SPECIAL SECTION ON KEY TECHNOLOGIES FOR SMART FACTORY OF INDUSTRY 4.

Received October 24, 2017, accepted December 9, 2017, date of publication December 14, 2017, date of current version March 9, 2018.
Digital Object Identifier 10.1109/ACCESS.2017.2783682

Smart Factory of Industry 4.0: Key Technologies,

Application Case, and Challenges
1 1 2,3
BAOTONG CHEN , JIAFU WAN , (Member, IEEE), LEI SHU , (Senior Member, IEEE),
4 5 6
PENG LI , MITHUN MUKHERJEE , (Member, IEEE), AND BOXING YIN
1 School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510641, China
2
School of Engineering, Nanjing Agricultural University, Nanjing 210014,
3
China School of Engineering, University of Lincoln, Lincoln, U.K.
4
Institute Industrial IT, Ostwestfalen-Lippe University of Applied Science, 32657 Lemgo, Germany
5
Guangdong Provincial Key Laboratory of Petrochemical Equipment Fault Diagnosis, Guangdong University of Petrochemical
Technology, Maoming 525000, China
6
School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou 314000, China
Corresponding author: Jiafu Wan ([email protected])
This work was supported in part by the National Key Research and Development Project under Grant 2017YFE0101000, in part
by the Key Program of Natural Science Foundation of Guangdong Province, China, under Grant 2017B030311008, in part by
the Maoming Engineering Research Center of Industrial Internet of Things under Grant 517018, and in part by the National
Natural Science Foundation of China under Grant 61401107.

ABSTRACT Due to the current structure of digital factory, it is necessary to build the smart
factory to upgrade the manufacturing industry. Smart factory adopts the combination of physical
technology and cyber technology and deeply integrates previously independent discrete
systems making the involved technologies more complex and precise than they are now. In this
paper, a hierarchical architecture of the smart factory was proposed rst, and then the key
technologies were analyzed from the aspects of the physical resource layer, the network layer,
and the data application layer. In addition, we discussed the major issues and potential solutions
to key emerging technologies, such as Internet of Things (IoT), big data, and cloud computing,
which are embedded in the manufacturing process. Finally, a candy packing line was used to
verify the key technologies of smart factory, which showed that the overall equipment
effectiveness of the equipment is signi cantly improved.

INDEX TERMS Smart factory, big data, cloud computing, cyber-physical systems, industrial Internet of

Things.

I. INTRODUCTION In the context of intelligent manufacturing, it is

With the rapid development of electric and electronic tech- important to establish the smart factory to achieve
nology, information technology and advanced advanced manu-facturing based on network
manufacturing technology, the production mode of technologies and manufacturing data. In addition, the
manufacturing enter-prises is being transferred from digital implementation of smart factory should take into account
to intelligent. The new era that combines virtual reality the status quo and manufacturing require-ments. Due to
technology based on the Cyber-Physical System (CPS) is the different characteristics of manufacturing eld and
coming [1] [4]. Due to the new challenges, the advantages information eld, there are still many technical problems to
of traditional manufac-turing industries have been gradually be solved in order to accelerate the path of smart factory.
diminished. Conse-quently, the intelligent manufacturing The main goals of this paper are summarized as follows:
technology is one of high technology areas where In the physical resources layer, physical equipment
industrialized countries highly pay more attention to. Europe needs to have support for real-time information acqui-
2020 strategy [5], Industry 4.0 strategy [6] and China sition, and communication devices should provide a
manufacturing 2025 [7] have been proposed. United States high-speed transmission of heterogeneous information.
has gradually accelerated the speed of reindustrialization The workshop should ensure fast recon guration and
and manufacturing re ow [8]. The transformation of adaptability. In addition, the intelligence of underlying
intelligent manufacturing intrigued the profound and lasting equipment should be enhanced in order to meet the
effect on the future manufacturing worldwide. requirements of Internet of Things (IoT).

2169-3536 2017 IEEE. Translations and content mining are permitted for academic research only.
VOLUME 6, 2018 Personal use is also permitted, but republication/redistribution requires IEEE permission. 6505
See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
 B. Chen et al.: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges

In the network layer, Industrial Internet of Things smart factory, which is based on digital and automated
(IIoT) should support new protocols and new data factory, uses information technology (e.g., cloud platform
format with high exibility and scalability, whereas the and IIoT) to improve the management of manufacturing
Indus-trial Wireless Sensor Networks (IWSNs) bring resources and QoS [13], [14]. In order to build the smart
new opportunities for development of industrial fac-tory, manufacturing enterprises should improve
network. Additionally, the other relevant production and marketing, enhance controllability of
technologies (e.g., OLE for Process Control Uni ed production process, and reduce manual intervention in
Architecture (OPC UA), Software de ned Networks workshop. Through the analysis of manufacturing data,
(SDNs), and Device-to-Device (D2D) the smart factory can realize exible manufacturing,
communication) should be introduced to guarantee dynamic recon guration, and pro-duction optimization,
Quality-of-Service (QoS) of the net-work, reliable which are aimed to adapt the system to the changes of
communication, and cooperation among equipment. business model and consumer shopping behavior [15].
In the data application layer, the cloud platform should be In the implementation of smart factory, the IIoT is
able to analyze the semantics of various data. There-fore, employed to integrate the underlying equipment resources.
ontology is being employed in modeling of the smart Accordingly, the manufacturing system has abilities of per-
factory, which can provide the abilities of self-organization, ception, interconnection and data integration. The data anal-
self-learning and self-adaption. Moreover, data analysis ysis and scienti c decision are used to achieve production
could provide the scienti c basis for decision-making, while scheduling, equipment service and quality control of
data mining could be used to products in smart factory. Further, the Internet of services is
ensure design optimization and active maintenance. intro-duced to virtualize the manufacturing resources from a
In general, we developed and analyzed the hierarchical archi- local database to the cloud server. Through the human-
tecture of smart factory with the focus on key technologies of machine interaction, the global collaborative process of
every layer. The remainder of the paper is organized as follows. intelligent manufacturing oriented to the order-driven market
In Section II, the architecture of smart factory is presented, and is built. Therefore, the smart factory represents an
approaches for implementation of smart factory based on engineering system that mainly consists of three aspects:
hierarchical architecture are discussed. In Section III, the key interconnection, collab-oration and execution. As shown in
technologies of physical resource layer are studied. In Section Fig. 1, the architecture of smart factory [16], [17] includes
IV, technologies related to the network layer are given. The four layers, namely physical resource layer, network layer,
methods used for data processing in data application layer are data application layer, and terminal layer. With the aim to
presented in Section V. Its research results and development convert modern factory into smart factory, key technologies
trends of these technologies are also presented. In Section VI, involved in all layers have to be studied in detail.
the implementation of smart factory, namely the prototype
platform of candy packing line, was introduced, wherein the key III. PHYSICAL RESOURCES LAYER
technologies of the smart fac-tory were employed and veri ed in The physical resources include all manufacturing resources
practice. In Section VII, main issues and challenges of key involved in the entire life cycle of manufacturing, which rep-
technologies are presented. Finally, in Section VIII a brief resent the basis for achievement of intelligent
conclusion and envisions of further development of smart manufacturing. The ef cient manufacturing of customized
factory are given. products puts for-ward new demands on manufacturing
equipment, production line and data acquisition. Therefore,
II. SMART FACTORY ARCHITECTURE to meet the requirements of smart factory, present problems
In the context of Industry 4.0, the intelligent manufacturing of key technologies should be solved.
attracts enormous interest from government, enterprises and
academic researchers [9]. Therefore, the construction pat-terns A. RECONFIGURABLE MANUFACTURING UNIT
of smart factory are widely discussed. However, the standards Due to the lack of exible and con gurable construction,
for smart factory implementation have not been established yet. current manufacturing equipment in workshop has strong
Benkamoun et al. [10] proposed a class diagram which can be speci city and relatively narrow application range, which
used to represent the manufacturing system from different results in weak adaptation to manufacturing environment
perspectives of entities and functions. Radziwon et al. [11] changes. The manufacturing unit, which is modularized by
expounded former research from the concept of smart factory, manufacturing equipment (e.g., industrial robot, mechanical
and they pointed out that smart factory is actually an exploring arm, and machining center), improves dynamic scheduling.
of adaptive and exible manufacturing. Lin et al. [12] proposed Moreover, the controller is recon gurable and provides an
an architecture for cloud manufacturing systems oriented to extension of manufacturing equipment functions.
aerospace conglom-erate, which facilitates optimal con guration
of manufac-turing resources. The above-mentioned authors 1) MODULAR MANUFACTURING UNITS
provided a guidance architecture for smart factory. In summary, From the aspect of modular manufacturing units,
the FiaschØ et al. [18] proposed a modular-adaptive and

