Available online at www.sciencedirect.

com

SScciieenncceeDDiirreecctt
IFAC PapersOnLine 52-10 (2019) 91–96

Maintenance 4.0 Technologies for Sustainable Manufacturing – an Overview

Małgorzata Jasiulewicz - Kaczmarek*, Arkadiusz Gola**
* Poznan University of Technology, Faculty of Management Engineering, Strzelecka 11, 60-965 Poznań, Poland
Poland (Tel: +48 500-007-701; e-mail: [email protected])
**
Lublin University of Technology, Institute of Technological Systems of Information, 20-618 Lublin, ul. Nadbystrzycka
36, Poland (Tel: +48 81 538 45 35; e-mail: [email protected]).

Abstract: Manufacturing is experiencing relevant changes under the challenges imposed by the
sustainable economic development model. Under this model, the significant progress in advanced
technologies is providing new opportunities to enhance competitiveness. Meanwhile, the maintenance
function is transforming its role in order to better support value creation, both contributing to the
economic dimension as well as extending its care for the environmental and social aspects. Maintenance
4.1 can break the trade-offs of the older strategies by enabling companies to maximize the useful life of
their production equipment while avoiding unplanned downtime, minimizing planned downtime,
increasing process and people safety, minimizing energy and resources consumption and saving costs.
The paper presents the possibility of incorporation new technologies into the planning, implementation,
monitoring and analysis of maintenance processes that support sustainable production in modern
manufacturing companies.
© 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.
Keywords: sustainability, sustainable manufacturing, sustainable maintenance, maintenance, Industry 4.0.

that predicts failure makes diagnosis and triggers

1. INTRODUCTION
maintenance actions (Lee et al., 2014). Maintenance 4.0 is a
Many authors (e.g. Seliger et al., 2008; Dubey et al., new term defining the next generation in the approach to
2017) have considered the relevant role that technology maintenance of production equipment. Maintenance 4.0 is
development has towards sustainable manufacturing. about predicting future failures in assets and ultimately
Technology influences and interacts with the economic prescribing the most effective preventive measure by
dimension (e.g. it allows new business solutions), with the applying advanced analytic techniques on big data about
environment (e.g. providing solutions to nature and resource technical condition, usage, environment, maintenance history,
conservation) and with the society (e.g. it supports new living and similar equipment elsewhere and in fact anything that
models), besides acting as a powerful tool to give resources may correlate with the performance of an asset. The main
for ‘meeting the needs of the present generation without goal of this work is to present the possibility of using modern
compromising the ability of future generations to meet their IT technologies into the planning, implementation,
own needs. In other words, it is not possible to look for monitoring and analysis of maintenance processes realized in
solutions to the sustainability manufacturing issue without manufacturing in manufacturing companies (Daniewski et al.,
considering technology as an integral component of the 2018; Fang et al., 2019; Gola, 2019).
development. This paper is organized as follows. First maintenance
Recently, the emerging technologies (e.g., Internet of processes and their evaluation during last few decades are
Things (IoT), wireless sensor networks, big data, cloud described. Moreover the maintenance contribution to
computing, embedded system, and mobile Internet) are being business competitive and sustainable manufacturing
introduced into the manufacturing environment. In the operations are presented. Then regarding the economic aspect
literature on production, the changes are referred to as the of maintenance contribution, economic factors affected by
next (fourth) industrial revolution, which is commonly called the maintenance function are defined. Finally, new IT
“Industry 4.0”. Literary research indicates a wide range of technologies in machines and devices that can support
possibilities that new technologies related to Industry 4.0 can maintenance function are described.
bring for sustainable manufacturing. Referring to the
2. MAINTENANCE FOR SUSTAINABLE
economic perspective of sustainability, transparency and
MANUFACTURING
interconnection of processes allow their optimization,
increasing efficiency, flexibility, quality, and customization During the last five decades, maintenance has radically
(Peukert et al., 2015). Regarding the ecological dimension of changed according not only to the technology requirements
sustainability, prediction of energy consumption, reduction of but also because of the new market requirements.
waste and resource consumption are the key potential Maintenance has evolved from reactive function, becoming
benefits (Dubey et al., 2017; Jabbour et al., 2018). firstly a preventive approach, then a lean process and later
One of the applications areas of Industry 4.0 technology
is maintenance in the form of self-learning and smart system
2405-8963 © 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.
