Predictive Maintenance and Intelligent Sensors in PDF
Predictive Maintenance and Intelligent Sensors in PDF
Predictive Maintenance and Intelligent Sensors in PDF
Abstract: With the arrival of new technologies in modern smart factories, automated predictive
maintenance is also related to production robotisation. Intelligent sensors make it possible to obtain
an ever-increasing amount of data, which must be analysed efficiently and effectively to support
increasingly complex systems’ decision-making and management. The paper aims to review the
current literature concerning predictive maintenance and intelligent sensors in smart factories. We
focused on contemporary trends to provide an overview of future research challenges and classifi-
cation. The paper used burst analysis, systematic review methodology, co-occurrence analysis of
keywords, and cluster analysis. The results show the increasing number of papers related to key
researched concepts. The importance of predictive maintenance is growing over time in relation to
Industry 4.0 technologies. We proposed Smart and Intelligent Predictive Maintenance (SIPM) based
on the full-text analysis of relevant papers. The paper’s main contribution is the summary and over-
view of current trends in intelligent sensors used for predictive maintenance in smart factories.
Citation: Pech, M.; Vrchota, J.;
Bednář, J. Predictive Maintenance
Keywords: intelligent sensors; maintenance; smart factory; Industry 4.0
and Intelligent Sensors in Smart
Factory: Review. Sensors 2021, 21,
1470. https://doi.org/
10.3390/s21041470
1. Introduction
Academic Editor: Susana Vieira; Industry sets the direction for the world economy, accounting for more than 70% of
João Figueiredo; João Miguel da the world’s total material production [1], depending on the regional economy’s develop-
Costa Sousa ment. The continuous introduction of new technologies in developed countries has an
impact on its relatively low level of employment of the population at the level of 20% [2].
Received: 31 December 2020
Simultaneously, the share of products and semifinished products in international trade is
Accepted: 16 February 2021
continuously growing, despite the declining share of national Gross Domestic Product
Published: 20 February 2021
(GDP) in developed countries [3]. All these facts are caused by introducing new technol-
ogies, which in the current industrial era of Industry 4.0 are summarised by many authors
Publisher’s Note: MDPI stays neu-
under the name Smart Factory.
tral with regard to jurisdictional
claims in published maps and insti-
This review aims to give the reader a comprehensive view of maintenance and intel-
tutional affiliations. ligent sensors in Smart Factory. As can be seen from the following, current literature re-
views [4–10] have shown that the literature is focusing on specific topics only separately.
The literature specializes in different types of sensors but does not consider them in rela-
tion to those technologies, and industry 4.0. Professional texts lack a summary of literature
Copyright: © 2021 by the authors. and texts that would bring the usability and potential of sensors closer to common prac-
Licensee MDPI, Basel, Switzerland. tice, so that these findings can be clearly used for business management in the implemen-
This article is an open access article tation of maintenance system planning. This would be beneficial for operational manag-
distributed under the terms and con- ers and engineers for the design of new maintenance systems. This article provides a com-
ditions of the Creative Commons At- prehensive overview of current trends to help structure and guide future research. At the
tribution (CC BY) license (http://cre- same time, it answers key questions related to contemporary trends in maintenance pro-
ativecommons.org/licenses/by/4.0/). cesses in smart factories. We define which Industry 4.0 technologies and intelligent sen-
sors usually provide maintenance in smart factories. Moreover, it helps to find new trends
in smart and intelligent predictive maintenance.
The article is organised into six sections (Figure 1). After the Introduction (Section 1),
the Theoretical Background (Section 2) discusses the relevant literature about intelligent
sensors, smart factory, and predictive maintenance and defines key terms. In Materials
and Methods (Section 3), we explain the qualitative and quantitative methods used for the
review. Section 4 is focused on the main results of the article, followed by a discussion
(Section 5). The last part presents the conclusion (Section 6), contributions, limitations, and
future research.
2. Theoretical Background
A literature review discussing intelligent sensors for maintenance in smart factories
has not been carried out. The literature currently offers reviews dealing with these areas
separately. Song at al. [4] pays attention to smart sensors in monitoring the condition and
integrity of rock bolts concerning economic and personnel losses. In the field of engineer-
ing, Jin [5] describes multifunctional sensors suitable for industrial production, Feng [11]
describes sensors for intelligent gas sensing in the literature review, and Paidi [6] de-
scribes intelligent parking sensors replacing ultrasonic sensors in combination with ma-
chine learning. Sony and Talal [7,12] then characterise sensors for health monitoring. In
literature reviews, we relatively often find a combination of smart sensors and smart fac-
tories, a key part of the 4.0 industry concept [13]. Lee [9] describes smart sensors’ use to
evaluate and diagnose individual devices in a smart factory. Strozzi [10] expands the lit-
erature review emphasising the actual transition and implementation of large, intelligent
factories. Pereira and Álvarez [14,15] also focus on implementing the principles of a smart
Sensors 2021, 21, 1470 3 of 39
factory and emphasise that effective value creation depends on the method of implemen-
tation. The implementation process about managing technological and organisational
changes and desirable competencies is further addressed by Sousa [16], as well as Lee et
al. [17]. They pay attention to the gap between recent researches on the actual level of
deployment. In the field of maintenance of intelligent factories, we find several literature
reviews with the resonant notion of predictive maintenance. In their overview, Carvalho
[18] focuses on machine learning methods, which they consider a promising tool for pre-
dictive maintenance. Sakib [19] observes the shift from service activities to proactive, pre-
dictive maintenance and places [20] in the context of Industry 4.0. Olesen and Shaker [21]
deals with practical use in thermal power plants, and Fei [22] in the field of aircraft sys-
tems.
no less important function of PdM is the possibility of early detection of faults, thanks to
tools based on historical data—machine learning—as well as visual aspects of faults—
colour and wear. As a possible part of the Industry 4.0 concept, PdM aims to minimise
maintenance costs, implement zero-waste production, and reduce the number of major
failures [35]. Despite PdM’s benefits, Herrmann [36] highlights the potential risks of re-
mote access to maintenance processes and cites Distributed Denial-of-Service (DDoS) at-
tacks, for example. According to Zonta [20], we distinguish three approaches to PdM,
namely: Based on a physical model, where the main feature is mathematical modelling
requiring the timeliness of the state and statistical methods of evaluation. The second ap-
proach is the knowledge-based approach, which reduces the complexity of the physical
model, and the last approach is the data-driven approach, which we find most often in
the current development of PdM. This approach is based on artificial intelligence, i.e., ma-
chine learning and statistical modelling, and is a satisfactory approach in the conditions
of Industry 4.0 [37]. Farooq et al. distinguish experience-driven and data-driven mainte-
nance [38]. Experience-driven preventive maintenance is based on gathering knowledge
about production equipment, which is then used to plan future maintenance. On the con-
trary, data-driven preventive maintenance is based on analysing a large volume of data
(Figure 2).
Searches Terms/Thesaurus
(“factory” OR “factories” OR “production” OR “manufac-
1. Smart factory/production
ture*”) AND (“smart” OR “intelligent”)
2. Intelligent sensors (“sensor” OR “sensors”) AND (“smart” OR “intelligent”)
(“maintenance”) AND (“smart” OR “intelligent” OR “pre-
3. Predictive maintenance
dictive”)
Query TOPIC (1), TOPIC (2), TOPIC (3)
Table 3. Results of topics searched for burst detection analysis (1 December 2020).
Searches Terms/Thesaurus
(“factory” OR “factories” OR “production” OR “manufac-
1. Smart factory/production
ture*”)
2. Intelligent sensors (“sensor” OR “sensors”)
3. Predictive maintenance (“maintenance”)
4. Smart/intelligent (“smart” OR “intelligent”)
Query 1 AND 2 AND 3 AND 4
We present the total number of publications found in Table 5. The result of the search
was 890 publications, which we further filtered based on the selected criteria.
Table 5. The number of papers from Web of Science (WoS) and Scopus bibliographic databases.
1. Not duplicated,
2. Published from January 2010 to December 2020,
3. Written in English,
4. Type of publication: journal paper (not review, white paper, book, short survey, pro-
ceedings, conference paper, etc.) for higher quality of data,
5. Publications with completed information (authors, year, journal name, etc.).
Furthermore, an objective screening was performed based on the title and keywords.
To evaluate the eligibility, we analysed the title, keywords, and abstracts of publications.
For this purpose, we have defined criteria for exclusion. We evaluated the publications at
meetings of the research team. In case of discrepancies in the assessment of suitability in
the title, keywords, or abstract, we compared the opinions of team members and, if nec-
essary, performed a full-text analysis. To document the extraction process, we used the
flow diagram in Figure 4, which captures the entire review flow based on the Preferred
Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology [48]
and Quality of Reporting of Meta-Analyses (QUORUM) methodology [49] from search to
final selection. The PRISMA checklist is available in supplementary materials (Table S1).
Figure 4. Flow diagram based on PRISMA [48] and QUORUM [49] flowchart.
Sensors 2021, 21, 1470 9 of 39
4. Results
The results are divided into three parts according to the research question: an over-
view of the main topics, smart and intelligent predictive maintenance, and Industry 4.0
Technologies and Sensors for Smart Factory.
Figure 5. The development of the total number of Scopus and Web of Science publications. Note: square on the line (Web
of Science), circle on the bold line (Scopus).
The burst detection analysis presents key terms for topics of intelligent sensors, smart
factory, and predictive maintenance (see Figures S1-S3 in Supplementary Materials). For
a better overview, we compare the results in three time periods (Figure 6), and then ac-
cording to the individual importance of key concepts (Figure 7). The importance of the
terms was expressed using the obtained burst weights. Based on these findings and anal-
ysis, we tried to answer research question 1 responsibly.
Sensors 2021, 21, 1470 11 of 39
Figure 6. The summary of burst detection analysis for main topics. The results are divided into three periods of time (1970–
1990, 1990–2010, and 2010–2020). The terms in each period are sorted according to the burst weights.
Top cited papers from smart factory/production areas focus on using ion batteries for
smart grids [59,60] and nanomaterials’ intelligent design [61]. The results show that the
most used terms in the paper titles are intelligent, Industry 4.0, and agent. Based on Figure
5, we conclude that the oldest wave in smart factories is associated with classical studies
dealing with intelligent, flexible, and automation planning and scheduling of manufac-
turing systems. This wave is the period 1970–1990, characterised by the burst terms intel-
ligent, system, knowledge, plan, and schedule. The second wave in 1990–2010 with the
primary burst terms: agent, manufacturing, control, expert, and process, refers to papers
using holon, RFID, or web technologies in factories. Publications on manufacturing con-
trol systems [62,63] were highly cited in this period. The current trend in smart factory is
related to implementing intelligent manufacturing [64]. In this contemporary wave, burst
terms Industry 4.0, digital twin, IoT, deep learning, digitalisation, smart grid, cyber, and
sustain dominate. These terms are well-known Industry 4.0 technologies and processes.