6506 VOLUME 6, 2018

B. Chen et al.: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges

FIGURE 1. Hierarchical architecture of smart factory.

self-contained recon gurable robotic island to improve In addition, heterogeneity of interaction should be
assembly capacity of the workshop, where exible manu- took account.
facturing ability was also enhanced by integrated manage- The functions of different modular manufacturing
ment framework which controls and organizes the modular units may be redundant for a certain product,
manufacturing unit. Piranda and Bourgeois [19] proposed a therefore it is crucial to make an optimal or
distributed algorithm for recon guration of lattice-based suboptimal combinatorial scheme.
modular self-recon gurable robots, which drastically sim-pli Each manufacturing unit can not only meet the manu-
es complexity of robots con guration through iterative facturing requirements of products, but also improve the
approach. Further, Valente [20] proposed a vertical cyber smart factory ef ciency in a self-organized way.
physical integration of cognitive robots in manufacturing. In the intelligent manufacturing, small quantities of vari-
The cognitive robots, which were vertically integrated into ous products enter into manufacturing system disorderly,
the manufacturing industry, and coordinated with the man- which certainly leads to the deadlock phenomenon.
ufacturing execution system. In the context of intelligent Currently, approach for deadlock prevention in exible
manufacturing, the cognitive robots can perceive manufacturing systems is a hot research topic [21], [22].
information uncertainty, change scheduling management
and adjust man-ufacturing behavior to independently cope 2) CONFIGURABLE CONTROLLER
with a complex manufacturing problem. The intelligent level The con gurability of the control system refers to the ability
of smart factory is closely related to the modular to integrate, extend, replace, and reuse hardware or
manufacturing unit, and the above-mentioned literature software components of the system. Proper con guration of
describes the intelligent robot units from different controller can improve con gurability of manufacturing unit,
perspectives. The modular manufacturing units can work which expands unit’s function in multi-application scenarios.
independently and deal with a changeable scheduling of In this way, manufacturing unit would be able to adapt
smart factory. swiftly to operation condition changes [23], [24].
Therefore, it is very important to enhance the intelligence Short and Burn [25] upgraded robot function using
of robots units. Several suggestions for construction of mod- available software components, which were used to adapt
ular manufacturing units are proposed as follows: the robot to changeable operating conditions. Moreover,
Modular manufacturing units should cooperate with they introduced an advanced design of robot controller
each other to accomplish the common tasks, where the which can be used in the new generation of robots. Morales-
emphasis is on the mutual perception and the Velazquez et al. [26] developed a new multi-agent
collaboration mechanism between intelligent modules.
6507
VOLUME 6, 2018
 B. Chen et al.: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges

distributed controller system to meet the requirements of technology convergence to support the re-con gurability of
intelligent recon gurable Computer Numerical Control (CNC). door trim assembly line, where the emphases is on mini-
Speci cally, they proposed an open architecture for recon mization of reconstruction complexity and maximization of
gurable applications based on a Field Programmable Gate workbench recyclability. Järvenpää et al. [30] proposed an
Array (FPGA) and utilized an eXtensible Markup Lan-guage ontology model and a description concept for manufacturing
(XML) structure to describe system les. Since the component resources based on XML, and developed a set of integrated
models of a control system can improve the recon guration tools to recon gure production system rapidly and auto-
processes by standardization and universal-ity, the embedded matically. Gyulai et al. [31] introduced a hierarchical plan-
design tools such as Ptolemy II have been matured for ning decision work ow to assign products to dedicated and
component model. The service oriented technology with the recon gurable production lines, which denotes an integrated
semantic web theory is employed to adapt external demand on way to optimize system con guration and production plan.
industry control domain. However, this static-related recon Goyal and Jain [32] divided the optimization design of recon
gurable technology cannot meet dynamic requirements. gurable production line into two stages. In the rst stage, a
Lepuschitz et al. [27] proposed an automation agent-based multiple-objective particle swarm algorithm was proposed to
architecture which subdivides the control layer into two layers, optimize cost, machine utilization, oper-ational capability,
where the high-level layer is combined with the ontology while and con guration convertibility. At the next stage, a
the low-level layer is based on the IEC 61499 standard. The maximum deviation method was used to choose an optimal
low-level control is modi ed by the reasoning and initiating scheme from the alternatives in order to avoid both
recon guration processes of high-level layer. Hence, the control subjectivity and uncertainty in decision-making process.
system provides the self-recon guration and self-adaption
services. However, the cur-rent research still lacks the The recon gurable production line can generate a
validation techniques for the strict background. Based to large range of different products due to its variability,
normalized structure of recon gurable logic controller, Adamski scalability and schedulability, which is the basis of exible
and Tkacz [28] proposed a hierar-chical modular control logic manufac-turing in smart factory. Presently, the problem
described by a petri net where the formal reasoning method is of production line is strong specialty, which can be
used to predict results of a logic design. With the development enhanced by advance planning and control methods.
of equipment computing ability, it has become a trend to apply Here, we build a recon g-urable system to simulate the
the multi-agent technol-ogy, knowledge modeling, and production line and propose a scheme for recon
reasoning technology in the control system. guration. The feasibility of proposed scheme is veri ed by
the manufacturing scenario. With the aim to respond
The research of con gurable controller mainly focuses on timely to the market requirements, it is nec-essary to
its structure and function. General, an information model is implement a recon gurable production line in the smart
built in the control system to perceive operation con-dition, factory.
while reasoning decision is made according to the
information of evaluation module. Moreover, the controller C. INTELLIGENT DATA ACQUISITION
system completes recon guration planning and implements The manufacturing resource data denote basic information for
processes automatically for speci c needs. However, lack of workshop scheduling and intelligent service in smart factory.
support for interoperable technology, such as interactive The wireless sensor networks (WSNs) are employed in smart
interface, results in poor exibility. The basic theory from factory for data monitoring, acquisition and logging. Based on
recon gurable aspect (e.g., ontology modeling and veri ca- data analysis and using an intelligent equipment in
tion) is still weak. Moreover, dynamic re-con guration mech- manufacturing scenarios, the manufacturing execution sys-tem
anism is not perfect and research results are only applicable can properly implement production scheduling. The most
to the speci c scenarios. Thus, more attention should be common types of wireless sensor networks are Radio Fre-
paid to the embedded component model in real-time run- quency Identi cation (RFID) [33], ZigBee, and Bluetooth. Zhong
ning framework. Therefore, the knowledge-driven adaptive et al. [34] proposed a RFID-enabled real-time man-ufacturing
re-con guration is crucial for the implementation of recon- execution system for mass-customization produc-tion, where
gurable service. RFID identi es anomalous information and feeds it back to the
decision-making production system in real-time, thus the smart
B. RECONFIGURABLE PRODUCTION LINE factory has more ef cient execution plans and makes accurate
Nowadays the manufacturing products in the market are scheduling decisions. Zhang et al. [35] proposed a new data
characterized by small batches and multiple varieties. There- cleaning algorithm based on WSNs and RFID, where WSNs
fore, the production-line should recon gure its process paths and RFID system provide an excellent infrastructure for data
and recombine manufacturing units dynamically. Accord-ingly, acquisition, distribution, and process-ing. With the development
the smart factory should adjust product type and pro-duction of RFID, the Near-Field Commu-nication (NFC) has been
capacity in real-time. Kim et al. [29] proposed an application studied as an access to manufactur-ing resources [36]. Further,
service based on information and communication both Bluetooth and ZigBee meet the requirements for cost of
industrial automation of wireless
6508
VOLUME 6, 2018
B. Chen et al.: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges

standardized [39], [40]. However, there are still many

issues such as routing, congestion control, errors
handling and seg-mentation technology in network layer.
The IWSNs and the other related technologies involved
in the smart factory are discussed in the following.