Peer review under responsibility of International Federation of Automatic Control.
10.1016/j.ifacol.2019.10.005
9 Małgorzata Jasiulewicz - Kaczmarek et al. / IFAC PapersOnLine 52-10 (2019) 91–96

a green process. Currently it is considered as a process that value for all stakeholders in the long-term horizon’.
needed to be managed in a sustainable perspective. Sustainable Maintenance should contribute to the
Based on literature review and observation of industrial minimization of environmental and social impacts of a
practices, it was stated that maintenance contribution to business system, the reduction of life cycle costs and enhancement of
competitive priorities and more sustainable manufacturing equipment durability and socioeconomic well-being
(SM) operations has got two main dimensions, which are: (Afrinaldi et al., 2017).
 the sustainability dimension,
 the life-cycle dimension.
The sustainability dimension is represented by the three
sustainability aspects: economic, environmental and social.
Maintenance contribution may be observed in all three
aspects (Fig. 1).

Figure 2. Information flow in technical object life cycle

Figure 1. The contribution of maintenance processes in SM The objectives of the Sustainable Maintenance in a
company are: (1) to be in line with the business and profit
Regarding the economic aspect of maintenance objectives (strategic decision rules and longer equipment life
contribution, there are four relevant economic factors cycle); (2) to keep the functional level of a machine and to
affected by the maintenance function: quality and preserve all its characteristics above the level required from the
productivity, delivery on time, innovation and cost viewpoint of the environmental impact; (3) to be in line with
(Jasiulewicz-Kaczmarek et al., 2018). With reference to the social expectations (satisfaction of employees, including their
environmental aspect the following factors may be health and safety).
distinguished: prevention of environmental damage, The essential question is ‘how to achieve specified goals
emissions reduction and land conservation, energy and what to do’. According Bilge et al., (2017) the enabling
consumption reduction and energy savings or efficiency technologies of the Maintenance 4.0, can contribute to
(Ajukumar & Gandhi, 2013; Franciosi et al., 2017). Finally, the provide information necessary for sustainable maintenance
social aspect concerns the relationship of maintenance function assessment, and they could become key-drivers in pursuit of
with its stakeholders within and outside the company, with a sustainable maintenance and asset life-cycle management.
particular focus on the maintenance personnel, who is affected 3. MAINTENANCE 4.0 TECHNOLOGIES
by decisions made in the maintenance department. Maintenance
contribution to social aspect is also linked to plant safety and It is not possible to look for solutions to the sustainable
human safety, as a main means to avoid undesired failures and maintenance issue without considering technology as an
minimize the consequences of the failures (Burduk & integral component of the development. From the point of
Jagodziński, 2015; Pintelon & Muchiri, 2009; Ratnayake & view of maintenance, the development of new technologies
Antosz, 2017). The second dimension of maintenance and end-user requirements have significantly affected both
contribution to more SM system is life-cycle thinking (Fig. the subject of maintenance operations (machines and
2). equipment) and the way of planning and implementing
Sustainable Maintenance or Sustainability Centered maintenance activities. With regard to the application of new
Maintenance (SCMn) has become a new challenge for technologies in machines and devices we use today, the most
enterprises realizing concept of SM. Sari et al., (2015) common term 'smart machine'. The term “smart machine”
defined sustainable maintenance as ‘…all required processes implies a machine that is better connected, more flexible,
for ensuring the acceptable assets condition by eliminating more efficient and safe. It can quickly respond to new
negative environmental impact, prudent in using resources, demands. Smart Machine has three main components:
concern for the safety of employees and stakeholders, while physical components, smart components and connectivity
at the same time economically sound’. Jasiulewicz- components. Smart components are directly connected with
Kaczmarek and Żywica (2018) defined SCMn as ‘a set of services related to the physical parts, while connectivity
proactive technical, economic and management activities allows exchanging information between the machine and its
implemented throughout the whole life-cycle of a technical environment, and enables services to exist outside the