Top cited papers focused on operational planning of a smart grid [65], deep learning in agri-
culture [66], and big data for the self-organised multiagent system in the smart factory [67].
Top cited papers from smart/intelligent sensors were in areas related to the Internet
of Things [68], wireless sensor networks [69], and nanotechnology applications [70]. We
found that the important paper title terms are IoT, structure, and sensor in the burst anal-
ysis. Figure 5 shows that the early history of intelligent sensors, 1970–1990, emphasised
the first application of sensors (burst terms sensor, intelligent, process). Later, in 1990–
Sensors 2021, 21, 1470 12 of 39
2010 came articles focused on the structure [71], optic, and control of sensors, and their
usage for robots. Some essential publications in this period focused on structural health
monitoring [72], piezoelectric laminate beam [73], and free vibration behaviour of the
beam [74]. The most contemporary period from 2010 to 2020, similar to the smart fac-
tory/production, covered the area of Industry 4.0 new technologies. In addition to the
mentioned Internet of Things [75], there is a significant representation of publications fo-
cused on wearable sensor-based systems [76], deep learning [77], edge technology [78],
graphene-based smart materials, blockchain, smart city, and grid.
The last area focused on smart/predictive maintenance. After omitting medical and
ecological articles, the most cited publications focused on proportional-integral-derivative
(PID) control [79], monitoring, and fault diagnosis in production [80]. Based on the burst
analysis results, we found that the most important terms are maintenance, learning, and
predict. We identified three trend waves in area maintenance (Figure 5). In the first wave
from 1970 to 1990, the publications dealt with predictive maintenance. In engineering and
production, maintenance is associated with predicting machines’ status [81] or deteriora-
tion of processes [82]. In the second wave in 1990 to 2010, we found that the publications
dealt with burst terms program, diagnostics, intelligence, knowledge, and database. These
publications focus, for example, on diagnostics, monitoring, or maintenance of intelligent
computer numerical control (CNC) machine tools [83] or power transformers [84]. The
current trend wave is characterised by Industry 4.0 technologies such as digital twins,
deep machine learning, IoT, big data analytics, blockchain, and digitisation for mainte-
nance. The most significant publications of this period focused on big data analytics in
logistics and supply chain management [85], maintenance strategy selection [86], vibra-
tion analysis of rotating machinery, or cloud-enabled prognosis [87] for predictive mainte-
nance in production.
Based on the burst analysis detection, we conclude that in all three areas in the last
10 years, the focus has been on the concept of Industry 4.0 and related technologies. We
arranged the keywords with the highest burst weights into three research areas in Figure
7. The results show that the terms Internet of Things and deep learning have the highest
weight for all topics. The terms Big Data, grid, and intelligent are also common to the area.
From this finding, we can conclude that the current trend in the monitored areas is related
to the collecting of big data through intelligent sensors on IoT devices and their evaluation
using learning algorithms.
Figure 7. The top terms in analysed areas based on the burst detection. Note: The top ten used
terms are highlighted “bold” and top twenty terms are depicted “italic”.
Sensors 2021, 21, 1470 13 of 39
The internet, smart grid, and blockchain technology are important for sensors used
in maintenance. The use of sensors in smart factories lies mainly in the area of control,
with a focus on processes. The sensors, together with actuators, are used to collect data to
control and optimise conditions. Piezoelectric, optics, wearable, beam, graphene, and
other sensors’ features are used. A special area of sensors lies in robotics, which has expe-
rienced rapid development in recent years. In the world’s most industrialised countries,
such as South Korea, Japan, Germany, and Sweden, there is the largest share of robots per
10,000 employees in factories [88]. Automation in smart factories requires new types of
sensors that have the ability to automatically calibrate and improve the functions of IoT
devices. The IoT is not aiming only at connect two machines with pre-programmed func-
tions. For IoT communication, it is important to connect embedded devices to the Internet
and communicate with each other [89]. It is an intelligent connection of various products,
devices, and facilities that provide a wide range of functions that evaluate certain condi-
tions. The interaction between systems brings new possibilities. The key elements are min-
iature intelligent sensors [90]. Even though devices and systems were not originally de-
signed to share data, the Internet of Things can. Connecting smart sensors and gateways
to existing devices leads to data collection and analysis, understanding, and better deci-
sion making [91].
Publications about smart factory/production are related to cyber-physical systems,
planning, scheduling, and sustaining them. Maintenance in smart factories relies on In-
dustry 4.0 technologies, digitisation, data-driven manufacturing, agent-based systems,
and digital twins. Predictive maintenance consists of programs for predicting, diagnosing,
and analysing future maintenance needs. Based on the rules, features, and conditions,
there are machines and devices controlled and repaired to maintain their life and future
sustainability. Information and data are collected and shared through databases.
• I4: Industry 4.0 for predictive maintenance in general (keywords: Industry 4.0, Big
Data, prognostics, optimisation, performance, predictive maintenance, system).
• CbM: Smart manufacturing for condition-based maintenance (keywords: smart man-
ufacturing, manufacture, condition-based maintenance).
• SFD: Condition, state, and fault diagnosis for maintenance (keywords: maintenance,
condition monitoring, fault diagnosis).
• RUL: Prognostics and health management for RUL (keywords: prognostics and
health management, signal processing, remaining useful lives).
The first cluster consists of publications that focus on intelligent sensors in smart
maintenance factories without preferring specific methods. This cluster is represented, for
example, by publications focused on data-driven simulation [92], big data in an Industry
4.0 environment [93], or performing predictive maintenance in a bottling plant [94]. The
second cluster consists mainly of publications that emphasise the use of condition-based
maintenance. The intelligent condition-based maintenance uses data fusion [95] and the In-
ternet of Things in connection to learning techniques [96]. The third cluster related to pub-
lications mainly emphasised fault diagnosis’ importance for monitoring and maintenance.
The fault diagnosis is used for prognosis in signal processing [97] and maintenance man-
agement systems [98]. The last cluster is characterised by a focus on determining the cur-
rent health and the remaining life of devices and machines. This concept is described con-
cerning edge-cloud platforms [99].
While the concept of condition monitoring has been around for some time, the mar-
ket for more sophisticated predictive maintenance products is still very young. There are
four types of maintenance classified in the literature: corrective, scheduled, condition-
based, and statistical-based maintenance [100,101]. Predictive maintenance has evolved
from corrective maintenance using new technologies and procedures for predicting and
preventing failure. Corrective maintenance is based on the reactive strategy to the mainte-
nance process—however, with a proactive strategy related to the preventive or opportun-
istic approach. Preventive maintenance is then seen as condition-based, dynamic predic-
tive, or scheduled (periodic) maintenance. The corrective maintenance is based on the re-
pair or replacement of assets ex-post. Condition-based maintenance means the decision-
making process, usually in real-time, based on selected indicators computed from the
gathered data.
Table 6 depicts maintenance process characteristics from analysed papers. The con-
dition-based preventive maintenance is discussed in Farooq et al. [38], Kumar et al. [102],
Li et al. [96], Lin et al. [103], Musselman and Djurdjanovic [104], Yan et al. [93], and Sadiki
et al. [105]. Preventive maintenance is regular maintenance of machines, devices, and
equipment to prevent their downtime concerning failure state. The preventive mainte-
nance actions were classified by Doostparast et al. [106] as inspection, low-level repair,
and replacement. These actions are based on fault prediction time statistically, upon fail-
ure accident, time-based (at the age for old machines), or cycle-based (periodically).
Sensors 2021, 21, 1470 15 of 39
This work proposes an ensemble learning algorithm using DAMSID that supports the
Lin et al. [103] use of classifiers to cope with three-stage CBM with concept drifts and imbalance CbM
data.
Experiments were run to establish the tension estimation variance when a human
Musselman and completely executed the manual technique (standard approach) and the tension esti-
CbM
Djurdjanovic [104] mation variance when the newly designed contact-based device was used for belt ex-
citation and signal collection.
In this study, the lifespan of the servo motor was estimated through accelerated deg-
radation testing methods based on a new system degradation assessment method,
Park et al. [112] which estimates the fault of the system using observer-based residuals with encoder SFD
data obtained from internal instrumentation, and the importance of the maintenance
for machineries within manufacturing sites.
As a result, in the pursuit of the so-called smart factory and the enhancement of the
production process, as well as attenuation of numerous human maintenance efforts, a
Peng et al. [113] SFD
graphical histogram algorithm (GHA) health condition diagnosis and monitoring
strategy is proposed.
With these applications, unscheduled shut down for inspection can be avoided, and
Peng and Tsan [98] preventive maintenance can be deployed when the online sensor is identified as SFD
faulty.
We evaluated our developed wireless sensor network application in the context of
maintenance monitoring on realistic networks using the Instant Contiki operational
Sadiki et al. [105] system environment. We used Cooja simulator to investigate the robustness of our CbM
system in a scenario where nodes (sensors) will collect data on a real-time basis and
transmit to the central node.
Preventive maintenance of intelligent manufacturing equipment is carried out to re-
Shan et al. [114] duce the failure rate of intelligent manufacturing equipment and promote the devel- I4
opment of the new generation of intelligent manufacturing systems.
System checks if it is capable of doing self-maintenance, otherwise it will request
Tarashioon et al.
maintenance from operators (human maintenance instead of system self-mainte- RUL
[115]
nance).
This study incorporates Industry 4.0, which considers predictive maintenance, into
the imperfect production systems into economic production quantity (EPQ) models.
Tsao et al. [116] SFD
The predictive maintenances could be implemented by using sensors and data analy-
sis, which maintain production systems before they become ‘out of control’.
This presented solution can be used to monitor production systems and their wear-
susceptible and critical components such as ball screw and bearings. This solution is
Uhlmann et al. [117] to realise, due to decentral data processing on the sensor nodes, the concentration of I4
data and services in the cloud. Mobile provision of data and merging varied distrib-
uted sensors into a sensor network.
Alarms can allow the operators in the plant to conduct proactive management of the
Villalobos et al. [118] CbM
different controls in the machine for predictive maintenance of the equipment.
Model for optimising predictive maintenance of equipment using wireless sensor net-
works based on minimising the costs of maintenance, diagnostics, and deployment of
the equipment.
Vlasov et al. [119] SFD
Monitoring system is proposed. The presented concept of a system of predictive
maintenance based on sensor networks allows real-time analysis of the state of equip-
ment.
The findings of this paper indicated that multisource heterogeneous data can provide
Yan et al. [120] new solutions for predictive maintenance, scheduling, and machining process optimi- RUL
sation for energy saving.