A. INDUSTRIAL WIRELESS SENSOR NETWORKS

The Industrial Wireless Sensor Networks (IWSNs) represent
the expansion and promotion of the existing wireless com-
munication technology intended for industrial application
and they lead to the revolution of measurement and control
mode in the traditional industrial eld. In the meantime, the
deployment of industrial networks has become exible,
reliable, and low-cost. Currently, the universal and mature
FIGURE 2. Dynamic electrocardiogram system. wireless network communication standards mainly include
wireless HART, WIA-AP, and ISA100.11a. The application
of industrial networks is complex, and it is dif culty to intro-
communication technologies (e.g., low price and low duce a generic wireless network communication standard.
energy consumption) [37]. The industrial wireless network technology should have low
Various kinds of special sensors are used to collect data in latency, high reliability, and high synchronous accuracy
manufacturing area, wherein devices are independent of each when dealing with a control service, and should have high
other. The collected data are heterogeneous with uneven access density and low power consumption in data
quality. Therefore, the communication interface of intelli-gent acquisition. The networks should also have a high
equipment should be compatible with a series of com- transmission rate of inter-active service.
munication protocols. For instance, it should be compatible with Reliability and latency are the core requirements of indus-
OPC, Open Database Connectivity (ODBC), RS232, Dynamic trial wireless network communication [41], [42]. The wireless
data exchange (DDE), etc., which are used to con-nect control network technology has gradually permeated into the indus-
systems such as Supervisory Control and Data Acquisition trial eld including data acquisition and production control.
(SCADA), Distributed Control System (DCS), and Process The workshop is characterized by a complicated electro-
Control System (PCS). In addition, data acquisi-tion devices magnetic environment. Meanwhile, data transmission may
should be easily set up and their interfaces should be exible be unsynchronized with the clock causing packet loss and
and scalable. The manufacturing resources should support a delay or some other interference factors, which have
ne-grained data acquisition in process visibility system. As negative effect on QoS of IWSNs. Niu et al. [43] presented a
show in Fig. 2, the equipment operating state is similar to the reli-able reactive routing enhancement to increase the
human heart beating. The equipment health management resilience of WSNs/IWSNs to link dynamics, which provides
system, which is based on the monitoring equip-ment status reliable and energy-ef cient packet delivery regardless the
obtained by the ‘‘electrocardiograph (EGC)’’, can predict system unreliable wireless links. Therefore, both high reliability and
failure and arrange necessary maintenance activity in advance. low deliv-ery latency are guaranteed. Dobslaw et al. [44]
However, current pattern of data acqui-sition is still a bottleneck proposed a generic heuristic scheduling algorithm extension
of intelligent manufacturing. to improve the end-to-end reliability of WSNs. In summary,
IWSNs are complex dynamical networks which couple real-
IV. NETWORK LAYER time control with high-speed communication using a multi-
Industrial networks represent the integration of various kinds node collaboration.
of network technologies such as eld bus and sensor net- Energy ef ciency is an important factor that affects adapt-
works. The network layer, which is characterized by per- ability of wireless sensor networks [45]. Due to the large
ception and control, plays an important role in the smart number of nodes in IWSNs, a dynamic scheduling is needed in
factory. Due to the improvements of cloud computing tech- intelligent manufacturing. Gao et al. [46] improved energy ef
nology [38], real-time and reliable network techniques are ciency with the coded preambles in low-power sensor networks.
required for data transmission, information sharing between Lee et al. [47] proposed FlexiCast which uses an energy-ef
intelligent equipment, and manufacturing cloud platform. cient method to check the integrity of software objects, and it
The advanced information technologies (e.g., IWSNs and signi cantly reduces energy consumption for both software
eld bus) and their related technologies provide an impor-tant object updating and modi cation checking. Luo et al. [48]
way to meet above mentioned requirements. Field buses achieved energy saving using an opportunistic routing algorithm
(e.g., Foundation Fieldbus (FF), Pro bus, and Hart) grad- that ensures a minimal-power low-residual energy, and which is
ually meet enterprise requirements of open, universal and focused on minimization of energy con-sumption and
compatible networks, and most of them have already been maximization of network lifetime of data relay

VOLUME 6, 2018 6509

 B. Chen et al.: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges

in one-dimensional queue networks. The current researches agent is characterized by autonomy, heterogeneity and decen-
on energy ef ciency are mainly based on following aspects: tralization [22]. Leitªo et al. [52] pointed out that OPC UA is
improvement of data forwarding mechanism of sensor itself, transferred from the original communication architecture (e.g.,
optimization of deployment of network nodes, and devel- the Component Object Model (COM) standard) to the service-
opment of new energy-saving algorithms. Along with the oriented architecture with a cross platform, in which way the
expanded deployment of IWSNs to enhance energy ef communication among equipment and intelligent manufacturing
ciency more attention should be paid to continuity. system is provided. With the standardization of OPC UA, a new
Since the wireless communication has a character of radio opportunity for multi-agent technology is created. Girbea et al.
broadcasting, wireless networks are easily accessed by both [53] designed a service-oriented architecture for optimization of
authorized users and unauthorized visitors. For that reason, industrial application, where OPC UA is used to connect
IWSNs are more vulnerable than industrial wire networks, and everysub-manufacturing system and ensure real-time
invasive intrusion may lead to serious consequences for smart communication between devices in stan-dardized and uni ed
factory. Sun et al. [49] proposed a fountain-coding (FC) aided manner. Fernbach et al. [54] proposed an OPC UA information
relaying scheme, where a secure cooperative transmis-sion is modelling framework which provides a holistic information base.
guaranteed by accumulating the required number of FC Hence, the multi-agent architecture can integrate agent-based
packets. Zou and Wang [50] proposed an optimal sensor system into the existing manufac-turing site using a semantic
scheduling scheme to improve the physical-layer security of method.
industrial WSNs against the eavesdropping attack, and they The multi-agent system is a system of coordinated solving of
also conducted an asymptotic intercept probability analy-sis to large-scale complex problems with the cooperation of every
characterize diversity gains of round-robin scheduling and agent. Besides data transmission, the OPC UA can be used to
optimal sensor scheduling. Dong and Liu [51] proposed robust integrate production data into manufacturing environ-ment and
and secure time-synchronization protocol to defend from Sybil provide semantic annotation for every agent. Due to the
attacks to the sensor networks. Due to limited computing power construction of data source and receiver, the OPC UA can
and networks resources, it is impossible to apply generic allocate all manufacturing resources including embedded
security protocols and mechanisms directly to the IWSNs. system to the speci c areas and extensible computing nodes
Therefore, IWSNs are faced with greater security challenges through the address space and pre-de ned model. Further, the
than public networks. OPC UA solves the problem related to uni ed access to the
The equipment monitoring and information interaction are information of different systems. The OPC UA-based interaction
convenient for smart factory with IWSNs because they in multi-agent systems makes all agent coordinate with each
accel-erate the progress of intelligent manufacturing. The other to solve problems in a parallel manner, which effectively
IWSNs should meet the requirements for reliability and real- improves the problem solving ef ciency. Thus, the development
time data transmission. Because of uncertainty of position, of OPC UA is of high importance because of redundancy, which
energy ef ciency of IWSNs constrains its expansion. When a is featured with adjustable overdue settings, error detection,
large-scale equipment accesses to the industrial networks, and automatic correction. Therefore, the communication tools
network security is very important. In the IWSNs scenarios which are in accordance with the OPC UA standard can deal
such as mass connection, low-power consumption, and with the communication errors and failures easily.
wide cover-age, new wireless communication technologies
(e.g., NB-IoT, 5G, LTE, and 3GPP) provide low latency and
high reliabil-ity. However, certain measures should be taken 2) SOFTWARE DEFINED INDUSTRIAL NETWORKS
to improve robustness of signal propagation in complex Network technology is used to integrate internal and exter-
electromagnetic environment and extend working hours of nal resources in smart factory in order to form compre-
networks nodes. Accordingly, networks standardization and hensive, uni ed, and high covering manufacturing resource.
security defense need further improvement. Therefore, it is crucial to achieve network scalability and
adaptive transmission [55], [56]. Making network con g-
B. RELATED TECHNOLOGIES uration exible is a key issue for researchers. The SDNs
The application of network technology in smart factory simplify the required hardware with centralized control by a
pro-vides reliable and supportable information service. software, which facilitates network management and satis
However, the implementation of industrial internet still es requirements of dynamic networks for intelligent
faces with many problems such as information manufacturing [57], [58].
interaction between equipment, exible con guration of As the IIoT advances, the network becomes overloaded due
networks, and transmission delay. Some of key related to a large number of connections between heterogeneous
technologies are described in detail in the following. equipment. Bizanis and Kuipers [59] supposed that SDNs and
networks virtualization technology provide scale and versatility
1) OPC UA-BASED INTERACTION IN MULTI-AGENT SYSTEMS necessary for IoT service, and they pointed out that SDNs could
The intelligent manufacturing system is a multi-agent system be used together with machine learning tech-nology to make
which consists of task-driven intelligent equipment, where network more intelligent and self-adaptive.