facility aimed at realizing functions of a technical facility, physical machine itself. According Porter and Heppelmann
ensuring at the same time the achievement of goals and the (2014) intelligence and connectivity enable an entirely new
ability to create the economic, environmental and social set of machine functions and capabilities:
 monitoring: machines enable the monitoring of a self- separates it from more traditional, reactionary approaches to
condition, operation and external environment through equipment repair and replacement. Big data analytics is the
sensors and external data sources, and can alert users or process of collecting, organizing and analyzing large sets of
others stakeholders to changes in circumstances or data called big data to discover patterns and other useful
performance; information. Big data analytics can help maintenance
 control: machines can be controlled through remote organizations to better understand the information contained
commands or algorithms that are built into the device or within the data and will also help identify the data that is
reside in the machine cloud; most important to future decisions. Karim et al., (2016)
 optimization: smart, connected machines can apply proposed concept for Maintenance Analytics (MA) that is
algorithms and analytics to in use or historical data to based on four interconnected time-lined phases (Fig. 3): (1)
improve output, utilization, and efficiency; and “Maintenance Descriptive Analytics” focuses to discover and
 autonomy: monitoring, control and optimization describe what happened in the past; it summarizes collected
capabilities combine to allow smart, connected machines data from various maintenance sources and provides
to achieve a previously unattainable level of autonomy. summary statistics in terms of measures (e.g. number of
At the simplest level an autonomous machine does faults) and visualizations (e.g. failure rate chart); (2)
operation using sensors and software on real time. More- “Maintenance Diagnostic Analytics” focuses to understand
sophisticated machines are able to learn about their why something happened; it can basically be divided into
environment, self-diagnose their own service needs, and fault detection (i.e. indicating faults and malfunctions), fault
adapt to users’ preferences. Autonomy not only can isolation (i.e. determining the cause and the related
reduce the need for operators, but it can improve safety in component) and fault identification (i.e. designating the type
dangerous environments and facilitate operation in remote and the nature of the fault) (Kothamasu et al., 2006; Vogl et
locations. al., 2016); (3) “Maintenance Predictive Analytics” focuses to
This 'intelligent object of maintenance' enables the estimate what will happen in the future; it take current
incorporation of new technologies into the planning, machine conditions and past operation profiles into account
implementation, monitoring and analysis of maintenance and either predict the probability that a machine operates
processes, such as: (1) smart sensors and smart devices (Zong without a failure up to a time in the future (i.e. system health
et al., 2017; Singh et al., 2014; Roy et al., 2016); (2) e- state estimation) or calculate the remaining useful life (RUL)
CMMS (Iung et al., 2014; Lopes et al., 2016; Rødseth et al., as the time left before a failure occurs (Peng et al., 2010;
2017); (3) diagnosis tools (Crespo Márquez & Iung, 2008); Elattar et al., 2016); (4) “Maintenance Prescriptive
(4) Prognosis tools (Lee et al., 2006; Crespo Márquez and analytics” which addresses what need to be done next; it
Iung, 2008; Muller et al., 2008); (5) Cloud -based tools builds on the results of the previously described types,
(Dillon et al., 2010; Zhong, et al., 2017); (6) simulation tools integrates additional data (e.g. costs and re-source
(Alrabghi & Tiwari, 2015; Antosz & Ratnayake 2019); (7) information), and transforms them into actionable
AR tools (Suarez-Warden et al., 2015; Klimant et al., 2017; maintenance recommendations to identify the optimal actions
Kollatsch et al., 2017; del Amo et al., 2018). These and/or the optimal time of actions (Bousdekis et al., 2015).
technologies defining the next generation in the approach to
maintenance of production equipment referred to in the Act
Value & Complexity

literature as Maintenance 4.0. Maintenance 4.0 is about Analyze

Maintenance Prescriptive Analytics
predicting future failures in assets and ultimately prescribing Inform
Maintenance Predictive Analytics

the most effective preventive measure by applying advanced Maintenance

Maintenance Diagnostic Analytics
Descriptive Analytics
analytic techniques on big data about technical condition, What happened?