Sensors 2021, 21, 1470 17 of 39
cused on Cloud-related technologies. It means that sensors based on RFID [92] and pro-
grammable logic controller [107] are used for cloud or edge computing [99] and analysis
of big data [109]. The third cluster concerned the IoT technologies based on CPS systems
[38], SCADA [94], and data for deep and machine learning.
A: Intelligent Sensors
Kumar et al. [102], Lao et al. [111], Park et al. [112], Peng et al. [113], Peng and Tsan
Sensor/Actuator
[98], Tarashioon et al. [115], Tsao et al. [116]
Automation Musselman and Djurdjanovic [104]
B: Cloud-related Technologies
Cloud Kiangala and Wang [94], Uhlmann et al. [117], Vlasov et al. [119]
Cloud/edge computing Barbieri et al. [99], Yan et al. [120], Zhang et al. [122]
Barbieri et al. [99], Kozlowski et al. [110], Chien and Chen [109], Villalobos et al.
Big Data
[118], Yan et al. [120], Zhang et al. [122]
RFID Goodall et al. [92], Sadiki et al. [105], Vlasov et al. [119], Zhang et al. [122]
PLC Al-Jlibawi et al. [107], Barbieri et al. [99], Kiangala and Wang [94]
C: Internet of Things Technologies
Farooq et al. [38], Li et al. [96], Lin et al. [103], Sadiki et al. [105], Shan et al. [114],
Internet of Things
Uhlmann et al. [117], Vlasov et al. [119]
CPS system Farooq et al. [38]
SCADA Farooq et al. [38], Al-Jlibawi et al. [107], Kiangala and Wang [94]
Machine learning Zhang et al. [121]
Artificial Intelligence Bekar et al. [108]
The different sensors’ data are used for prediction and diagnostics of devices, ma-
chines, facilities, and equipment. The results in Table 8 show that data are usually col-
lected from SCADA systems, PLCs, CNC machine sensors, IoT devices, or other special
sensors. Analysed papers mostly used case study and experimental research methods.
tion of the welding robot operation status. The electrocardiogram of intelligent manufac-
turing equipment technology provides the maintenance of intelligent manufacturing
equipment.
Very popular are piezoelectric and magnetostrictive technologies. Another way of sensing
is based on induction, pneumatic, and hydraulic forces.
Oil particle sensors enable the possibility of monitoring contamination levels in lu-
brication systems (for example, gear boxes). These sensors target to change the level of
pollution based on the presence of the number of substances processed. They analysed
the light intensity via a laser beam and photo detector.
Humidity (moisture) sensors focused diagnostics on water content in oils to prevent
corrosion of machines. These sensors are usually installed in a lubrication or hydraulic
tank. Humidity sensors play an essential role in the selected automated manufacturing
processes. To achieve the desired atmosphere, it is necessary to detect, monitor, and reg-
ulate humidity in conditions of low and high temperatures. The use of sensors for mois-
ture detection can be found, for example, in monitoring systems and networks, as a mon-
itoring device in agriculture, and as a tool for determining soil moisture during irrigation.
Furthermore, also in the field of corrosion diagnostics in the areas of infrastructure and
construction. The key element in this type of sensor is the materials used and the associ-
ated availability of suitable production technologies [134].
5. Discussion
The discussion is divided into two parts. First, we discuss the sensor-based smart
factory to imagine the factories of the future. Then, in the second part, we focus on insights
and future research issues related to intelligent sensors.
The transformation of a traditional factory into a smart one brings with it a higher
integration of physical production with digital technologies. Sensors and actuators bring
factory communication capabilities and data collection and analysis capabilities [144]. The
intelligent factory brings a change from traditional automation to a fully connected and
flexible system that can use a continuous flow of data from connecting operations and
production systems to learn and adapt to new requirements. The production system in
Sensors 2021, 21, 1470 25 of 39
smart factory is different—with more resources for small-lot products, dynamic routing
of production line, comprehensive connections with high-speed network infrastructure,
deep convergence of physical and digital world (digital twins), self-organisation control
system, and big data analytics [64]. A flexible conveying system of the production lines is
designed for the main production loops (cycles), with storage loops on the production line
and branch loops for customizing products. The smart factory can integrate data from
corporate assets to manage production, maintenance, inventory tracking, digitize opera-
tions through the digital twin, and other technologies. In the enterprise infrastructure,
smart logistics, smart grids, smart buildings, and smart distribution are interconnected.
Project management is important for the successful implementation and sustainability of
these systems in smart factories [145].
Due to the frequent occurrence of extraordinary situations caused mainly by external
elements, there is a need to deploy more demanding control systems. Management in
smart factories is decentralised. Decentralisations can offer the ability to make decisions
at process locations, independent of any central entity [146]. The complexity of these en-
vironments with many simultaneous processes, most of which follow each other, as well
as the enormous amount of data that sensors generate in production, can no longer be
served by existing control systems based on the simple technology of recording or pro-
cessing transactions. Therefore, multi-agent systems come to the light, where intelligent
information agents form a network of decentralised and distributed intelligence [147,148].
Beside the existing solutions, these systems are not based on centralised control but are
capable of collective self-configuration. These systems interconnect individual autono-
mous agents (or their digital twins) to communicate, coordinate, and cooperate to achieve
a set common goal. Individual communication elements collect data as needed, which
they later use to improve and optimize production.
In smart factories, thanks to intelligent sensors, each product actively participates in
the production process. The components to be processed contain digital information on
how to process them. They, therefore, communicate directly with robots and production
machines. With the help of a chip with radio frequency identification or other sensor tech-
nology, it can control its production flow. A smart product has access to knowledge re-
lated to its structure, composition, or purpose [149]. On the other hand, thanks to this
connection, the customer uses the user interface and intervenes in production in real-time.
The sensors allow the customer to obtain information for creating the product specifica-
tion, and its adjustment according to needs and requirements [150]. Autonomous vehicles
powered by electricity are also connected to the system, ensuring the transport of stock
and final products around the factory. Vehicle control is provided by a sophisticated sys-
tem of sensors. Parts, materials, and components needed for production are transported
to the factory when they are really needed for production (Just-in-Time system). Sensors
and possibly drones constantly check stock in a smart factory [151].
We performed profound words’ analysis of full-text papers to find phrases contain-
ing the terms “smart” or “intelligent”. Figure 11 shows that the obtained keywords form
various clusters and subclusters related to the predictive maintenance process. We iden-
tified four main components of the Smart and Intelligent Predictive Maintenance (SIPM)
system for smart factories based on cluster analysis. These are the production system, the
monitoring system, the factory planning system, and the maintenance system. The pro-
duction system of SIPM is based on energy saving control, transportation, and economics
costs, with use of controllers for predictive maintenance based on data analysis, and
equipment diagnostics. The monitoring system uses condition-based diagnostics, sensors
network linking management, and production—the factory planning system concerning
different components of objects and agents by using algorithms and meters. The mainte-
nance system is related to using analysis and diagnostics sensor data for predictive
maintenance.
Sensors 2021, 21, 1470 26 of 39
From the point of view of preventive maintenance, the machines and robots perform-
ing production communicate with each other continuously and inform each other about
non-standard situations. The machines report themselves to the maintenance staff (in this
sense it is a robot), besides, they precisely define the problem. The sensors in production
are thus connected to other factory systems based on SCADA. All elements can minimize
energy losses or use alternative energy sources for their activities [152]. Zero error rate is
ensured in production using smart sensors. Smart sensors and testers monitor the quality
of the final products.
We discussed the results and interpreted them in the perspective of previous studies
and research. Predictive maintenances in Cavalieri-Salafia’s model [153] includes data ac-
quisition from sensors, data manipulation (filtering, transforming, removing noise), ag-
gregation, prediction, decision-making, scheduling, and further monitoring of status and
configuration. Similarly, it describes the process of data acquisition, data processing, and
machine decision-making [154]. Possible application of artificial intelligence (AI) for pre-
ventive maintenance is discussed by Carlson and Sakao [155]. Modern systems are based
on the Internet of Things that enable real-time prediction and data sharing [96]. Uhlmann
et al. [117] described the solution of sensor network enhanced by cloud. The edge technol-
ogies [156] allow integration between PLC and cloud for modern sensors. Miniaturisation
of current sensors and nanotechnology [157] provides higher flexibility of maintenance
systems. Fernandes et al. [158] emphasise the role of data visualisation, data mining, and
data storage. These models have a standard data flow process which is a part of the pos-
sible prediction preparation. It is necessary to set a reliability model to analyse the dataset
[159]. Ruhi and Karim [160] show that a suitable statistical model can be applied to esti-
mate the optimum maintenance period at a minimum cost. Stodola and Stodola [161]
Sensors 2021, 21, 1470 27 of 39
pointed out that a useful model needs to consider human factors and related issues such
as labour intensity, administrative, and human errors.
quency, and security are lower than for flow, torque, or proximity sensors. The main ben-
efits of vibration sensors are predictability of impending failures, machine safety, cost,
extended maintenance intervals, machine reliability, and confidence in scheduled mainte-
nance. In the future, these advantages resulting from the use of vibration sensors can be
obtained by using new types of sensors, for example, virtual sensors or nanosensors, etc.
For this reason, current research is focused on minimizing the costs and flexibility of vi-
bration and temperature sensor solutions.
Many of the wireless sensor networks still have centralised control (so-called “net-
work manager”). Centralised server-client systems had one central database, which leads
to data consistency, easy administration, and a high level of security. However, centrali-
sation can result in the failure of a single point. High traffic can overload the bottleneck.
A centralised “network management” system can be slow and take a vest to lose data
packets. It is essential to use decentralised solutions within complex digital ecosystems,
such as production factories. The responsibility and need to make operational decisions is
performed at lower levels. A distributed architecture based on decentralisation is suitable
for their coordination and management [171]. Coordination between the individual nodes
involved in cyber-physical systems requires communication between the elements. The
benefit of the distributed architecture of components connected to the network and de-
centralised smart industry systems is the expandability (scalability) of the network, as well
as the increased resistance to failures of the network itself, individual connected systems,
as well as their components. For example, Kiangala and Wang [94] proposed a decentral-
ised monitoring system with a cloud-based dashboard displaying real-time reports for
every maintenance schedule generated. Zhang et al. [122] consider as a future trend ser-
vices in cyberspace that control, plan, and schedule production line items in a timely way.
Smart Industry systems already use intelligent algorithms to monitor, control, manage,
and plan complex processes and operations throughout the production process and sup-
ply chain. Advanced cognitive technologies will be gradually implemented in production
systems to increase the autonomy of individual components of the network. These sys-
tems use the principles of collective intelligence in industrial processes, especially solu-
tions based on multiagent systems. The future of these systems lies in achieving a high
level of artificial intelligence that will use the collective knowledge of all parts of the net-
work.
wireless nodes fully responsible for communication. Controllers have the automation con-
trol function based on the received commands from other devices in the network.