6510 VOLUME 6, 2018

B. Chen et al.: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges

Wan et al. [60] proposed a software-de ned IIoT architec-ture control of communication system. In common cellular net-
which can determine network resource allocation and works, an intelligent equipment can use D2D communication
accelerate information exchange by an easily customizable technology for direct communication via an isotropic antenna at
networking protocol. Using this architecture, some innovative every base station. This technology provides a new way for low-
industrial applications can be realized through well-de ned latency communication, large data transmission, and massive
APIs. The OpenFlow [61], [62], which is a novel switched access to the mobile terminal. Holfeld et al. [68] stated that
internetwork model, promotes implementation of SDNs [63]. LTE-based wireless technology can provide new services for
The application of OpenFlow drastically reduces complexity of factory automation. On the other hand, 5G com-munication
control plane, increases programmability and extensibility, and technology brings new opportunities to the auto-mated wireless
provides a gradual adoption path [64]. Though the Open-Flow is communication technology. Liu et al. [69] described the
not a sole standard that supports SDN technology, its rules challenges and potential solutions to the imple-mentation of
have been generally accepted. Namely, the OpenFlow-based machine-type communication system and pre-sented a
SDN deployment has been already used in industrial scenarios, roadmap of current cellular technologies toward 5G mobile
such as intranets and data center. systems capable of fully-machine type commu-nication(MTC).
Currently, the basic network system of manufacturing Pratas and Popovski [70] proposed network-assisted D2D
enterprises is consisted of different types of communica-tion schemes that enable the cooperation between machine-type
devices (e.g., routers, switches, and services). There-fore, devices and standard cellular devices, and meet the MTC
present network management problems are as follows: outage requirement by maximizing the rate of broadband
(1) work- ow of network security is complex [65], and it is dif services. Bagaa et al. [71] proposed an opti-mal solution that
cult to locate network failure; (2) traditional networks cannot uses D2D communication to reduce the overhead of MTC
effectively support a real-time cloud manufacturing; in devices in 5G networks, and which aims to decrease energy
addition, it is crucial to establish the coordination in multi- consumption and data transfer delay at eNodeBs. Yu et al. [72]
layer network; and lastly, (3) it is dif cult to adjust net-work proposed a D2D-communication-based system underlying
bandwidth in real time according to the ow demand of data cellular networks to improve local services, where optimal
acquisition, which leads to low utilization of net-work resource allocation and power con-trol between cellular and
resources. The solutions to the above problems require an D2D connections were analyzed for different resource sharing
intelligent network management. The SDNs framework, modes.
which makes network programmable by separating the con-
trol layer from the data transmission layer is presented in
Fig. 3. This separation meets demand on centralized control
of network and increases exibility of con guration and
operation of data center. The OpenFlow-based SDNs pro-
vide a good platform for innovative network applications and
development of IIoT.

FIGURE 4. The D2D communication in smart factory.

Once the D2D communication link is established in com-

munication network, data transmission is free of core device
and interference from the middleware, which can reduce
pressure on core network in communication system, improve
FIGURE 3. The SDN framework in smart factory.
spectrum utilization and networks throughput, and expand
network capacity. The D2D-based communication in smart
factory is presented in Fig. 4. The D2D communication tech-
3) DEVICE TO DEVICE COMMUNICATION nology brings high-quality network services to the intelli-gent
The contradictions between rapid growth of intelligent equip- manufacturing. Although, a small-scale distribution of data
ment and limited bandwidth of industrial networks become packets is more convenient, there are still many chal-lenges
increasingly prominent in smart factory [66], [67]. The D2D related to the introduction of D2D communication technology
communication refers to the communication wherein devices into cellular networks. For instance, it is dif cult to switch
directly exchange information with neighbors under the network interaction from D2D communication to

VOLUME 6, 2018 6511

 B. Chen et al.: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges

cellular communication, and spectrum reuse in D2D system interacts with physical system with high stability.
commu-nication causes interference. Additionally, edge computing makes a full use of embed-ded
computing of terminal-side equipment, which provides
4) EDGE COMPUTING autonomy of equipment with a disperse treatment. Mean-
Edge computing denotes an open platform with many fea-tures while, the edge computing that is coordinated with cloud
such as networking, computing, storage, and appli-cation. Edge computing increases intelligence of the entire manufacturing
computing is performed at the network edge near to device or system. As edge intelligence advances, communication and
data source. Moreover, edge computing provides intelligent computing performances in distributed perception, decision-
services that meet key requirements of intelligent manufacturing making and control will change signi cantly.
for agile connection, real-time pro-cessing, data cleaning, and
privacy protection [73], [74]. Brito et al. [75] supposed that V. DATA APPLICATION LAYER
deployment of programmable fog nodes, which is attributed to The semantic association between manufacturing data is
inter-node Peer-to-Peer (P2P) communication and services established by ontology model [78]. The essence of data
orchestration without cen-tralized control, could increase application is to discover knowledge from data resources
exibility, reliability and ef - ciency. Pizo« et al. [76] argued that and build the industrial value chain. The industrial big
edge computing enables dynamic monitoring and control of data mainly include structured data and semi-structured
manufacturing process. Meanwhile they pointed out that edge data. As data mining technology advances, data-driven
computing requires special IT ecosystem to build dynamic innovation will further promote intelligent manufacturing.
systems for transfer of production data. Georgakopoulos et al.
[77] presented a manufacturing roadmap of IoT and edge cloud A. ONTOLOGY-BASED MANUFACTURING MODEL
computing to address elastic and virtual manufacturing Considering the large amount of manufacturing resources,
resources, which provides opportunities for real-time monitoring resources concept may vary among different perspectives. A
of production KPIs and smart inventory management. formal description is presented by ontology for domain
knowledge. Namely, ontology is a semantic representation of
In the context of distributed computing based on hetero- related concepts and their relationship in intelligent manufac-
geneous networks, the concept of edge computing is closely turing. It is signi cant to construct the ontology for knowl-edge
related to distributed autonomy in industry. Edge computing sharing, reuse, and reasoning. Chungoora et al. [79] presented
combines disperse treatment with centralized upload. This a model-driven method with ontology to achieve the
mode provides an effective use of network bandwidth and interoperability and the knowledge sharing for manufac-turing
ensures autonomy, security and robustness of manufactur- system across multiple platforms in product lifecycle. Usman et
ing system. Fig. 5 shows the generic architecture of edge al. [80] supposed that a veri able formal semantic base could
computing. The middle layer is edge computing platform. solve the problem of inappropriate interpretation of
The lower layer controls manufacturing equipment with the manufacturing concepts, and that formal manufacturing
characteristics of low latency, interoperability, autonomy, reference ontology is a key component of future interoperable
and adaptability. manufacturing system. Wang et al. [81] proposed a cloud-
based manufacturing semantic model which can be used to
obtain general task ontology construction and task sub-ontology
matching. Alsa and Vyatkin [82] proposed an approach for fast
recon guration of modular manufacturing systems, which is
based on the recon guration agent with ontology. The ontology-
based model achieves standardized terms and semantic
knowledge for decision-making or other applications in
intelligent manufacturing [83].
The ontology-based modeling of manufacturing resources
provides a novel technical reference for construction of smart
factory. Due to the improvement of manufacturing system con
guration, the ontology-based model promotes event-driven
interoperability in smart factory. Ontology- based applications
are able to optimize scheduling for manufac-turing resources
and provide a semantic basis for consistent description of
FIGURE 5. The generic architecture of edge computing. interactions between different applications. The modeling
language for manufacturing ontology (e.g., the Web Ontology
The upper layer reduces pressure to the core network, Language) has rich semantic expression ability and support
optimizes data transmission, and provides support for appli- reasoning mechanism. Additionally, the ontology-based
cation extension. The edge computing integrates opera-tion modeling for intelligent manufactur-ing should align the
technology with ICT, while its distributed control following criteria: clarity, consistency,

6512 VOLUME 6, 2018

B. Chen et al.: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges

FIGURE 7. Open application architecture for active maintenance based on

manufacturing big data.