Why did it happend?
usage, environment, maintenance history, and similar equip- Objectives
What will happen?
What shall we do?
Objectives Objectives Objectives
ment elsewhere and in fact anything that may correlate with Fault Detection Fault Isolation Fault Identification Optimal Time
the performance of an asset. Measures Visualizations
of Maintenance Optimal Action of Maintenance
System Health State Remaining Useful Life
A modern maintenance operation involves numerous de-
cision-making activities, requiring a large amount of infor-
mation and intensive computation. With the growing popu- Figure 3. Maintenance Analytics time-lined phases
larity of condition monitoring, prognostics and cloud compu- The aim of this concept is to facilitate maintenance
ting, the volume of data available for maintenance decision actions through enhanced understanding of data and
making has increased significantly (Bokrantz et al., 2017; information. While descriptive and diagnostic MA are rather
Valis et al., 2018). The rise of big data and its usage can be focused on the past, predictive or prognostic MA is concerned
beneficial for operations and maintenance in order to be with a more forward-looking perspective to answer the
proactive with regard to ongoing equipment maintenance and question “What is likely to happen?”. The application of big
upkeep. The use of data can provide more opportunity to data analytics in maintenance represents the fourth level of
predict upcoming issues in a system or equipment and, maturity in predictive maintenance (Fig. 4).
therefore utilize maintenance in a predictive manner, rather Focusing on industrial scenarios, in the Maintenance 4.0
than relying on the costly extremes – such as random approaches, the smart sensors are considered as the real
Preventative Maintenance or crisis-related Reactive enablers for industrial digitalization, since these sensors
Maintenance. All of this Big Data is meaningless without become the unique data sources for all the services and big
analysis. Analysis is what powers predictive maintenance and data applications (Sikora et al., 2019; Zarnik et al., 2018).
 can be collected, segregated and performer in the real time
Big Data & Statistics Level 4 using cloud technology. Repair options can be taken
Maintenance 4.0 Level 3 automatically by the system, and actions can be
Real-time condition monitoring
recommended to the technician. All possible failure data will
Level 2 be used to direct the repair, including system operating
continuous real-time
Instrument
monitoring
inspection
continuous real-time
of assets, withmonitoring
alerts sent of assets,
based conditions
on predictive techniques, atanalysis
such as regression the time of failure, previous repair data from the
Level 1
Visual instection
with alerts given based on pre-established rules
or critical levels.
CMMS, wear patterns and operating data from the
periodic inspections; conclusions are based on a combination
periodic physical inspections; conclusions are based solely on inspector’s expertise
equipment. In effect, the technicians will be able to perform
of inspector’s expertise and
instrument read-outs their work more efficiently.
The next advanced technology which supports Maintenance
Realiability
4.1 practices is Augmented Reality (AR) and Virtual Reality
Content -periodic inspection (physical) -periodic inspection (physical) -continouos inspection (remote) -continouos inspection (remote) (VR). Original ideas were developed in 1960s and since then a
(the types of data -checlist
they use) -paper recording
-instruments
-digital recording
-sensor
-digital recording
-sensor and other data
-digital recording
steady progress has been made with the advancement of
-digital condition data computing power and image analysis. The main idea of VR is
Processes
(how that data is
-paper based condition data -digital condition data -digital condition data -multiple inspection points
-multiple inspection points -single inspection points -multiple inspection points -digital environmet data
to create a digital world in which the user can be immersed and
collected) -digital maintenance history interact. In AR, the user can see the real world as well as digital
IT -condition monitoring software
-condition monitoring software -big data platform
objects superimposed over it. Work instructions for maintenance
(which hardware and - MS Excel / MS Access
software tools are used)
- embedded instrument software
-condition database -wifi network and assembly operations can be given directly to workers
-statistical software
through AR technologies. These technologies show promise for
Figure 4. PdM maturity matrix (based on Mulders & Haarman, 2017) assisting workers through integration of information into the
working environment, reducing the cognitive load on workers
These sensors translate physical actions from machines into and enabling better performance of various operations within
digital signals that communicate variables such as maintenance. AR has the potential to become a major tool for
temperature, vibration, or conductivity. Simply gathering data the maintenance, by overlaying and integrating virtual
on machinery from sensors is not enough. Maintenance 4.0 information on physical objects. Schwald and de Laval (2003)
requires an Internet of Things infrastructure that wirelessly presented an early study on the effectiveness of AR
connects assets to maintenance data center and enables the technologies for maintenance training within industrial context.