6. Conclusions
The fourth industrial revolution is permeating the industry, enabling an increasing
number of enterprises to have an incomparably greater overview of their production and
maintenance activities than ever before. The deployment of highly reliable and low-
maintenance devices contributes to the precise planning of production capacity and
equipment’s associated maintenance.
The first research question relates to the contemporary trends in the maintenance
processes of smart factories. The number of papers discussing the key terms sensors, smart
factories, and preventive maintenance increased over time, mostly in the last years. We
found that the contemporary burst trend is related to Industry 4.0 technology. Predictive
maintenance, smart factories, and intelligent sensors publications, together concerned
topics mainly related to deep machine learning, Internet of Things, and big data analytics.
The maintenance process in smart factories is based on digitisation, data-driven manufac-
turing, agent-based systems, and digital twins. Intelligent sensors in such factories use
edge, fog, and deep learning methods for control of manufacturing processes. In the fu-
ture, Internet and blockchain will be important for predictive maintenance.
Smart and intelligent predictive maintenance is characterised to answer a second re-
search question. Here, the results show four different types of maintenance used in smart
factories—Industry 4.0 for predictive maintenance, smart manufacturing for condition-
based maintenance, fault diagnosis for maintenance and prognostics, and remaining use-
ful life analysis. The importance of predictive maintenance is also growing due to the
growing number of robots, digitisation, and artificial intelligence introduced into produc-
tion lines to automate routine activities.
Following the third question’s answer, we can state that the three types of sensors
are mainly used for predictive maintenance in smart factories. Firstly, intelligent sensors
which have the potential to connect to higher-level systems. Furthermore, there is a pos-
sibility to connect these intelligent sensors to the internet—to build up the IoT devices.
Finally, we can use the gathered data in cloud-related technologies. The most prevalent
methods used for collecting and monitoring machines and devices are vibration analysis
[120], SCADA systems, CNC machine sensors, and PLCs. Based on the deep analysis, we
conclude that the current trend, insights, and future research issues are characterised by:
• Usage of multisource wireless networks of sensors in predictive maintenance.
• Dominance of vibration and temperature sensors for predictive maintenance.
• Challenges of the big data analytics and deep learning techniques.
• Challenges of interoperability of multiple sensors and maintenance systems.
• Decentralisation of maintenance control systems.
• High potential of virtual sensors and nanosensors for the future.
• Challenge of availability and reconfigurability of sensors.
• Security and safety of sensor data.
Based on the results synthesis, we proposed the Smart and Intelligent Predictive
Maintenance (SIPM) system for smart factory concerning four major subsystems: produc-
tion, monitoring, planning, and maintenance. These subsystems communicate and collab-
orate through modern IoT and cloud-based technologies. Their main advantage is real-
time management and planning to reduce the economic costs caused by production
downtime.
From a managerial point of view, the predictive maintenance system in smart facto-
ries is an early warning, especially in high-risk industries. The ability to detect weak sig-
nals of potentially significant strategic impact is a welcome positive in a turbulent busi-
ness environment. The system of predictive maintenance does not reduce the responsibil-
ity or the possibility of personal development of employees, but it must be stimulated by
responsible managers. It offers the possibility to reduce the number of hierarchical levels
between managers and ordinary employees, so that you can bring about higher employee
Sensors 2021, 21, 1470 32 of 39
autonomy and help other innovation processes to be implemented effectively. The chal-
lenge for managers today is to select criteria based on which they will be able to select
intelligent sensors for smart factories. There is a wide range of sensors on the market and
the authors most often state the criteria of sensor sensitivity, sensor cost, flexibility, and
size (miniaturity).
Further research may comprise the advanced machine learning methods as deep
learning, data-driven algorithms. The new concept called “Machine as a Service” (MaaS)
takes over the software as a service (SaaS) model and is another trend suitable for future
research. An interesting direction of future research concerns building performance
model evaluation related to the reasonable cost. The cost/benefit analysis of using preven-
tive tools in contrast to sustainability requirements is challenging for research.
This work suffers from several limitations, notably related to publication collections,
filtering, and analysis. The search strategy is biased by the problematic synonym of the
term “factory”. Primarily, the term “plant” is not interchangeable in the same meaning.
The study is limited because we omitted highly cited publications related to medicine in
burst analysis. Our goal was to bring the reader closer manufacturing- and production-
related publications. Investigated trends in burst detection analysis have weights based
on occurrence in publication titles. Results do not show the quality of publication based
on the times cited. Thus, we instead present examples of highly cited publications of most
important burst terms. The lack of a comprehensive review due to a steadily increasing
number of related works is another notable limitation of this study.
Supplementary Materials: The PRISMA Checklist (Table S1) and burst analysis results (Figures S1-
S3) are available online at www.mdpi.com/1424-8220/21/4/1470/s1, Figure S1: The burst detection in
topic Smart Factory/production based on WoS data, Figure S2: The burst detection in topic Smart
Sensors based on WoS data, Figure S3: The burst detection in topic Smart/predictive maintenance
based on WoS data, Table S1: The PRISMA Checklist.
Author Contributions: Conceptualisation, M.P. and J.V.; methodology, M.P.; software, M.P.; vali-
dation, M.P.; formal analysis, M.P.; investigation, M.P. and J.V.; resources, J.B.; data curation, M.P.;
writing—original draft preparation, M.P., J.V. and J.B.; writing—review and editing, M.P. and J.V.;
visualisation, M.P.; supervision, M.P.; project administration, J.V.; funding acquisition, J.B. and
J.V. All authors have read and agreed to the published version of the manuscript.
Funding: This research was funded by “EF-150-GAJU 047/2019/S”.
Institutional Review Board Statement: not applicable.
Informed Consent Statement: not applicable.
Data Availability Statement: not applicable.
Acknowledgments: The authors thank the University of South Bohemia in Ceske Budejovice for
technical support of the databases search.
Conflicts of Interest: The authors declare no conflict of interest.
References
1. Allwood, J.M.; Ashby, M.F.; Gutowski, T.G.; Worrell, E. Material efficiency: Providing material services with less material pro-
duction. Philos. Trans. R. Soc. A: Math. Phys. Eng. Sci. 2013, 371, 20120496, doi:10.1098/rsta.2012.0496.
2. Nightingale, A.J. Bounding difference: Intersectionality and the material production of gender, caste, class and environment in
Nepal. Geoforum 2011, 42, 153–162, doi:10.1016/j.geoforum.2010.03.004.
3. Zhang, Y.; Zhang, S. The impacts of GDP, trade structure, exchange rate and FDI inflows on China’s carbon emissions. Energy
Policy 2018, 120, 347–353, doi:10.1016/j.enpol.2018.05.056.
4. Song, G.; Li, W.; Wang, B.; Ho, S.C.M. A review of rock bolt monitoring using smart sensors. Sensors 2017, 17, 776,
doi:10.3390/s17040776.
5. Jin, X.; Feng, C.; Ponnamma, D.; Yi, Z.; Parameswaranpillai, J.; Thomas, S.; Salim, N.V. Review on exploration of graphene in
the design and engineering of smart sensors, actuators and soft robotics. Chem. Eng. J. Adv. 2020, 4, 100034,
doi:10.1016/j.ceja.2020.100034.
Sensors 2021, 21, 1470 33 of 39
6. Paidi, V.; Fleyeh, H.; Håkansson, J.; Nyberg, R.G. Smart parking sensors, technologies and applications for open parking lots:
A review. IET Intell. Transp. Syst. 2018, 12, 735–741, doi:10.1049/iet-its.2017.0406.
7. Talal, M.; Zaidan, A.A.; Zaidan, B.B.; Albahri, A.S.; Alamoodi, A.H.; AlSalem, M.A.; Lim, C.K.; Tan, K.L.; Shir, W.L.; Moham-
med, K.I. Smart home-based IoT for real-time and secure remote health monitoring of triage and priority system using body
sensors: Multi-driven systematic review. J. Med. Syst. 2019, 43, 42, doi:10.1007/s10916-019-1158-z.
8. Sony, M. Industry 4.0 and lean management: A proposed integration model and research propositions. Prod. Manuf. Res. 2018,
6, 416–432, doi:10.1080/21693277.2018.1540949.
9. Lee, G.-Y.; Kim, M.; Quan, Y.-J.; Kim, M.-S.; Kim, T.J.Y.; Yoon, H.-S.; Min, S.; Kim, D.-H.; Mun, J.-W.; Oh, J.W.; et al. Machine
health management in smart factory: A review. J. Mech. Sci. Technol. 2018, 32, 987–1009, doi:10.1007/s12206-018-0201-1.
10. Strozzi, F.; Colicchia, C.; Creazza, A.; Noè, C. Literature review on the ‘Smart Factory’ concept using bibliometric tools. Int. J.
Prod. Res. 2017, 55, 6572–6591, doi:10.1080/00207543.2017.1326643.
11. Feng, S.; Farha, F.; Li, Q.; Wan, Y.; Xu, Y.; Zhang, T.; Ning, H. Review on smart gas sensing technology. Sensors 2019, 19, 3760,
doi:10.3390/s19173760.
12. Sony, M.; Naik, S.S. Ten lessons for managers while implementing industry 4.0. IEEE Eng. Manag. Rev. 2019, 47, 45–52,
doi:10.1109/emr.2019.2913930.
13. Osterrieder, P.; Budde, L.; Friedli, T. The smart factory as a key construct of industry 4.0: A systematic literature review. Int. J.
Prod. Econ. 2020, 221, 107476, doi:10.1016/j.ijpe.2019.08.011.
14. Pereira, A.; Romero, F. A review of the meanings and the implications of the Industry 4.0 concept. Procedia Manuf. 2017, 13,
1206–1214, doi:10.1016/j.promfg.2017.09.032.
15. Bahena-Álvarez, I.L.; Cordón-Pozo, E.; Delgado-Cruz, A. Social entrepreneurship in the conduct of responsible innovation:
Analysis cluster in Mexican smes. Sustainability 2019, 11, 3714, doi:10.3390/su11133714.
16. Sousa, M.J.; Cruz, R.; Rocha, Á.; Sousa, M. Innovation trends for smart factories: A literature review. In New Knowledge in Infor-
mation Systems and Technologies; Rocha, Á., Adeli, H., Reis, L.P., Costanzo, S., Eds.; Advances in Intelligent Systems and Com-
puting; Springer International Publishing: Cham, Switzerland, 2019; Volume 930, pp. 689–698, ISBN 978-3-030-16180-4.
