdf? ga= [80] Hennequin S., Restrepo L.M.R., Fuzzy model of a
2.59863273.579588607.1583496369-1381774598.158 joint maintenance and production control under sus-
3496369. tainability constraint, IFAC-PapersOnLine, 49–12,
1216–1221, 2016.
[68] Liu Z., Meyendorf N., Mrad N., The role of data
fusion in predictive maintenance using digital twin, [81] Afrinaldi F. et al., Minimizing economic and envi-
AIP Conference Proceedings, 1949, 020023, 2018. ronmental impacts through an optimal preventive re-
placement schedule: Model and application, J. Clean.
[69] Wang J. et al., Digital twin for rotating machinery Prod., 143, 882–893, 2017.
fault diagnosis in smart manufacturing, Internation-
al Journal of Production Research, 57, 12, 3920– [82] Hoang A., Do P., Iung B., Energy efficiency
3934, 2019. performance-based prognostics for aided mainte-
nance decision-making: Application to a manufac-
[70] Cattaneo L., Macchi M., A Digital Twin Proof of turing platform, J. Clean. Prod., 142, 2838–2857,
Concept to Support Machine Prognostics with Low 2017.
Availability of Run-To-Failure Data, IFAC Paper-
sOnLine, 52–10, 37–42, 2019. [83] Ighravwe D.E., Oke S.A., Ranking maintenance
strategies for sustainable maintenance plan in man-
[71] Negri E. et al., A digital twin-based scheduling ufacturing systems using fuzzy axiomatic design
framework including equipment health index and ge- principle and fuzzy-TOPSIS, Journal of Manufac-
netic algorithms, IFAC PapersOnLine, 52–10, 43– turing Technology Management, 28, 7, 961–992,
48, 2019. 2017.

86 Volume 11 • Number 2 • June 2020

 Management and Production Engineering Review

[84] Boral S. et al., A hybrid AI based conceptual decision intelligent assets and smart products in the cyber-
making model for sustainable maintenance strategy physical circular economy, IFAC-PapersOnLine, 50,
selection, [in:] Chatterjee P. et al., Advanced Multi- 1, 11719–11724, 2017.
Criteria Decision Making for Addressing Complex
Sustainability Issues, IGI Global, 63,-90, 2019. [94] Rodseth H., Schjolberg P., Data-driven predic-
tive maintenance for green manufacturing, IWA-
[85] Singh R.K., Gupta A., Framework for sustainable MA 2016, Manchester, UK, 36–41, 10–11 November
maintenance system: ISM – fuzzy MICMAC and 2016.
TOPSIS approach, Annals of Operations Research,
2019. [95] Nielsen I., Dang Q.-V., Nielsen P., Pawlewski P.,
Scheduling of mobile robots with preemptive tasks,
[86] Jasiulewicz-Kaczmarek M., Identification of main- Advances in Intelligent Systems and Computing,
tenance factors influencing the development of sus- 290, 19–27, 2014.
tainable production processes – a pilot study, IOP
Conf. Series: Materials Science and Engineering, [96] Thibbotuwawa A., Nielsen P., Banaszak Z., Bo-
400, no 062014, 2018. cewicz, G., Energy consumption in unmanned aeri-
al vehicles: A review of energy consumption models
[87] Fraser K., Hvolby H.H., Tseng T.L., Maintenance and their relation to the UAV routing, Advances in
management models: a study of the published liter- Intelligent Systems and Computing, 853, 173–184,
ature to identify empirical evidence, Int. J. Qual. 2019.
Reliab. Manag., 32, 6, 635–664, 2015.
[97] Tao F., Zhang M., Nee A.Y.C., Digital twin driven
[88] Ajukumar V.N., Gandhi O.P., Evaluation of green smart manufacturing, Academic Press, 2019.
maintenance initiatives in design and development
[98] Yao X., Sun Z., Li L., Shao H., Joint maintenance
of mechanical systems using an integrated approach,
and energy management of sustainable manufactur-
J. Clean. Prod., 51, 34–46, 2013.
ing systems, [in:] ASME 2015 International Manu-
[89] Franciosi C., Lambiase A., Miranda S., Sustainable facturing Science and Engineering Conference, Pa-
maintenance: a periodic preventive maintenance per No: MSEC2015-9345, V002T04A008, 2015.
model with sustainable spare parts management,
[99] Gaiardelli P. et al., A classification model for
IFAC PapersOnLine, 50–1, 13692–13697, 2017.
product-service offerings, J. Clean. Prod., 66, 3,
[90] Takata S. et al., Maintenance: changing role in life 507–519, 2014.
cycle management, Annals of the CIRP, 53, 2, 643–
[100] Zhang Y. et al., A big data analytics architecture
656, 2004.
for cleaner manufacturing and maintenance process-
[91] Grabowska M., Takala J., Assessment of quali- es of complex products, J. Clean. Prod., 142, 2, 626–
ty management system maturity, Lecture Notes in 641, 2017.
Mechanical Engineering, Advances in Manufactur-
[101] Boone C.A., Skipper J.B., Hazen B.T., A frame-
ing, Springer International Publishing, pp. 889–898,
work for investigating the role of big data in service
2018.
parts management, J. Clean. Prod., 153, 687–691,
[92] Bilge P. et al., Mapping and integrating value cre- 2017.
ation factors with life-cycle stages for sustainable
[102] Bevilacqua M. et al., Big data analytics method-
manufacturing, Procedia CIRP, 61, 28–33, 2017.
ologies applied at energy management in industrial
[93] Romero D., Noran O., Towards green sensing vir- sector: A case study, International Journal of RF
tual enterprises: interconnected sensing enterprises, Technologies, 8, 3, 105–122, 2017.

Volume 11 • Number 2 • June 2020 87

View publication stats