collection and distribution of sensor data. The IoT is a new To justify incorporation of AR technology to support aerospace
revolution resulting from the convergence of maintenance maintenance, Suarez-Warden et al. (2015 ) have presented an
systems with advanced computing, sensors, and ubiquitous analysis of the benefits of AR for aerospace maintenance
communication systems. It is a transformative event where assembly task. The analysis incorporates the impact of
countless industrial devices, both old and new, are beginning downtime and the maintenance variable cost reduction. Ong and
to use Internet Protocol (IP) communication technologies. Zhu (2013) developed an AR-assisted real-time equipment
There are several ways the IoT can improve the way maintenance system. According authors by creating and
machinery and equipment are managed: (1) Greater adoption augmenting context-aware overlay of textual and graphical
of Predictive Maintenance. The main reason for applying IoT maintenance instructions on the maintenance scene, remote
to manage assets is predictive maintenance. Rather than maintenance between equipment experts and maintenance
performing routine calendar-based inspections and personnel can be achieved, thus improving maintenance
component replacement, predictive techniques monitor workflow and enhancing equipment. Del Amo et al., (2018)
equipment for pending failures and notify maintenance staff believe that Augmented Reality (AR) is one of the most
when a part replacement is required. Sensors embedded in interesting technologies in which enterprises should invest,
equipment check for abnormal conditions and trigger work especially to improve service. And for this new project
orders when safe operating limits are breeched; (2) Real- implementation in the context of the ability to absorb and use
Time data analysis. The IoT takes Machine-to-Machine new technology in Maintenance 4.0. the most-important
(technologies that allow machines to communicate with each competences are personal competencies (Patalas-Maliszewska
other) to the next level by including a third element: data. and Kłos, 2018)
The availability of all machine data in one virtual network
gives original equipment manufacturers the ability to 5. CONCLUSIONS
aggregate and analyze the data to generate better predictive
analytic models; (3) Accurate performance metrics. Maintenance 4.0 can break the trade-offs of the older
Availability, reliability and other key performance metrics strategies by enabling companies to maximize the useful life
such as mean time between failures (MTBF) and mean time of their production equipment while avoiding unplanned
to repair (MTTR) can be calculated automatically by the downtime, minimizing planned downtime, increasing process
system and fed to reporting dashboards. This removes the and people safety, minimizing energy and resources
human element in capturing all downtime, ensuring the data consumption and saving costs. From a sustainable production
is as accurate as possible; (4) Remote assets. The connected perspective, the Maintenance 4.0 contribution can be applied
assets generating their own work orders in the CMMS with a to the following areas:
proposed list of action items and recommended list of spares  Life cycle thinking. Technological advances, such as the
to complete the job will reduce the mean time to repair; (5) IoT, resulted in developments that influence life cycle
Recommended repair actions. The complete data on failure thinking. The IoT could underpin the Product System Service
design by using information feedback at any stage of the
Product-Service life cycle. The availability of all machine Ajukumar, V.N., Gandhi, O.P. (2013). Evaluation of green
data in one virtual network gives original equipment maintenance initiatives in design and development of
manufacturers the ability to aggregate and analyze the data to mechanical systems using an integrated approach.
generate better predictive analytic models. Moreover, IoT Journal of Cleaner Production 51, pp. 34-46
provides information for continuous improvement, closer Antosz, K., Ratnayake R.M.C. (2019) Spare parts’ criticality
relationship with stakeholders, resource efficiency and the assessment and prioritization for enhancing
ability to meet sustainability. manufacturing systems’ availability and reliability,
 Services and aftersales. A key element of the strategy of Journal of Manufacturing Systems, 50 (2), pp. 212-225
most companies involved in the production of machines is to Beier, G., Niehoff, S., Ziems, T., Xue, B., (2017), Sustainability
build solid, lasting relationships with its customers, providing Aspects of a Digitalized Industry – A Comparative Study
them with an independent, expert support and after sales from China and Germany, Int. Journal of Precision
service. One of the elements of such support is remote Engineering and Manufacturing-green Technology 4 (2), pp.