17. Lee, S.; Kim, J.-Y.; Lee, W. Smart factory literature review and strategies for korean small manufacturing firms. J. Inf. Technol.
Appl. Manag. 2017, 24, 133–152, doi:10.21219/JITAM.2017.24.4.133.
18. Carvalho, T.P.; Soares, F.A.A.M.N.; Vita, R.; Francisco, R.D.P.; Basto, J.P.; Alcalá, S.G.S. A systematic literature review of ma-
chine learning methods applied to predictive maintenance. Comput. Ind. Eng. 2019, 137, 106024, doi:10.1016/j.cie.2019.106024.
19. Sakib, N.; Wuest, T. Challenges and opportunities of condition-based predictive maintenance: A review. Procedia CIRP 2018, 78,
267–272, doi:10.1016/j.procir.2018.08.318.
20. Zonta, T.; Da Costa, C.A.; Righi, R.D.R.; De Lima, M.J.; Da Trindade, E.S.; Li, G.P. Predictive maintenance in the Industry 4.0: A
systematic literature review. Comput. Ind. Eng. 2020, 150, 106889, doi:10.1016/j.cie.2020.106889.
21. Olesen, J.F.; Shaker, H.R. Predictive maintenance for pump systems and thermal power plants: State-of-the-art review, trends
and challenges. Sensors 2020, 20, 2425, doi:10.3390/s20082425.
22. Fei, X.; Bin, C.; Jun, C.; Shunhua, H. Literature review: Framework of prognostic health management for airline predictive
maintenance. In Proceedings of the 2020 Chinese Control and Decision Conference (CCDC), Hefei, China, 22–24 Aug., 2020; pp.
5112–5117. doi:10.1109/CCDC49329.2020.9164546
23. Salkin, C.; Oner, M.; Ustundag, A.; Cevikcan, E. A conceptual framework for industry 4.0. In Industry 4.0: Managing The Digital
Transformation; Ustundag, A., Cevikcan, E., Eds.; Springer International Publishing: Cham, Switzerland, 2018; doi:10.1007/978-
3-319-57870-5_1.
24. Bartodziej, C.J. The concept industry 4.0. In The Concept Industry 4.0; Springer Fachmedien Wiesbaden: Wiesbaden, Germany,
2017; pp. 27–50, ISBN 978-3-658-16501-7.
25. Chen, B.; Wan, J.; Shu, L.; Li, P.; Mukherjee, M.; Yin, B. Smart factory of industry 4.0: Key technologies, application case, and
challenges. IEEE Access 2018, 6, 6505–6519, doi:10.1109/access.2017.2783682.
26. Eifert, T.; Eisen, K.; Maiwald, M.; Herwig, C. Current and future requirements to industrial analytical infrastructure—Part 2:
Smart sensors. Anal. Bioanal. Chem. 2020, 412, 2037–2045, doi:10.1007/s00216-020-02421-1.
27. Tan, P.; Wu, H.; Li, P.; Xu, H. Teaching management system with applications of RFID and IOT technology. Educ. Sci. 2018, 8,
26, doi:10.3390/educsci8010026.
28. Chen, Y.; Han, Z.; Cao, K.; Zheng, X.; Xu, X. Manufacturing upgrading in industry 4.0 era. Syst. Res. Behav. Sci. 2020, 37, 766–
771, doi:10.1002/sres.2717.
29. Karabegovic, I.; Mahmic, M.; Husak, E. The role of smart sensors in production processes and the implementation of industry
4.0. J. Eng. Sci. 2019, 6, b8–b13, doi:10.21272/jes.2019.6(2).b2.
30. Schmitt, R.H.; Voigtmann, C. Sensor information as a service–component of networked production. J. Sens. Sens. Syst. 2018, 7,
389–402, doi:10.5194/jsss-7-389-2018.
31. Nguyen, K.T.; Medjaher, K. A new dynamic predictive maintenance framework using deep learning for failure prognostics.
Reliab. Eng. Syst. Saf. 2019, 188, 251–262, doi:10.1016/j.ress.2019.03.018.
32. Selcuk, S. Predictive maintenance, its implementation and latest trends. Proc. Inst. Mech. Eng. Part B J. Eng. Manuf. 2017, 231,
1670–1679, doi:10.1177/0954405415601640.
Sensors 2021, 21, 1470 34 of 39
33. Tortorella, G.L. An empirical analysis of total quality management and total productive maintenance in industry 4.0. In Pro-
ceedings of the International Conference on Industrial Engineering and Operations Management (IEOM), Pretoria/Johannes-
burg, South Africa, 29 October–1 November, 2018; pp. 742–753.
34. Bukhsh, Z.A.; Saeed, A.; Stipanovic, I.; Doree, A.G. Predictive maintenance using tree-based classification techniques: A case of
railway switches. Transp. Res. Part C Emerg. Technol. 2019, 101, 35–54, doi:10.1016/j.trc.2019.02.001.
35. Li, D.; Landström, A.; Fast-Berglund, Åsa; Almström, P. Human-centred dissemination of data, information and knowledge in
industry 4.0. Procedia CIRP 2019, 84, 380–386, doi:10.1016/j.procir.2019.04.261.
36. Herrmann, F. The smart factory and its risks. System 2018, 6, 38, doi:10.3390/systems6040038.
37. Lee, S.M.; Lee, D.; Kim, Y.S. The quality management ecosystem for predictive maintenance in the Industry 4.0 era. Int. J. Qual.
Innov. 2019, 5, 4, doi:10.1186/s40887-019-0029-5.
38. Farooq, B.; Bao, J.; Li, J.; Liu, T.; Yin, S. Data-driven predictive maintenance approach for spinning cyber-physical production
system. J. Shanghai Jiaotong Univ. Sci. 2020, 25, 453–462, doi:10.1007/s12204-020-2178-z.
39. Shi, Z.; Xie, Y.; Xue, W.; Chen, Y.; Fu, L.; Xu, X. Smart factory in Industry 4.0. Syst. Res. Behav. Sci. 2020, 37, 607–617,
doi:10.1002/sres.2704.
40. Mabkhot, M.M.; Al-Ahmari, A.M.; Salah, B.; Alkhalefah, H. Requirements of the smart factory system: A survey and perspec-
tive. Machines 2018, 6, 23, doi:10.3390/machines6020023.
41. Frank, A.G.; Dalenogare, L.S.; Ayala, N.F. Industry 4.0 technologies: Implementation patterns in manufacturing companies. Int.
J. Prod. Econ. 2019, 210, 15–26, doi:10.1016/j.ijpe.2019.01.004.
42. Rojko, A. Industry 4.0 concept: Background and overview. Int. J. Interact. Mob. Technol. IJIM 2017, 11, 77–90,
doi:10.3991/ijim.v11i5.7072.
43. Pai, M.; McCulloch, M.; Gorman, J.D.; Pai, N.; Enanoria, W.; Kennedy, G.; Tharyan, P.; Colford, J.M. Systematic reviews and
meta-analyses: An illustrated, step-by-step guide. Natl. Med. J. India 2004, 17, 86–95.
44. Aromataris, E.; Riitano, D. Systematic reviews. AJN Am. J. Nurs. 2014, 114, 49–56, doi:10.1097/01.naj.0000446779.99522.f6.
45. Van Eck, N.J.; Waltman, L. Software survey: VOSviewer, a computer program for bibliometric mapping. Scientometrics 2010, 84,
523–538, doi:10.1007/s11192-009-0146-3.
46. Kleinberg, J. Bursty and hierarchical structure in streams. Data Min. Knowl. Discov. 2003, 7, 373–397,
doi:10.1023/a:1024940629314.
47. Sci2 Team Science of Science (Sci2) Tool. Available online: https://sci2.cns.iu.edu (accessed on 1 September 2020).
48. Moher, D.; Liberati, A.; Tetzlaff, J.; Altman, D.G. Preferred reporting items for systematic reviews and meta-analyses: The
PRISMA statement. Int. J. Surg. 2010, 8, 336–341, doi:10.1016/j.ijsu.2010.02.007.
49. Hooper, L.; Bartlett, C.; Davey Smith, G.; Ebrahim, S. Reduced dietary salt for prevention of cardiovascular disease (Cochrane
Review). In The Cochrane Library (Issue 1); Update Softwar: Oxford, UK, 2003.
50. Aheleroff, S.; Xu, X.; Lu, Y.; Aristizabal, M.; Velásquez, J.P.; Joa, B.; Valencia, Y. IoT-enabled smart appliances under industry
4.0: A case study. Adv. Eng. Inform. 2020, 43, 101043, doi:10.1016/j.aei.2020.101043.
51. Hopkins, J.; Hawking, P. Big dataanalytics and IoT in logistics: A case study. Int. J. Logist. Manag. 2018, 29, 575–591,
doi:10.1108/ijlm-05-2017-0109.
52. Varsha, P.V.; Sankar, S.R.; Mathew, R.J. Predictive analysis using big data analytics for sensors used in fleet truck monitoring
system. Int. J. Eng. Technol. 2016, 8, 714–719.
53. Taie, M.A.; Moawad, E.M.; Diab, M.; Elhelw, M. Remote diagnosis, maintenance and prognosis for advanced driver assistance
systems using machine learning algorithms. SAE Int. J. Passeng. Cars Electron. Electr. Syst. 2016, 9, 114–122, doi:10.4271/2016-01-
0076.
54. Djurdjanovic, D.; Lee, J.; Ni, J. Watchdog Agent—An infotronics-based prognostics approach for product performance degra-
dation assessment and prediction. Adv. Eng. Inform. 2003, 17, 109–125, doi:10.1016/j.aei.2004.07.005.
55. Hsu, H.-Y.; Srivastava, G.; Wu, H.-T.; Chen, M.-Y. Remaining useful life prediction based on state assessment using edge com-
puting on deep learning. Comput. Commun. 2020, 160, 91–100, doi:10.1016/j.comcom.2020.05.035.
56. Lu, Y.-W.; Hsu, C.-Y.; Huang, K.-C. An autoencoder gated recurrent unit for remaining useful life prediction. Processes 2020, 8,
1155, doi:10.3390/pr8091155.
57. Alonso, Álvaro; Pozo, A.; Cantera, J.M.; De La Vega, F.; Hierro, J.J. Industrial data space architecture implementation using
FIWARE. Sensors 2018, 18, 2226, doi:10.3390/s18072226.
58. Karimanzira, D.; Rauschenbach, T. Enhancing aquaponics management with IoT-based predictive analytics for efficient infor-
mation utilization. Inf. Process. Agric. 2019, 6, 375–385, doi:10.1016/j.inpa.2018.12.003.
59. Hwang, J.-Y.; Myung, S.-T.; Sun, Y.-K. Sodium-ion batteries: Present and future. Chem. Soc. Rev. 2017, 46, 3529–3614,
doi:10.1039/c6cs00776g.