FIGURE 6. Ontology-based domain modeling method.

built models for bearing faults prediction based on
historical wind turbine data.
extendibility, coding minimum deviation, and ontology The regular maintenance in traditional mode just wastes
min-imum commitment. resource and time. In contrast, active maintenance based on
As shown in Fig. 6, the ontology-based modeling combines big data can provide necessary maintenance service. The
knowledge base with database to achieve semantic reasoning, active maintenance reduces machine downtime, optimizes
and this method decouples data processing from speci c resource utilization, and increases production. In the mean-
applications. The data-centric architecture has both exibility and time, the maintenance cost is also reduced. The open appli-
universality. The ontology-based manufacturing model provides cation architecture of active maintenance based on manufac-
a new research direction in fault diagnosis, equip-ment health turing big data is presented in Fig. 7. The requirements for
prediction, and active preventive maintenance in smart factory. active maintenance of production facilities are as follows:
(1) improve intelligence of workshop equipment; (2) coop-
erate with domain experts; and (3) express knowledge pro-
B. APPLICATIONS OF BIG DATA IN MANUFACTURING fessionally. The machine learning and statistical analysis
The big data in smart factory mainly include real-time are the mainstream approaches of active maintenance.
sensor data, machine log, and manufacturing process However, many factors should be considered. Such as
data, which have large volume, multiple sources, and uncer-tainty of production process, integration of different
spare value. In the context of intelligent manufacturing, meth-ods and model applicability. Presently, active
the applications of big data develop rapidly in industrial maintenance of complex equipment still lacks the effective
supply chain anal-ysis and optimization, product quality methods, thus further improvement is needed.
control, and active maintenance [84] [87].
2) PRODUCT DESIGN OPTIMIZATION BASED ON
1) ACTIVE MAINTENANCE BASED ON BIG DATA MANUFACTURING BIG DATA
Proper operation of intelligent equipment is a guarantee of With the development of IoT technology, it becomes conve-
continuous production in the smart factory, where oper-ation nient to collect the product data. At present, the optimization
conditions have an important impact on equipment based on big data in manufacturing is effective on the stages of
utilization and productivity. Data mining technology brings logistics, warehousing, and selling. Analysis technology based
new breakthroughs to failure prediction and active main- on big data is used in product design, which takes advantage of
tenance. Wan et al. [88] proposed a manufacturing big data knowledge discovery and trend prediction of data. Graening
solution for active preventive maintenance in manu-facturing and Sendhoff [92] proposed a shape mining as a framework,
environment, which combines a real-time active based on engineering design data, which was applied to the
maintenance mechanism with an off-line prediction method. passenger car design. Williams et al. [93] developed a big data
Regev and Benson-Karhi [89] proposed a segmented model management infrastructure with seman-tic technologies, which
for preventive maintenance of semiconductor manufac- provides uni ed data access layer and consistent approach to
turing equipment, namely they presented both paramet-ric analytic execution. Bae and Kim [94] proposed the apriori and
and non-parametric models for preventive maintenance. C5.0 algorithms for data mining, and mining results were
Hashemian and Bean [90] discussed the limitations of time- attributed as knowledge to provide the suggestions for product
based equipment maintenance methods and advantages of design and marketing. However, if data receiver and feedback
predictive and online maintenance techniques for early iden- mechanism are added to the traditional product, the product
ti cation of equipment failure. Xiong et al. [91] used data itself will become the data source for design optimization
mining to identify bearing faults in wind turbines, and they without affecting its use.

VOLUME 6, 2018 6513

 B. Chen et al.: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges

In addition, the product logs, maintenance data, and user The physical resources layer was consisted of intelli-
data will become the valuable resources to build product gent equipment, conveyor equipment, packing
informa-tion model. The scienti c and reasonable product products. It was mainly responsible for execution of
evaluation results can be obtained by data fusion and tasks such as processing, monitoring, and assembling.
data mining, thus these technologies represent the basis The manufac-turing process information was the
for design of a next-generation product. primary data source for upper application.
Data mining helps designers to transform big data into The cloud service layer contained the cloud platform (a
enlightening knowledge using selection, analysis and mod-eling service cluster system based on the Hadoop archi-
methods. The data fusion technology can analyze the same tecture) which provided data storage and computing
object based on multiple data resource. The data mining resource for data application. The ontology model of
technology is introduced in optimization of product design packing line was built on the cloud platform, and a
because it can deal with fuzzy and uncertain reasoning results relationship between objects was established in two
caused by a designer. However, the product optimization dimensions: structure and interaction. The ProtØgØ
design based on big data lacks the knowledge discovery tools. was used to build application-oriented ontology, and
Therefore, we cannot take full advantage of potential com-plex constraints were expressed by semantic web
information from design examples. The decision-making, which rule language. The manufacturing data were uploaded
is based on existing knowledge, is less exible in design to the cloud platform to form a semantic data model.
optimization. The product design optimization based on big data Based on the knowledge base, the Jena tool was used
requires multidisciplinary knowledge. Therefore, the other to reason the equipment operating mode. This layer
interdisciplinarities associated with big data, such as deep provides sup-ports for the fault alarm, the resource
learning and arti cial intelligent, have become impor-tant allocation, and the scheduling optimization.
research directions in product design optimization. The terminal layer mainly included end-user devices,
such as smart phones, desktop computers and electri-
VI. APPLICATION CASE STUDY cal boards, which were distributed in workshop, of ce,
From the view of intelligent manufacturing, manufacturing monitoring center and other regions. Terminal devices
equipment should be equipped with the abilities of edge com- were used to visualize the results of cloud processing,
puting, environment perception, and coordination between and they supported remote monitoring of operation and
equipment. The smart factory, which is a cyber-physical maintenance. Moreover, customers were able to check
production system (CPPS), integrates intelligent sensors, the order in real time using the intelligent terminal.
embedded terminal systems, intelligent control system, and The network layer was used to connect layers within
communications facilities. The peer to peer interaction (e.g., smart factory. According to the distributed control, the
person to equipment, equipment to equipment, service to connection between controller and actuator was
service) is achieved by CPPS. Therefore, building of smart implemented by eld bus, Modbus, and EtherCAT. The
factory should take into consideration manufacturing char- connection between equipment was achieved by
acteristics to meet rapidly-changing market needs [95], [96]. In the combination of Ethernet and DDS, which formed
the following, we use the laboratory prototype platform as an the self-organized network. The connection between
example to explore typical characteristics of smart factory. The equipment and cloud platform was implemented
laboratory prototype platform, which represents a candy by integration of Ethernet and OPC UA, which
packing production line, is shown in Fig. 8. provided data interaction.
The basic ow of candy packing is as follows. Firstly, cus-
tomers choose candy and purchase it online. Then, the
order information is sent directly to the manufacturing
system. Finally, the completed order is automatically
transported by logistical system of smart factory. The
candy packaging line has typical characteristics of smart
factory, such as high interconnection, dynamical recon
guration, deep integration, and so on.
In the experiment, we took into account factors such as
equipment availability, equipment performance, and qual-i
ed rate of products. Next, we developed a cloud-aided
FIGURE 8. Prototype platform for the validation of key technologies. manufacturing system, which gave suggestions on schedul-
ing optimization of self-organized equipment. The six-month
According to the smart factory architecture, the prototype experiment was performed on the equipment of candy pack-
platform had four layers including the physical resources aging line. The smart meter is used to measure the total
layer, the cloud service layer, the terminal layer, and the electrical energy for the equipment in the lab. We calculated
network layer. The prototype layers were as follows. the related parameter every day, and the average was took

6514 VOLUME 6, 2018

B. Chen et al.: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges

The high-speed operation in workshop needs higher standards

of data acquisition. Namely, data acquisition is the basis of big
data analytics, where physical resource should: (1) support ne-
grained and ef cient data acquisition, and achieve visi-bility of
manufacturing process; (2) integrate heterogeneous data in a
uni ed system by generic protocols (e.g., RFID, ZigBee, and
NFC); and (3) improve extensibility of controller for access to
the core industrial networks.