maintenance. According Rødseth et al., (2017) predictive 227-234
maintenance combined with remote maintenance will Bilge, P., Emec, S., Seliger, G., Jawahir, I. S. (2017). Mapping
typically reduce the maintenance cost from 10% to 40%. and Integrating Value Creation Factors with Life-cycle
 Resource/process. Maintenance prognostics techniques Stages for Sustainable Manufacturing. Procedia CIRP
could be used not only for calculating a RUL as 61, pp. 28-33.
conventionally defined but for evaluating the energy Bokrantz, J., Skoogh, A., Berlin, C., Stahre, J., (2016).
consumption, the energy efficiency, failures causing high Maintenance in digitalized manufacturing: Delphi-based
CO2-emissions or other environmental impact (Iung & scenarios for 2030. International Journal of Production
Levrat, 2014; Rødseth & Schjølberg, 2016). Conducting real- Economics 191, pp. 154–169
time preventive maintenance of measurement sensors helps Bousdekis, A., Magoutas, B., Apostolou, D., Mentzas, G.,
improve the economic performance of manufacturing (2015). Review, Analysis and Synthesis of Prognostic-
processes and provides process stability. Based Decision Support Methods for Condition Based
 Inventories. Connected technologies can help Maintenance. Journal of Intelligent Manufacturing, pp. 1-14
maintenance managers address the core challenge: the right Burduk, A., Jagodziński, M., (2015). Assessment of Production
part in the right place, at the right time. System Stability with the Use of the FMEA Analysis and
 Asset utilization. Predictive maintenance can drive Simulation Models. Springer, Cham, Lecture Notes in
value by decreasing the planned machine downtime, Computer Science, Vol 9375, pp. 216-223
unplanned machine downtime, or changeover times. The Crespo Márquez, A., Moreu de León P., Gómez Fernández J.,
predictive maintenance typically decreases the total machine Parra Márquez C. & López Campos M. (2009). The
downtime from 30% to 50% and extends the operation life maintenance management framework: A practical view
from 20% to 40% (Rødseth et al., 2017). to maintenance management, Journal of Quality in
 Labor. Maintenance is a critical activity that takes place Maintenance Engineering, 15(2), pp. 167-178
at the manufacturing shop-floor. A proper level of detailed Daniewski, K., Kosicka, E., Mazurkiewicz, D., (2018).
maintenance instructions should be provided to the Analysis of the correctness of determination of the
maintenance personnel, according to their level of expertise. effectiveness of maintenance service actions.
With the aid of AR, various virtual information (e.g. virtual Management and Production Engineering Review, 9 (2),
components, disassembly instructions, diagnostic information, pp. 20-25
etc.) that is needed to assist maintenance operators can be del Amo, I.F., Erkoyuncu, J.A., Roy, R., Wilding, S., (2018).
overlaid directly onto the real workspace. Maintenance Augmented Reality in Maintenance: An information- centred
workers can easily get the instructions in real time and design framework. Proc.Manuf.19, pp. 148–155 Dubey, R.,
remote experts can collaborate with them intuitively. AR- Gunasekaran, A., Childe, S.J., Papadopoulos, T.,
assisted disassembly guidance could significantly reduce the Luo, Z., Wamba, S.F., Roubaud, D., (2017), Can big
workload of maintenance workers (Ong & Zhu, 2013). data and predictive analytics improve social and
Nevertheless, despite the fact that many authors point to the environmental sustainability? Technological Forecasting &
wide range of applications of new maintenance technologies Social Change. Elattar, H.M., Elminir, H.K.,
for the implementation of economic, environmental and Riad, A.M. (2016). Prognostics: A
social challenges of sustainable production, it can only be Literature Review. Complex & Intelligent
said today, according to Franciosi et al., (2018) that ‘the role Systems 2(2), pp. 125-154.
of Maintenance 4.0 for sustainable manufacturing is still in Fang, Y., Tao, W., Tee, K.F. (2019)., A new computational
its infancy and it has big potentiality that need to be method for structural reliability with big data. Eksploatacja
investigated’. i Niezawodnosc – Maintenance and Reliability 21 (1), pp.