60. Palomares, V.; Serras, P.; Villaluenga, I.; Hueso, K.B.; Carretero-González, J.; Rojo, T. Na-ion batteries, recent advances and
present challenges to become low cost energy storage systems. Energy Environ. Sci. 2012, 5, 5884–5901, doi:10.1039/c2ee02781j.
61. Buzea, C.; Pacheco, I.I.; Robbie, K. Nanomaterials and nanoparticles: Sources and toxicity. Biointerphases 2007, 2, MR17–MR71,
doi:10.1116/1.2815690.
62. Leitão, P. Agent-based distributed manufacturing control: A state-of-the-art survey. Eng. Appl. Artif. Intell. 2009, 22, 979–991,
doi:10.1016/j.engappai.2008.09.005.
Sensors 2021, 21, 1470 35 of 39
63. McFarlane, D.; Sarma, S.; Chirn, J.L.; Wong, C.; Ashton, K. Auto ID systems and intelligent manufacturing control. Eng. Appl.
Artif. Intell. 2003, 16, 365–376, doi:10.1016/s0952-1976(03)00077-0.
64. Wang, S.; Wan, J.; Li, D.; Zhang, C. Implementing smart factory of industrie 4.0: An outlook. Int. J. Distrib. Sens. Netw. 2016, 12,
doi:10.1155/2016/3159805.
65. Kanchev, H.; Lu, D.; Colas, F.; Lazarov, V.; Francois, B. Energy management and operational planning of a microgrid with a
PV-based active generator for smart grid applications. IEEE Trans. Ind. Electron. 2011, 58, 4583–4592,
doi:10.1109/tie.2011.2119451.
66. Kamilaris, A.; Prenafeta-Boldú, F.X. Deep learning in agriculture: A survey. Comput. Electron. Agric. 2018, 147, 70–90,
doi:10.1016/j.compag.2018.02.016.
67. Wang, S.; Wan, J.; Zhang, D.; Li, D.; Zhang, C. Towards smart factory for industry 4.0: A self-organized multi-agent system with
big data based feedback and coordination. Comput. Netw. 2016, 101, 158–168, doi:10.1016/j.comnet.2015.12.017.
68. Gubbi, J.; Buyya, R.; Marusic, S.; Palaniswami, M. Internet of Things (IoT): A vision, architectural elements, and future direc-
tions. Future Gener. Comput. Syst. 2013, 29, 1645–1660, doi:10.1016/j.future.2013.01.010.
69. Yick, J.; Mukherjee, B.; Ghosal, D. Wireless sensor network survey. Comput. Netw. 2008, 52, 2292–2330, doi:10.1016/j.com-
net.2008.04.002.
70. Peppas, N.A.; Hilt, J.Z.; Khademhosseini, A.; Langer, R. Hydrogels in biology and medicine: From molecular principles to bi-
onanotechnology. Adv. Mater. 2006, 18, 1345–1360, doi:10.1002/adma.200501612.
71. Housner, G.W.; Bergman, L.A.; Caughey, T.K.; Chassiakos, A.G.; Claus, R.O.; Masri, S.F.; Skelton, R.E.; Soong, T.T.; Spencer,
B.F.; Yao, J.T.P. Structural control: Past, present, and future. J. Eng. Mech. 1997, 123, 897–971, doi:10.1061/(asce)0733-
9399(1997)123:9(897).
72. Ou, J.; Li, H. Structural health monitoring in mainland China: Review and future trends. Struct. Health Monit. 2010, 9, 219–231,
doi:10.1177/1475921710365269.
73. Halim, D.; Moheimani, S. Spatial resonant control of flexible structures-application to a piezoelectric laminate beam. IEEE Trans.
Control Syst. Technol. 2001, 9, 37–53, doi:10.1109/87.896744.
74. Annigeri, A.R.; Ganesan, N.; Swarnamani, S. Free vibration behaviour of multiphase and layered magneto-electro-elastic beam.
J. Sound Vib. 2007, 299, 44–63, doi:10.1016/j.jsv.2006.06.044.
75. Atzori, L.; Lera, A.; Morabito, G. The internet of things: A survey. Tạp Chí Nghiên Cứu Dân Tộc 2018, 54, doi:10.25073/0866–
773x/64.
76. Pantelopoulos, A.; Bourbakis, N.G. A survey on wearable sensor-based systems for health monitoring and prognosis. IEEE
Trans. Syst. Man Cybern. C 2010, 40, 1–12, doi:10.1109/tsmcc.2009.2032660.
77. Zhang, Q.; Yang, L.T.; Chen, Z.; Li, P. A survey on deep learning for big data. Inf. Fusion 2018, 42, 146–157,
doi:10.1016/j.inffus.2017.10.006.
78. Gupta, H.; Dastjerdi, A.V.; Ghosh, S.K.; Buyya, R. iFogSim: A toolkit for modeling and simulation of resource management
techniques in the Internet of Things, edge and fog computing environments. Softw. Pract. Exp. 2017, 47, 1275–1296,
doi:10.1002/spe.2509.
79. Ang, K.H.; Chong, G.; Li, Y. PID control system analysis, design, and technology. IEEE Trans. Control. Syst. Technol. 2005, 13,
559–576, doi:10.1109/tcst.2005.847331.
80. Widodo, A.; Yang, B.-S. Support vector machine in machine condition monitoring and fault diagnosis. Mech. Syst. Signal Process.
2007, 21, 2560–2574, doi:10.1016/j.ymssp.2006.12.007.
81. Peng, Y.; Dong, M.; Zuo, M.J. Current status of machine prognostics in condition-based maintenance: A review. Int. J. Adv.
Manuf. Technol. 2010, 50, 297–313, doi:10.1007/s00170-009-2482-0.
82. Van Noortwijk, J. A survey of the application of gamma processes in maintenance. Reliab. Eng. Syst. Saf. 2009, 94, 2–21,
doi:10.1016/j.ress.2007.03.019.
83. Xu, X.; Newman, S. Making CNC machine tools more open, interoperable and intelligent—A review of the technologies. Com-
put. Ind. 2006, 57, 141–152, doi:10.1016/j.compind.2005.06.002.
84. McArthur, S.; Strachan, S.; Jahn, G. The design of a multi-agent transformer condition monitoring system. IEEE Trans. Power
Syst. 2004, 19, 1845–1852, doi:10.1109/tpwrs.2004.835667.
85. Wang, G.; Gunasekaran, A.; Ngai, E.W.; Papadopoulos, T. Big data analytics in logistics and supply chain management: Certain
investigations for research and applications. Int. J. Prod. Econ. 2016, 176, 98–110, doi:10.1016/j.ijpe.2016.03.014.
86. Bevilacqua, M.; Braglia, M. The analytic hierarchy process applied to maintenance strategy selection. Reliab. Eng. Syst. Saf. 2000,
70, 71–83, doi:10.1016/s0951-8320(00)00047-8.
87. Gao, R.; Wang, L.; Teti, R.; Dornfeld, D.; Kumara, S.; Mori, M.; Helu, M. Cloud-enabled prognosis for manufacturing. CIRP Ann.
2015, 64, 749–772, doi:10.1016/j.cirp.2015.05.011.
88. International Federation of Robotics Robot Density in the Manufacturing Industry 2019 Available online: https://ifr.org/down-
loads/press2018/Robot_density_by_country_2019_-_chart.png (accessed on 5 December 2020).
89. Manikandan, G.; Perumal, R. Symmetric cryptography for secure communication in IoT. In Proceedings of the Materials Today;
Elsevier Ltd: Oxford, UK, 2020. doi:10.1016/j.matpr.2020.09.737.
90. Xu, W.; Cai, Y.; Gao, S.; Hou, S.; Yang, Y.; Duan, Y.; Fu, Q.; Chen, F.; Wu, J. New understanding of miniaturized VOCs moni-
toring device: PID-type sensors performance evaluations in ambient air. Sens. Actuators B Chem. 2021, 330, 129285,
doi:10.1016/j.snb.2020.129285.
Sensors 2021, 21, 1470 36 of 39
91. Antons, O.; Arlinghaus, J.C. Designing decision-making authorities for smart factories. Procedia CIRP 2020, 93, 316–322,
doi:10.1016/j.procir.2020.04.047.
92. Goodall, P.; Sharpe, R.; West, A. A data-driven simulation to support remanufacturing operations. Comput. Ind. 2019, 105, 48–
60, doi:10.1016/j.compind.2018.11.001.
93. Yan, J.; Lee, J.; Pan, Y.-C. Introduction of watchdog prognostics agent and its application to elevator hoistway performance
assessment. J. Chin. Inst. Ind. Eng. 2005, 22, 56–63, doi:10.1080/10170660509509277.
94. Kiangala, K.S.; Wang, Z. Initiating predictive maintenance for a conveyor motor in a bottling plant using industry 4.0 concepts.
Int. J. Adv. Manuf. Technol. 2018, 97, 3251–3271, doi:10.1007/s00170-018-2093-8.
95. Starr, A.; Willetts, R.; Hannah, P.; Hu, W.; Banjevic, D.; Jardine, A.K.S. Data fusion applications in intelligent condition moni-
toring. In 6th WSEAS International Multiconference on Circuits, Systems, Communications and Computers (CSCC 2002),
Rethymno, Crete, Greece, 7–14 July 2002, pp. 110–115.
96. Li, J.; Tao, H.; Shuhong, L.; Salih, S.Q.; Zain, J.M.; Yankun, L.; Vivekananda, G.N.; Thanjaivadel, M. Internet of things assisted
condition-based support for smart manufacturing industry using learning technique. Comput. Intell. 2020, 36, 1737–1754,
doi:10.1111/coin.12319.
97. Suh, J.H.; Kumara, S.R.; Mysore, S.P. Machinery fault diagnosis and prognosis: Application of advanced signal processing tech-
niques. CIRP Ann. 1999, 48, 317–320, doi:10.1016/s0007-8506(07)63192-8.
98. Peng, C.-C.; Tsan, L.-G. IEPE accelerometer fault diagnosis for maintenance management system information integration in a
heavy industry. J. Ind. Inf. Integr. 2020, 17, 100120, doi:10.1016/j.jii.2019.100120.
99. Barbieri, M.; Nguyen, K.T.P.; Diversi, R.; Medjaher, K.; Tilli, A. RUL prediction for automatic machines: A mixed edge-cloud
solution based on model-of-signals and particle filtering techniques. J. Intell. Manuf. 2020, 1–20, doi:10.1007/s10845-020-01696-6.
100. Çınar, Z.M.; Nuhu, A.A.; Zeeshan, Q.; Korhan, O.; Asmael, M.; Safaei, B. Machine learning in predictive maintenance towards
sustainable smart manufacturing in industry 4.0. Sustainability 2020, 12, 8211, doi:10.3390/su12198211.