B. DEEP INTEGRATION NETWORKS

The IIoT facilitates a deep integration of information and
industrialization. The advanced IIoT technology is important for
the implementation of the smart factory. The mature and
generic standards have not been formed yet in the eld of
FIGURE 9. The overall effectiveness and influential factors of prototyping IWSNs, and the standardization process of IWSNs should be
platform. promoted continuously. In the complicated electromagnetic
environment, data transmission should meet the requirements
as the value of the month. As shown in Fig. 9, the Over-all of reliability and real time equipment control. Due to the limited
Equipment Effectiveness (OEE) of tested equipment is energy, energy ef ciency is a key issue that affects the
improved from 0.42 to 0.82 using the cloud-aided manu- deployment of IWSNs. Moreover, because of the access of
facturing system. Compared to the centralized scheduling, large-scale devices, network security also becomes very
the self-organized scheduling with the cloud-aided manufac- important. As the information technologies have advanced (e.g.,
turing system has more remarkable effect. In general, the NB-IoT, 5G, LTE-Advanced, and 3GPP), a signi - cant progress
candy packing line is an example which was used to explore has been made in industrial wireless networks. These progress
exibility, ef ciency, and transparency of smart factory. has provided new solutions for key issues of IWSNs, such as
reliability, real-time performance, energy ef ciency, and security
VII. ISSUES AND CHALLENGES
strategy.
Due to the rapid progress of manufacturing, smart factory
should be exible and reliable, and satisfy the high qual-ity Development of information technologies has brought
standards. The technological breakthroughs bring many opportunities to the intelligent manufacturing. The OPC UA-
opportunities for the implementation of intelligent manufac- based interaction facilitates the coordination between
turing. However, there are still some issues and challenges. intelligent agents because a multi-agent system can solve
problems in a parallel way. The OpenFlow-based SDN tech-
A. INTELLIGENT REQUIREMENTS OF EQUIPMENT nology provides more exible solution for network con g-
Due to the foundation place of the underlying equipment, it uration, which enhances network management ability. The
is crucial to monitor and control the underlying man- D2D technology makes communication between devices
ufacturing resource for recon guration of production line, more ef cient and expands network capacity. The edge
dynamic scheduling, and information fusion in smart fac- com-puting equips terminal system with decision-making
tory. Therefore, it is necessary to improve the intelligence ability and autonomy. Additionally, high transmission rate of
level of manufacturing equipment. The con gurable con- data, low duty cycle, and IP network availability are the
troller and self-recon gurable robots can provide potential require-ments of network layer which denote the foundation
solutions to function expansion of manufacturing units. In for ubiquitous communication in smart factory.
the context of hybrid production, the coordination and
informa-tion interaction among the multi-module C. KNOWLEDGE-DRIVEN MANUFACTURING
manufacturing units should be explored. The optimized The large amount of manufacturing data provides a com-
combination of programs should be made to enhance the prehensive description of the smart factory, but manufactur-
workshop ef ciency. The intelligent equipment should be ing data cannot be utilized directly due to high dimension,
able to collect production information, provide compatible variable metric, and high noise. Consequently, it is impor-
data interface, and support generic communication protocol. tant to de ne the data semantic through the manufacturing
In addition, the equipment could perceive manufacturing glossary. The domain ontology provides a potential solution
environment and cooperate with other equipment in smart to data semantic for data application. Using the big data of
factory. Flexible manufactur-ing is a typical feature of smart intelligent manufacturing, the active maintenance of equip-
factory, but there are still many problems such as strong ment, the optimization design for manufacturing product,
proprietary of production line, dynamic scheduling, and tight and the optimization of production line is achieved in the
coupling between functions and devices. smart factory. The knowledge-driven manufacturing brings
In the context of intelligent manufacturing, the data opportunities to transformation from traditional industry to
generated by intelligent equipment is mostly unstructured. intelligent industry, meanwhile the data mining technology is

VOLUME 6, 2018 6515

 B. Chen et al.: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges

a serious challenge to enterprises. Moreover, the data- [7] J. Zhou, ‘‘Intelligent manufacturing-main direction of ‘Made in China
based optimization of product design needs to add data 2025,’’’ China Mech. Eng., vol. 26, no. 17, pp. 2273 2284, 2015.
[8] J. P. Holdren, T. Power, G. Tassey, A. Ratcliff, and L. Christodoulou, ‘‘A
receiver and feedback mechanism to the traditional National strategic plan for advanced manufacturing,’’ US Nat. Sci. Technol.
product, and then the product itself will become the data Council, Washington, DC, USA, Tech. Rep., 2012. [Online]. Available:
source. Consequently, the product will become a http://www.docin.com/p-391856652.html
[9] J. Wan, M. Yi, D. Li, C. Zhang, S. Wang, and K. Zhou, ‘‘Mobile
participant in the process of data col-lection, which services for customization manufacturing systems: An example of
provides technical information to the product designer. industry 4.0,’’ IEEE Access, vol. 4, pp. 8977 8986, 2016.
In order to achieve a knowledge-based intelligent manu- [10] N. Benkamoun, W. ElMaraghy, A.-L. Huyet, and K. Kouiss, ‘‘Architecture
framework for manufacturing system design,’’ Procedia CIRP, vol. 17,
facturing, the manufacturing entity should be able to provide pp. 88 93, 2014.
data collection, data fusion, and extraction of manufacturing [11] A. Radziwon, A. Bilberg, M. Bogers, and E. S. Madsen, ‘‘The smart
resource characteristics. The smart factory should integrate fac-tory: Exploring adaptive and exible manufacturing solutions,’’
Procedia Eng., vol. 69, pp. 1184 1190, Jan. 2014.
data resources (e.g., supply chains, product data, and logistic [12] J. Lin et al., ‘‘Application technology of cloud manufacturing for aerospace
data) into service platform, which provides product services complex products,’’ Comput. Integr. Manuf. Syst., vol. 22, no. 4,
pp. 883 896, 2016.
such as sales forecasting and quality analysis. In general, data
mining and knowledge discovery provide a scienti c decision for [13]J. Wan, S. Tang, Q. Hua, D. Li, C. Liu, and J. Lloret, ‘‘Context-
aware cloud robotics for material handling in cognitive industrial Inter-net
planning and scheduling of manufacturing product. of Things,’’ IEEE Internet Things J., to be published, doi: 10.1109/
JIOT.2017.2728722.2017.
VIII. CONCLUSIONS [14] J. Wan, S. Tang, H. Yan, D. Li, S. Wang, and A. V. Vasilakos, ‘‘Cloud
robotics: Current status and open issues,’’ IEEE Access, vol. 4,
The smart factory is an intelligent production system which pp. 2797 2807, 2016.
utilizes the integration of manufacturing and services. It inte- [15] Y. Lyu and J. Zhang, ‘‘Big-data-based technical framework of
grates communication process, computing process, and con- smart factory,’’ Comput. Integr. Manuf. Syst., vol. 22, no. 11, pp. 2691
2697, 2016.
trol process to meet the industrial demands. In this paper, we [16] D. Zhang, J. Wan, C.-H. Hsu, and A. Rayes, ‘‘Industrial
proposed the hierarchical architecture of smart factory technologies and applications for the Internet of Things,’’ Comput.
according to the newly research. Then the main issues of key Netw., vol. 101, pp. 1 4, Jun. 2016.
[17] Z. Shu, J. Wan, D. Zhang, and D. Li, ‘‘Cloud-integrated cyber-
technologies involved in the physical resource layer, the physical systems for complex industrial applications,’’ Mobile Netw.
network layer, and the data application layer in the smart Appl., vol. 21, no. 5, pp. 865 878, 2016.
factory are analyzed, and some application cases were dis- [18] M. FiaschØ, G. Ripamonti, F. G. Sisca, M. Taisch, and A. A. Valente,
‘‘Man-agement integration framework in a shop- oor employing self-contained
cussed to explore potential solutions for key technologies. assembly unit for optoelectronic products,’’ in Proc. IEEE 1st Int. Forum Res.
Finally we established veri cation platform by means of the Technol. Soc. Ind. Leveraging Better Tomorrow (RTSI), Turin, Italy, Sep.
2015, pp. 569 578.
proposed key technologies, which showed that the OEE ration
[19] B. Piranda and J. Bourgeois, ‘‘A distributed algorithm for recon
is improved. The compound talents and multi- eld coopera-tion gura-tion of lattice-based modular self-recon gurable robots,’’ in Proc.
is required for the implementation of smart factory. The 24th Euromicro Int. Conf. Parallel, Distrib., Netw.-Based Process.
research of key technologies not only refers to the integration of (PDP), Heraklion, Greece, Feb. 2016, pp. 1 9.
[20] A. Valente, ‘‘Recon gurable industrial robots An integrated approach to
information technology as a main body, but also includes the design the joint and link modules and con gure the robot manipulator,’’ in
traditional disciplines such as control theory, mechanical Advances in Recon gurable Mechanisms and Robots II, vol. 36. Cham,
Switzerland: Springer, 2016, pp. 779 794.
technology, and materials and energy. As the big data tech-
[21] S. Wang, C. Zhang, and J. Wan, ‘‘A smart factory solution to hybrid
nology advances, the data-based virtual manufacturing mode production of multi-type products with reduced intelligence,’’ in Proc.
will improve product quality, increase production ef ciency, and IEEE Inf. Technol., Netw., Electron. Autom. Control Conf., Chongqing,
China, May 2016, pp. 848 853.
reduce energy consumption. Furthermore, the intelligent
[22] S. Wang, J. Wan, D. Zhang, D. Li, and C. Zhang, ‘‘Towards smart
manufacturing based on big data will lead to the revolution of fac-tory for Industry 4.0: A self-organized multi-agent system with big
traditional industry. data based feedback and coordination,’’ Comput. Netw., vol. 101, pp.
158 168, Jun. 2016.
[23] W. Dai, V. Vyatkin, J. H. Christensen, and V. N. Dubinin, ‘‘Bridging service-
oriented architecture and IEC 61499 for exibility and interoper-ability,’’ IEEE Trans.
REFERENCES Ind. Informat., vol. 11, no. 3, pp. 771 781, Jun. 2015.
[24] M. G. Valls, I. R. Lopez, and L. F. Villar, ‘‘ILAND: An enhanced middle-ware
[1] M. Brettel, N. Friederichsen, M. Keller, and M. Rosenberg, ‘‘How for real-time recon guration of service oriented distributed real-time systems,’’ IEEE
virtu-alization, decentralization and network building change the Trans. Ind. Informat., vol. 9, no. 1, pp. 228 236, Feb. 2013.
manufacturing landscape: An industry 4.0 perspective,’’ Int. J. Mech., [25] M. Short and K. Burn, ‘‘A generic controller architecture for intelli-gent
Ind. Sci. Eng., vol. 8, no. 1, pp. 37 44, 2014. robotic systems,’’ Robot. Comput.-Integr. Manuf., vol. 27, no. 2,
[2] F. Li, J. Wan, P. Zhang, D. Li, D. Zhang, and K. Zhou, ‘‘Usage-speci c pp. 292 305, 2011.
semantic integration for cyber-physical robot systems,’’ ACM Trans. [26] L. Morales-Velazquez, R. de J. Romero-Troncoso, R. A. Osornio-Rios,
Embedded Comput. Syst., vol. 15, no. 3, 2016, Art. no. 50. G. Herrera-Ruiz, and E. Cabal-Yepez, ‘‘Open-architecture system based on a
[3] J. Wan, D. Zhang, Y. Sun, K. Lin, C. Zou, and H. Cai, ‘‘VCMIA: A novel recon gurable hardware software multi-agent platform for CNC machines,’’ J.
architecture for integrating vehicular cyber-physical systems and mobile cloud Syst. Archit., vol. 56, no. 9, pp. 407 418, 2010.
computing,’’ Mobile Netw. Appl., vol. 19, no. 2, pp. 153 160, 2014. [27] W. Lepuschitz, A. Zoitl, M. VallØe, and M. Merdan, ‘‘Toward self-
[4] J. Wan, H. Yan, D. Li, K. Zhou, and L. Zeng, ‘‘Cyber-physical recon guration of manufacturing systems using automation agents,’’
systems for optimal energy management scheme of autonomous IEEE Trans. Syst., Man, Cybern. C, Appl. Rev., vol. 41, no. 1, pp. 52 69,
electric vehicle,’’ Comput. J., vol. 56, no. 8, pp. 947 956, 2013. Jan. 2011.
[5] Europe 2020: A Strategy for Smart, Sustainable and Inclusive [28] M. Adamski and J. Tkacz, ‘‘Formal reasoning in logic design of
Growth, European Commission, Brussels, Belgium, 2010. recon-gurable controllers,’’ IFAC Proc. Volumes, vol. 45, no. 7, pp. 1 6,
[6] H. Lasi, P. Fettke, H.-G. Kemper, T. Feld, and M. Hoffmann, ‘‘Industry 2012.
4.0,’’ Bus. Inf. Syst. Eng., vol. 6, no. 4, pp. 239 242, 2014.
VOLUME 6, 2018
6516
B. Chen et al.: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges

[29] H. J. Kim, Y. K. Lee, Y. A. Jeon, and J. Y. Son, ‘‘ICT convergence- [52] P. Leitªo, V. Marík, and P. Vrba, ‘‘Past, present, and future of indus-trial
based application service development to support the re-con gurability of agent applications,’’ IEEE Trans. Ind. Informat., vol. 9, no. 4,
door trim assembly line,’’ in Proc. Int. Conf. Inf. Commun. Technol. Converg. pp. 2360 2372, Nov. 2013.
(ICTC), Jeju, South Korea, Oct. 2016, pp. 1126 1128. [53] A. Girbea, C. Suciu, S. Nechifor, and F. Sisak, ‘‘Design and
[30] E. Järvenpää, N. Siltala, and M. Lanz, ‘‘Formal resource and implemen-tation of a service-oriented architecture for the optimization of
capability descriptions supporting rapid recon guration of assembly industrial applications,’’ IEEE Trans. Ind. Informat., vol. 10, no. 1, pp.
systems,’’ in Proc. IEEE Int. Symp. Assembly Manuf. (ISAM), Fort 185 196, Feb. 2014.
Worth, TX, USA, Aug. 2016, pp. 120 125. [54] A. Fernbach, W. Kastner, S. Mätzler, and M. Wollschlaeger, ‘‘An
[31] D. Gyulai, B. KÆdÆr, A. KovÆcs, and L. Monostori, ‘‘Capacity OPC UA information model for cross-domain vertical integration in
management for assembly systems with dedicated and recon gurable automation sys-tems,’’ in Proc. IEEE Emerg. Technol. Factory Autom.
resources,’’ CIRP Ann., vol. 63, no. 1, pp. 457 460, 2014. (ETFA), Barcelona, Spain, Sep. 2014, pp. 1 8.
[32] K. K. Goyal and P. K. Jain, ‘‘Design of recon gurable ow lines [55] Z. Shu et al., ‘‘Traf c engineering in software-de ned networking: Mea-
using MOPSO and maximum deviation theory,’’ Int. J. Adv. Manuf. surement and management,’’ IEEE Access, vol. 4, pp. 3246 3256, 2016.
Technol., vol. 84, nos. 5 8, pp. 1587 1600, 2016. [56] J. Liu, J. Wan, B. Zeng, Q. Wang, H. Song, and M. Qiu, ‘‘A
[33] D. Zhang, Y. Qian, J. Wan, and S. Zhao, ‘‘An ef cient RFID search scalable and quick-response software de ned vehicular network assisted
protocol based on clouds,’’ Mobile Netw. Appl., vol. 20, no. 3, by mobile edge computing,’’ IEEE Commun. Mag., vol. 55, no. 7, pp. 94
pp. 356 362, 2015. 100, Jul. 2017.
[34] R. Y. Zhong, Q. Y. Dai, T. Qu, G. J. Hu, and G. Q. Huang, ‘‘RFID- [57] Y. Li and M. Chen, ‘‘Software-de ned network function virtualization: A
enabled real-time manufacturing execution system for mass- survey,’’ IEEE Access, vol. 3, pp. 2542 2553, 2015.
customization production,’’ Robot. Comput.-Integr. Manuf., vol. 29, no. [58] J. Liu, Q. Wang, J. Wan, J. Xiong, and B. Zeng, ‘‘Towards key
2, pp. 283 292, 2013. issues of disaster aid based on wireless body area networks,’’ KSII
[35] D. Zhang, Z. He, Y. Qian, J. Wan, D. Li, and S. Zhao, ‘‘Revisiting Trans. Internet Inf. Syst., vol. 7, no. 5, pp. 1014 1035, 2013.
unknown RFID tag identi cation in large-scale Internet of Things,’’ IEEE [59] N. Bizanis and F. A. Kuipers, ‘‘SDN and virtualization solutions for the
Wireless Commun., vol. 23, no. 5, pp. 24 29, Oct. 2016. Internet of Things: A survey,’’ IEEE Access, vol. 4, pp. 5591 5606, 2016.
[36] V. Coskun, B. Ozdenizci, and K. Ok, ‘‘A survey on near eld commu- [60] J. Wan et al., ‘‘Software-de ned industrial Internet of Things in the
nication (NFC) technology,’’ Wireless Pers. Commun., vol. 71, no. 3, con-text of industry 4.0,’’ IEEE Sensors J., vol. 16, no. 20, pp. 7373
pp. 2259 2294, 2013. 7380, Oct. 2016.
[37] S. Choudhury, P. Kuchhal, R. Singh, and Anita, ‘‘ZigBee and [61] Flowgrammable: Driving the Next SDN Generation. Accessed:
Bluetooth network based sensory data acquisition system,’’ Procedia Jul. 15, 2015. [Online]. Available: http:// owgrammable.org/
Comput. Sci., vol. 48, pp. 367 372, Jan. 2015. sdn/open ow/
[38] M. Chen, Y. Ma, Y. Li, D. Wu, Y. Zhang, and C.-H. Youn, ‘‘Wearable [62] The ONF is an Operator Led Consortium. Accessed: Jun. 21, 2017.
2.0: Enabling human-cloud integration in next generation healthcare [Online]. Available: http://www.opennetworking.org
systems,’’ IEEE Commun. Mag., vol. 55, no. 1, pp. 54 61, Jan. 2017. [63] K. Lin, W. Wang, X. Wang, W. Ji, and J. Wan, ‘‘QoE-driven spec-
[39] R. A. Gupta and M.-Y. Chow, ‘‘Networked control system: Overview trum assignment for 5g wireless networks using SDR,’’ IEEE Wireless
and research trends,’’ IEEE Trans. Ind. Electron., vol. 57, no. 7, Commun., vol. 22, no. 6, pp. 48 55, Dec. 2015.
pp. 2527 2535, Jul. 2010. [64] S. Das, G. Parulkar, and N. McKeown, ‘‘Why OpenFlow/SDN can suc-
[40] T. Sauter, ‘‘The three generations of eld-level networks Evolution and ceed where GMPLS failed,’’ in Proc. Eur. Conf. Exhib. Opt. Commun.,
compatibility issues,’’ IEEE Trans. Ind. Electron., vol. 57, no. 11, Amsterdam, Netherlands, Sep. 2012, pp. 1 3, paper Tu.1.D.1.
pp. 3585 3595, Nov. 2010. [65] Z. Shu, J. Wan, D. Li, J. Lin, A. V. Vasilakos, and M. Imran, ‘‘Security in
[41] X. Li, D. Li, J. Wan, A. V. Vasilakos, C.-F. Lai, and S. Wang, ‘‘A software-de ned networking: Threats and countermeasures,’’ Mobile Netw.
review of industrial wireless networks in the context of industry 4.0,’’ Appl., vol. 21, no. 5, pp. 764 776, 2016.
Wireless Netw., vol. 23, no. 1, pp. 23 41, 2017. [66] M. Chen, J. Wan, S. Gonzalez, X. Liao, and V. C. M. Leung, ‘‘A survey
[42] C. Zou, J. Wan, M. Chen, and D. Li, ‘‘Simulation modeling of cyber- of recent developments in home M2M networks,’’ IEEE Commun. Surveys
physical systems exempli ed by unmanned vehicles with WSNs navi-gation,’’ Tuts., vol. 16, no. 1, pp. 98 114, 1st Quart., 2014.
in Proc. 7th Int. Conf. Embedded Multimedia Comput. Technol. Service, [67] L. Kong, D. Zhang, Z. He, Q. Xiang, J. Wan, and M. Tao, ‘‘Embracing big
Gwangju, South Korea, Sep. 2012, pp. 269 275. data with compressive sensing: A green approach in industrial wireless networks,’’
[43] J. Niu, L. Cheng, Y. Gu, L. Shu, and S. K. Das, ‘‘R3E: Reliable IEEE Commun. Mag., vol. 54, no. 10, pp. 53 59, Oct. 2016.
reactive routing enhancement for wireless sensor networks,’’ IEEE [68] B. Holfeld et al., ‘‘Wireless communication for factory automation: An
Trans. Ind. Informat., vol. 10, no. 1, pp. 784 794, Feb. 2014. opportunity for LTE and 5G systems,’’ IEEE Commun. Mag., vol. 54, no. 6,
[44] F. Dobslaw, T. Zhang, and M. Gidlund, ‘‘End-to-end reliability- pp. 36 43, Jun. 2016.
aware scheduling for wireless sensor networks,’’ IEEE Trans. Ind. [69] J. Liu et al., ‘‘High-ef ciency urban traf c management in context-aware
Informat., vol. 12, no. 2, pp. 758 767, Apr. 2016. computing and 5G communication,’’ IEEE Commun. Mag., vol. 55, no. 1,
[45] D. Zhang, J. Wan, Q. Liu, X. Guan, and X. Liang, ‘‘A taxonomy of pp. 34 40, Jan. 2017.
agent technologies for ubiquitous computing environments,’’ KSII Trans. [70] N. K. Pratas and P. Popovski. (2013). ‘‘Low-rate machine-type
Internet Inf. Syst., vol. 6, no. 2, pp. 547 565, 2012. commu-nication via wireless device-to-device (D2D) links.’’ [Online].
[46] Y. Gao, W. Dong, L. Deng, C. Chen, and J. Bu, ‘‘COPE: Improving Available: https://arxiv.org/abs/1305.6783
energy ef ciency with coded preambles in low-power sensor networks,’’ IEEE [71] M. Bagaa, A. Ksentini, T. Taleb, R. Jantti, A. Chelli, and I.
Trans. Ind. Informat., vol. 11, no. 6, pp. 1621 1630, Dec. 2015. Balasingham, ‘‘An ef cient D2D-based strategies for machine type
[47] J. Lee, L. Kim, and T. Kwon, ‘‘Flexicast: Energy-ef cient software integrity communications in 5G mobile systems,’’ in Proc. IEEE Wireless
checks to build secure industrial wireless active sensor networks,’’ IEEE Trans. Ind. Commun. Netw. Conf. (WCNC), Doha, Qatar, Apr. 2016, pp. 1 6.
Informat., vol. 12, no. 1, pp. 6 14, Feb. 2016. [72] C.-H. Yu, K. Doppler, C. B. Ribeiro, and O. Tirkkonen, ‘‘Resource
[48] J. Luo, J. Hu, D. Wu, and R. Li, ‘‘Opportunistic routing algorithm for shar-ing optimization for device-to-device communication underlaying
relay node selection in wireless sensor networks,’’ IEEE Trans. Ind. cellular networks,’’ IEEE Trans. Wireless Commun., vol. 10, no. 8, pp.
Informat., vol. 11, no. 1, pp. 112 121, Feb. 2015. 2752 2763, Aug. 2011.
[49] L. Sun, P. Ren, Q. Du, and Y. Wang, ‘‘Fountain-coding aided strat- [73] W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, ‘‘Edge computing: Vision and
egy for secure cooperative transmission in industrial wireless sensor challenges,’’ IEEE Internet Things J., vol. 3, no. 5, pp. 637 646, Oct. 2016.
networks,’’ IEEE Trans. Ind. Informat., vol. 12, no. 1, pp. 291 300, Feb. [74] A. V. Dastjerdi, H. Gupta, R. N. Calheiros, S. K. Ghosh, and R.
2016. Buyya. (2016). ‘‘Fog computing: Principles, architectures, and
[50] Y. Zou and G. Wang, ‘‘Intercept behavior analysis of industrial wireless applications.’’ [Online]. Available: https://arxiv.org/abs/1601.02752
sensor networks in the presence of eavesdropping attack,’’ IEEE Trans. Ind. [75] M. S. De Brito, S. Hoque, R. Steinke, and A. Willner, ‘‘Towards pro-
Informat., vol. 12, no. 2, pp. 780 787, Apr. 2016. grammable fog nodes in smart factories,’’ in Proc. IEEE Int. Workshops
[51] W. Dong and X. Liu, ‘‘Robust and secure time-synchronization Found. Appl. Self Syst., Augsburg, Germany, Sep. 2016, pp. 236 241.
against sybil attacks for sensor networks,’’ IEEE Trans. Ind. Informat., [76] J. Pizo« and J. Lipski, ‘‘Perspectives for fog computing in
vol. 11, no. 6, pp. 1482 1491, Dec. 2015. manufacturing,’’ Appl. Comput. Sci., vol. 12, no. 3, pp. 37 46, 2016.