REFERENCES 159–163
Franciosi, C., Iung, B., Miranda, S., Riemma, S., (2018).
Afrinaldi, F., Tasman, A. M., Zhang, H. C., Hasan, A., (2017). Maintenance for Sustainability in the Industry 4.0 context:
Minimizing economic and environmental impacts through a Scoping Literature Review. IFAC PapersOnLine 51-11,
an optimal preventive replacement schedule: Model and pp. 903–908
application. Journal of Cleaner Production 143, 882-893 Franciosi, C., Lambiase, A., Miranda, S., (2017). Sustainable
Maintenance: a Periodic Preventive Maintenance
Model with Sustainable Spare Parts Management.
IFAC PapersOnLine 50-1, pp. 13692–13697
Gola, A., (2019). Reliability analysis of reconfigurable Manufacturing Companies. Advances in Intelligent Systems
manufacturing system structures using computer and Computing, Vol 637, pp. 131-138 Springer, Cham
simulation methods. Eksploatacja i Niezawodnosc – Peng, Y., Dong, M., Zuo, M.J., (2010), Current Status of
Maintenance and Reliability 21 (1), pp. 90–102 Machine Prognostics in Condition-Based Maintenance: A
Herrmann, C., Schmidt, C., Kurle, D., Blume, S., Thiede, S., Review. The International Journal of Advanced
(2014), Sustainability in manufacturing and factories of Manufacturing Technology 50 (1), pp. 297-313
the future. International Journal of Precision Engineering Peukert B., Benecke S., Clavell J., Neugebauer S., Nissen
and Manufacturing-green Technology 1, pp. 283–292 N.F., Uhlmann E., Lang K.D., Finkbeiner M., 2015
Iung, B., Levrat, E., (2014), Advanced Maintenance Services Addressing Sustainability and Flexibility in
for Promoting Sustainability. Procedia CIRP 22:15–22 Manufacturing via Smart Modular Machine Tool Frames
Jabbour, A.B.L.S., Jabbour, C.J.C., C. Foropon., Godinho Filho to Support Sustainable Value Creation. Procedia CIRP
M., (2018), When titans meet – Can industry 4.0 29, pp. 514–519
revolutionize the environmentally sustainable Porter, M., Heppelmann, J., (2014). How Smart, Connected
manufacturing wave? The role of critical success factors, Products Are Transforming Competition, Harvard
Technological Forecasting & Social Change 132, 18–25 Business Review, November.
Jasiulewicz-Kaczmarek, M., Żywica, P., (2018). The concept Rødseth H., Schjølberg P., Marhaug A., (2017). Deep digital
of maintenance sustainability performance assessment by maintenance, Adv. Manuf. 5, pp. 299–310
integrating balanced scorecard with non-additive fuzzy Ratnayake, R.M.C., Antosz, K. (2017) Development of a Risk
integral. Eksploatacja i Niezawodnosc – Maintenance and Matrix and Extending the Risk-based Maintenance Analysis
Reliability 20 (4), pp. 650–661 with Fuzzy Logic, Procedia Engineering 182, pp. 602 – 610
Karim, R., Westerberg, J., Galar, D., Kumar, U., (2016). Roy R., Stark R., Tracht K., Takata S., Mori M. (2016).
Maintenance Analytics – The New Know in Maintenance. Continuous maintenance and the future – foundations and
IFAC-PapersOnLine 49-28, pp. 214 – 219 technological challenges, CIRP Annals - Manufacturing
Klimant, P., Kollatsch, C., Schumann M. (2017), Augmented Technology 65, pp. 667–688
Reality Solutions in Mechanical Engineering, ASME Sari E., Shaharoun A.M., Maaram A., Yazid A.M. (2015).