101. Tinga, T. Principles of Loads and Failure Mechanisms; Springer International Publishing: London, UK, 2013.
102. Kumar, A.; Chinnam, R.B.; Tseng, F. An HMM and polynomial regression based approach for remaining useful life and health
state estimation of cutting tools. Comput. Ind. Eng. 2019, 128, 1008–1014, doi:10.1016/j.cie.2018.05.017.
103. Lin, C.-C.; Deng, D.-J.; Kuo, C.-H.; Chen, L. Concept drift detection and adaption in big imbalance industrial iot data using an
ensemble learning method of offline classifiers. IEEE Access 2019, 7, 56198–56207, doi:10.1109/access.2019.2912631.
104. Musselman, M.; Djurdjanovic, D. Tension monitoring in a belt-driven automated material handling system. CIRP J. Manuf. Sci.
Technol. 2012, 5, 67–76, doi:10.1016/j.cirpj.2011.08.002.
105. Sadiki, S.; Ramadany, M.; Faccio, M.; Amegouz, D.; Boutahari, S. Running smart monitoring maintenance application using
cooja simulator. Int. J. Eng. Res. Afr. 2019, 42, 149–159, doi:10.4028/www.scientific.net/jera.42.149.
106. Doostparast, M.; Kolahan, F.; Doostparast, M. A reliability-based approach to optimize preventive maintenance scheduling for
coherent systems. Reliab. Eng. Syst. Saf. 2014, 126, 98–106, doi:10.1016/j.ress.2014.01.010.
107. Al-Jlibawi, A.; Othman, I.M.L.; Al-Huseiny, M.S.; Bin Aris, I.; Noor, S.B.M. Efficient soft sensor modelling for advanced manu-
facturing systems by applying hybrid intelligent soft computing techniques. Int. J. Simul. Syst. Sci. Technol. 2019, doi:10.5013/ijs-
sst.a.19.03.15.
108. Bekar, E.T.; Nyqvist, P.; Skoogh, A. An intelligent approach for data pre-processing and analysis in predictive maintenance
with an industrial case study. Adv. Mech. Eng. 2020, 12, 168781402091920, doi:10.1177/1687814020919207.
109. Chien, C.-F.; Chen, C.-C. Data-driven framework for tool health monitoring and maintenance strategy for smart manufacturing.
IEEE Trans. Semicond. Manuf. 2020, 33, 1, doi:10.1109/tsm.2020.3024284.
110. Kozłowski, E.; Mazurkiewicz, D.; Żabiński, T.; Prucnal, S.; Sęp, J. Machining sensor data management for operation-level pre-
dictive model. Expert Syst. Appl. 2020, 159, 113600, doi:10.1016/j.eswa.2020.113600.
111. Lao, L.; Ellis, M.; Durand, H.; Christofides, P.D. Real-time preventive sensor maintenance using robust moving horizon estima-
tion and economic model predictive control. AIChE J. 2015, 61, 3374–3389, doi:10.1002/aic.14960.
112. Park, B.; Jeong, H.; Huh, H.; Kim, M.; Lee, S. Experimental study on the life prediction of servo motors through model-based
system degradation assessment and accelerated degradation testing. J. Mech. Sci. Technol. 2018, 32, 5105–5110,
doi:10.1007/s12206-018-1007-x.
113. Peng, C.C.; Kuo, C.H.; Wu, C.Y. Graphical histogram algorithm for integrated-circuit-piezoelectric-type accelerometer for health
condition diagnosis and monitoring. Sens. Mater. 2017, 1645, doi:10.18494/SAM.2017.1738.
114. Shan, L.; Wang, Z.R.; Jiang, C. Key technologies of real-time visualization system for intelligent manufacturing equipment op-
erating state under hot environment. J. Internet Technol. 2020, 21, 1479–1489, doi:10.3966/160792642020092105021.
115. Tarashioon, S.; Baiano, A.; Van Zeijl, H.; Guo, C.; Koh, S.; Van Driel, W.; Zhang, G. An approach to “Design for Reliability” in
solid state lighting systems at high temperatures. Microelectron. Reliab. 2012, 52, 783–793, doi:10.1016/j.microrel.2011.06.029.
116. Tsao, Y.-C.; Lee, P.-L.; Liao, L.-W.; Zhang, Q.; Vu, T.-L.; Tsai, J. Imperfect economic production quantity models under predictive
maintenance and reworking. Int. J. Syst. Sci. Oper. Logist. 2020, 7, 347–360, doi:10.1080/23302674.2019.1590663.
117. Uhlmann, E.; Laghmouchi, A.; Geisert, C.; Hohwieler, E. Smart wireless sensor network and configuration of algorithms for
condition monitoring applications. J. Mach. Eng. 2017, 17, 45–55.
118. Villalobos, K.; Suykens, J.; Illarramendi, A. A flexible alarm prediction system for smart manufacturing scenarios following a
forecaster–analyzer approach. J. Intell. Manuf. 2020, 1–22, doi:10.1007/s10845-020-01614-w.
Sensors 2021, 21, 1470 37 of 39
119. Vlasov, A.I.; Grigoriev, P.V.; Krivoshein, A.I.; Shakhnov, V.A.; Filin, S.S.; Migalin, V.S. Smart management of technologies:
Predictive maintenance of industrial equipment using wireless sensor networks. Entrep. Sustain. Issues 2018, 6, 489–502,
doi:10.9770/jesi.2018.6.2(2).
120. Yan, J.; Meng, Y.; Lu, L.; Li, L. Industrial big data in an industry 4.0 environment: Challenges, schemes, and applications for
predictive maintenance. IEEE Access 2017, 5, 23484–23491, doi:10.1109/access.2017.2765544.
121. Zhang, H.; Zhang, Q.; Shao, S.; Niu, T.; Yang, X. Attention-based LSTM network for rotatory machine remaining useful life
prediction. IEEE Access 2020, 8, 132188–132199, doi:10.1109/access.2020.3010066.
122. Zhang, Y.; Cheng, Y.; Wang, X.V.; Zhong, R.Y.; Zhang, Y.; Tao, F. Data-driven smart production line and its common factors.
Int. J. Adv. Manuf. Technol. 2019, 103, 1211–1223, doi:10.1007/s00170-019-03469-9.
123. Luo, Z.; Hu, X.; Borisenko, V.E.; Chu, J.; Tian, X.; Luo, C.; Xu, H.; Li, Q.; Li, Q.; Zhang, J.; et al. Structure-property relationships
in graphene-based strain and pressure sensors for potential artificial intelligence applications. Sensors 2019, 19, 1250,
doi:10.3390/s19051250.
124. Cottone, P.; Re, G.L.; Maida, G.; Morana, M. Motion sensors for activity recognition in an ambient-intelligence scenario. In
Proceedings of the 2013 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM
Workshops), San Diego, CA, USA, 18–22 March 2013; pp. 646–651.
125. Shoaib, M.; Bosch, S.; Incel, O.D.; Scholten, J.; Havinga, P.J.M. Fusion of smartphone motion sensors for physical activity recog-
nition. Sensors 2014, 14, 10146–10176, doi:10.3390/s140610146.
126. Kaptan, C.; Kantarci, B.; Soyata, T.; Boukerche, A. Emulating smart city sensors using soft sensing and machine intelligence: A
case study in public transportation. In Proceedings of the 2018 IEEE International Conference on Communications (ICC), Kansas
City, MO, USA, 20–24 May 2018; pp. 1–7.
127. Ryu, S.; Kim, S.-C. Impact sound-based surface identification using smart audio sensors with deep neural networks. IEEE Sens.
J. 2020, 20, 10936–10944, doi:10.1109/jsen.2020.2993321.
128. Mennel, L.; Symonowicz, J.; Wachter, S.; Polyushkin, D.K.; Molina-Mendoza, A.J.; Mueller, T. Ultrafast machine vision with 2D
material neural network image sensors. Nat. Cell Biol. 2020, 579, 62–66, doi:10.1038/s41586-020-2038-x.
129. Sergiyenko, O.; Tyrsa, V.; Flores-Fuentes, W.; Rodriguez-Quiñonez, J.; Mercorelli, P. Machine vision sensors. J. Sens. 2018, 2018,
3202761, doi:10.1155/2018/3202761.
130. Rodriguez-Vazquez, A.; Fernandez-Berni, J.; Lenero-Bardallo, J.A.; Vornicu, I.; Carmona-Galan, R. CMOS vision sensors: Em-
bedding computer vision at imaging front-ends. IEEE Circuits Syst. Mag. 2018, 18, 90–107, doi:10.1109/mcas.2018.2821772.
131. Ping, J.; Wang, Y.; Wu, J.; Ying, Y. Development of an electrochemically reduced graphene oxide modified disposable bismuth
film electrode and its application for stripping analysis of heavy metals in milk. Food Chem. 2014, 151, 65–71, doi:10.1016/j.food-
chem.2013.11.026.
132. Schroeder, V.; Savagatrup, S.; He, M.; Lin, S.; Swager, T.M. Carbon nanotube chemical sensors. Chem. Rev. 2018, 119, 599–663,
doi:10.1021/acs.chemrev.8b00340.
133. Salvatore, G.A.; Sülzle, J.; Kirchgessner, N.; Hopf, R.; Magno, M.; Tröster, G.; Valle, F.D.; Cantarella, G.; Robotti, F.; Jokic, P.; et
al. Biodegradable and highly deformable temperature sensors for the internet of things. Adv. Funct. Mater. 2017, 27,
doi:10.1002/adfm.201702390.
134. Farahani, H.; Wagiran, R.; Hamidon, M.N. Humidity sensors principle, mechanism, and fabrication technologies: A compre-
hensive review. Sensors 2014, 14, 7881–7939, doi:10.3390/s140507881.
135. Alberto, N.; Domingues, M.F.; Marques, C.; André, P.; Antunes, P. Optical fiber magnetic field sensors based on magnetic fluid:
A review. Sensors 2018, 18, 4325, doi:10.3390/s18124325.
136. Jureschi, C.-M.; Linares, J.; Boulmaali, A.; Dahoo, P.R.; Rotaru, A.; Garcia, Y. Pressure and temperature sensors using two spin
crossover materials. Sensors 2016, 16, 187, doi:10.3390/s16020187.
137. Wang, T.; Guo, Y.; Wan, P.; Zhang, H.; Chen, X.; Sun, X. Flexible transparent electronic gas sensors. Small 2016, 12, 3748–3756,
doi:10.1002/smll.201601049.
138. Indri, M.; Lachello, L.; Lazzero, I.; Sibona, F.; Trapani, S. Smart sensors applications for a new paradigm of a production line.