2017 doi:10.1115/MSEC2017-2858 Sustainable maintenance performance measures: a pilot
Kollatsch C., et al. (2017). Industrial Augmented Reality: survey in Malaysian automotive companies. Procedia
Transferring a Numerical Control Connected CIRP 26, pp. 443-448
Augmented Realty System from Marketing to Schwald, B., de Laval, B., (2003), An Augmented Reality
Maintenance, 10.1109/ISMAR-Adjunct.2017.27 System for Training and Assistance to Maintenance in the
Kothamasu, R., Huang, S.H., Ver Duin, W.H., (2006), System Industrial Context. Journal of WSCG, Vol.11, No.1.
Health Monitoring and Prognostics - A Review of Current Seliger G., Kim H-J., Kernbaum, S. Zettl, M. (2008)
Paradigms and Practices. The International J. of Advanced Approaches to sustainable manufacturing, International
Manufacturing Technology 28(9-10), pp. 1012-1024 Journal. Sustainable Manufacturing 1 (1/2), pp.58–77
Lee, J, Kao, H-A, Yang, S., (2014), Service Innovation and Shrouf, F., Miragliotta, G,. (2015), Energy Management
Smart Analytics for Industry 4.0 and Big Data Based on Internet of Things: Practices and Framework
Environment. Procedia CIRP 16, pp. 3–8 for Adoption in Production Management. Journal of
Lee, J., Ni, J., Djurdjanivic, D., Qiu, H., Liao, H., (2006), Cleaner Production 100, pp. 235–246
Intelligent prognostic tools and e-maintenance, Computers Sikora, M., Szczyrba, K., Wróbel, Ł., Michalak, M. (2019).
in Industry, 57, pp 476-489 Monitoring and maintenance of a gantry based on a
Lopes, I., Senra, P., et al., (2016), Requirements specification of a wireless system for measurement and analysis of the
computerized maintenance management system – a case vibration level. Eksploatacja i Niezawodnosc –
study. Procedia CIRP 52, pp. 268 – 273 Maintenance and Reliability 21 (2), pp. 341–350
Mulders, M., Haarman, M. (2017). PdM 4 Predict the Suarez-Warden, F, Mendıvil, EG, Ramırez, AF, Garcıa-
unpredictable. Mainnovation Lumbreras, S., (2015), Profit Model for Incorporating AR
Müller J.M., Kiel D., Voigt K.I. (2018), What Drives the Technology in Assembly Tasks of Aeronautical
Implementation of Industry 4.0? The Role of Maintenance. Procedia Computer Science 75, pp.113–122
Opportunities and Challenges in the Context of Valis, D., Mazurkiewicz, D. (2018). Application of selected
Sustainability, Sustainability 10, 247. Levy processes for degradation modelling of long range
Niu, G. (2017). Data-Driven Technology for Engineering mine belt using real-time data. Archives of Civil and
Systems Health Management: Design Approach, Feature Mechanical Engineering 18, pp. 1430-1440
Construction, Fault Diagnosis, Prognosis, Fusion and Vogl, G.W., Weiss, B.A., Helu, M. (2016). A Review of
Decisions, Springer Singapore Diag- nostic and Prognostic Capabilities and Best
Ong S.K., Zhu J. (2013) A novel maintenance system for practices for Manufacturing. Journal of Intelligent
equipment serviceability improvement. CIRP Ann Manuf Manufacturing, 1-17
Technol 62(1), pp. 39–42. Zarnik, M.S., Novak, F., Papa, G., (2018). Sensors in
Patalas-Maliszewska J., Kłos S. (2018) An Intelligent System proactive maintenance – a case of LTCC pressure
for Core-Competence Identification for Industry 4.0 Based sensors. Eksploatacja i Niezawodnosc – Maintenance and
on Research Results from German and Polish Reliability 20 (2), pp. 267–272
Zhong, R.Y., Wang, L., Xu, X. (2017). An IoT-enabled Real-
time Machine Status Monitoring Approach for Cloud
Manufacturing, Procedia CIRP 63, pp. 709 –
714