Sensors 2019, 19, 650, doi:10.3390/s19030650.
139. Jia, L.; Chen, R.; Xu, J.; Zhang, L.; Chen, X.; Bi, N.; Gou, J.; Zhao, T. A stick-like intelligent multicolor nano-sensor for the detec-
tion of tetracycline: The integration of nano-clay and carbon dots. J. Hazard. Mater. 2021, 125296, 125296, doi:10.1016/j.jhaz-
mat.2021.125296.
140. Thakkar, S.; Dumée, L.F.; Gupta, M.; Singh, B.R.; Yang, W. Nano–enabled sensors for detection of arsenic in water. Water Res.
2021, 188, 116538, doi:10.1016/j.watres.2020.116538.
141. Singh, K.; Sharma, S.; Shriwastava, S.; Singla, P.; Gupta, M.; Tripathi, C. Significance of nano-materials, designs consideration
and fabrication techniques on performances of strain sensors-A review. Mater. Sci. Semicond. Process. 2021, 123, 105581,
doi:10.1016/j.mssp.2020.105581.
142. Büchi, G.; Cugno, M.; Castagnoli, R. Smart factory performance and Industry 4.0. Technol. Forecast. Soc. Chang. 2020, 150, 119790,
doi:10.1016/j.techfore.2019.119790.
143. Kalsoom, T.; Ramzan, N.; Ahmed, S.; Ur-Rehman, M. Advances in sensor technologies in the era of smart factory and industry
4.0. Sensors 2020, 20, 6783, doi:10.3390/s20236783.
144. Zunino, C.; Valenzano, A.; Obermaisser, R.; Petersen, S. Factory communications at the dawn of the fourth industrial revolution.
Comput. Stand. Interfaces 2020, 71, 103433, doi:10.1016/j.csi.2020.103433.
Sensors 2021, 21, 1470 38 of 39
145. Vrchota, J.; Řehoř, P.; Maříková, M.; Pech, M. Critical success factors of the project management in relation to industry 4.0 for
sustainability of projects. Sustainability 2020, 13, 281, doi:10.3390/su13010281.
146. Lujak, M.; Fernández, A.; Onaindia, E. Spillover Algorithm: A decentralised coordination approach for multi-robot production
planning in open shared factories. Robot. Comput. Manuf. 2021, 70, 102110, doi:10.1016/j.rcim.2020.102110.
147. Shpilevoy, V.; Shishov, A.; Skobelev, P.; Kolbova, E.; Kazanskaia, D.; Shepilov, Y.; Tsarev, A.; Shepilov, Y. Multi-agent system
“Smart Factory” for real-time workshop management in aircraft jet engines production. IFAC Proc. Vol. 2013, 46, 204–209.
148. Leusin, M.E.; Kück, M.; Frazzon, E.M.; Maldonado, M.U.; Freitag, M. Potential of a multi-agent system approach for production
control in smart factories. IFAC PapersOnLine 2018, 51, 1459–1464, doi:10.1016/j.ifacol.2018.08.309.
149. Nunes, M.L.; Pereira, A.; Alves, A. Smart products development approaches for Industry 4.0. Procedia Manuf. 2017, 13, 1215–
1222, doi:10.1016/j.promfg.2017.09.035.
150. Wang, Y.; Ma, H.-S.; Yang, J.-H.; Wang, K.-S. Industry 4.0: A way from mass customization to mass personalization production.
Adv. Manuf. 2017, 5, 311–320, doi:10.1007/s40436-017-0204-7.
151. Yang, J.; Xie, H.; Yu, G.; Liu, M. Achieving a just–in–time supply chain: The role of supply chain intelligence. Int. J. Prod. Econ.
2021, 231, 107878, doi:10.1016/j.ijpe.2020.107878.
152. Kumar, M.; Shenbagaraman, V.M.; Shaw, R.N.; Ghosh, A. Predictive data analysis for energy management of a smart factory
leading to sustainability. In Innovations in Electrical and Electronic Engineering; Lecture Notes in Electrical Engineering; Fa-
vorskaya, M.N., Mekhilef, S., Pandey, R.K., Singh, N., Eds.; Springer Singapore: Singapore, 2021; Volume 661, pp. 765–773, ISBN
9789811546914.
153. Cavalieri, S.; Salafia, M.G. A model for predictive maintenance based on asset administration shell. Sensors 2020, 20, 6028,
doi:10.3390/s20216028.
154. Jimenez-Cortadi, A.; Irigoien, I.; Boto, F.; Sierra, B.; Rodriguez, G. Predictive maintenance on the machining process and ma-
chine tool. Appl. Sci. 2019, 10, 224, doi:10.3390/app10010224.
155. Carlson, A.; Sakao, T. Environmental assessment of consequences from predictive maintenance with artificial intelligence tech-
niques: Importance of the system boundary. Procedia CIRP 2020, 90, 171–175, doi:10.1016/j.procir.2020.01.093.
156. Xu, Y.; Nascimento, N.M.M.; De Sousa, P.H.F.; Nogueira, F.G.; Torrico, B.C.; Han, T.; Jia, C.; Filho, P.P.R. Multi-sensor edge
computing architecture for identification of failures short-circuits in wind turbine generators. Appl. Soft Comput. 2021, 101,
107053, doi:10.1016/j.asoc.2020.107053.
157. Xiang, W.; Tian, Y.; Liu, X. Theoretical analysis of detection sensitivity in nano-resonator-based sensors for elasticity and density
measurement. Int. J. Mech. Sci. 2021, 197, 106309, doi:10.1016/j.ijmecsci.2021.106309.
158. Fernandes, S.; Antunes, M.; Santiago, A.R.; Barraca, J.P.; Gomes, D.; Aguiar, R.L. Forecasting appliances failures: A machine-
learning approach to predictive maintenance. Information 2020, 11, 208, doi:10.3390/info11040208.
159. Verhagen, W.J.; De Boer, L.W. Predictive maintenance for aircraft components using proportional hazard models. J. Ind. Inf.
Integr. 2018, 12, 23–30, doi:10.1016/j.jii.2018.04.004.
160. Ruhi, S.; Karim, M.R. Selecting statistical model and optimum maintenance policy: A case study of hydraulic pump. Springer-
Plus 2016, 5, 969, doi:10.1186/s40064-016-2619-1.
161. Stodola, P.; Stodola, J.; Stodola Model of predictive maintenance of machines and equipment. Appl. Sci. 2019, 10, 213,
doi:10.3390/app10010213.
162. Warneke, B.A.; Pister, K.S.J. MEMS for distributed wireless sensor networks. In Proceedings of the 9th International Conference
on Electronics, Circuits and Systems, Doubrovnik, Croatia, 15–18 September 2002; pp. 291–294.
163. Ovsthus, A.A.K.; Kristensen, L.M. An industrial perspective on wireless sensor networks—a survey of requirements, protocols,
and challenges. IEEE Commun. Surv. Tutor. 2014, 16, 1391–1412, doi:10.1109/surv.2014.012114.00058.
164. Flammini, A.; Ferrari, P.; Marioli, D.; Sisinni, E.; Taroni, A. Wired and wireless sensor networks for industrial applications.
Microelectron. J. 2009, 40, 1322–1336, doi:10.1016/j.mejo.2008.08.012.
165. Li, X.; Li, D.; Wan, J.; Vasilakos, A.V.; Lai, C.-F.; Wang, S. A review of industrial wireless networks in the context of Industry
4.0. Wirel. Netw. 2017, 23, 23–41, doi:10.1007/s11276-015-1133-7.
166. Usamentiaga, R.; Venegas, P.; Guerediaga, J.; Vega, L.; Molleda, J.; Bulnes, F.G. Infrared thermography for temperature meas-
urement and non-destructive testing. Sensors 2014, 14, 12305–12348, doi:10.3390/s140712305.
167. Akerberg, J.; Gidlund, M.; Bjorkman, M. Future research challenges in wireless sensor and actuator networks targeting indus-
trial automation. In Proceedings of the 2011 9th IEEE International Conference on Industrial Informatics, Caparica, Lisbon,
Portugal, 26–29 July 2011; pp. 410–415.
168. Park, H.; Kim, H.; Joo, H.; Song, J. Recent advancements in the Internet of Things related standards: A oneM2M perspective.
ICT Express 2016, 2, 126–129, doi:10.1016/j.icte.2016.08.009.
169. Cavalieri, S.; Salafia, M.G.; Scroppo, M.S. Towards interoperability between OPC UA and OCF. J. Ind. Inf. Integr. 2019, 15, 122–
137, doi:10.1016/j.jii.2019.01.002.
170. Turk, Žiga Interoperability in construction – Mission impossible? Dev. Built Environ. 2020, 4, 100018,
doi:10.1016/j.dibe.2020.100018.
171. Salarian, H.; Chin, K.-W.; Naghdy, F. Coordination in wireless sensor–actuator networks: A survey. J. Parallel Distrib. Comput.
2012, 72, 856–867, doi:10.1016/j.jpdc.2012.02.013.
172. Kullaa, J. Robust damage detection using Bayesian virtual sensors. Mech. Syst. Signal Process. 2020, 135, 106384,
doi:10.1016/j.ymssp.2019.106384.
Sensors 2021, 21, 1470 39 of 39
173. Villagrossi, E.; Simoni, L.; Beschi, M.; Pedrocchi, N.; Marini, A.; Tosatti, L.M.; Visioli, A. A virtual force sensor for interaction
tasks with conventional industrial robots. Mechatronics 2018, 50, 78–86, doi:10.1016/j.mechatronics.2018.01.016.
174. Landolfi, G.; Barni, A.; Izzo, G.; Fontana, A.; Bettoni, A. A MaaS platform architecture supporting data sovereignty in sustaina-
bility assessment of manufacturing systems. Procedia Manuf. 2019, 38, 548–555, doi:10.1016/j.promfg.2020.01.069.
175. Toublanc, T.; Guillet, S.; De Lamotte, F.; Berruet, P.; Lapotre, V. Using a virtual plant to support the development of intelligent
gateway for sensors/actuators security. IFAC PapersOnLine 2017, 50, 5837–5842, doi:10.1016/j.ifacol.2017.08.541.
176. Alcaraz, C.; Roman, R.; Najera, P.; Lopez, J.; Tello, M.C.A. Security of industrial sensor network-based remote substations in
the context of the Internet of Things. Ad Hoc Netw. 2013, 11, 1091–1104, doi:10.1016/j.adhoc.2012.12.001.
177. Gungor, V.C.; Hancke, G.P. Industrial wireless sensor networks: Challenges, design principles, and technical approaches. IEEE
Trans. Ind. Electron. 2009, 56, 4258–4265, doi:10.1109/tie.2009.2015754.