VOLUME 6, 2018 6517

 B. Chen et al.: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges

[77] D. Georgakopoulos, P. P. Jayaraman, M. Fazia, M. Villari, and R. Ranjan, JIAFU WAN (M’11) has been a Professor with the
‘‘Internet of Things and edge cloud computing roadmap for manufactur-ing,’’ IEEE School of Mechanical and Automotive Engi-
Cloud Comput., vol. 3, no. 4, pp. 66 73, Jul. 2016. neering, South China University of Technology,
[78] P. Shvaiko and J. Euzenat, ‘‘Ontology matching: State of the art since 2015. He has directed 16 research projects,
and future challenges,’’ IEEE Trans. Knowl. Data Eng., vol. 25, no. 1, including the National Key Research and Develop-
pp. 158 176, Jan. 2013. ment Project, the National Natural Science Foun-
[79] N. Chungoora et al., ‘‘A model-driven ontology approach for dation of China, the High-level Talent Project of
manufactur-ing system interoperability and knowledge sharing,’’ Guangdong Province, and the Natural Science
Comput. Ind., vol. 64, no. 4, pp. 392 401, 2013.
Foundation of Guangdong Province. Thus far, he
[80] Z. Usman, R. I. M. Young, N. Chungoora, C. Palmer, K. Case, and
has published over 140 scienti c papers, includ-
J. A. Harding, ‘‘Towards a formal manufacturing reference ontology,’’
Int. J. Prod. Res., vol. 51, no. 22, pp. 6553 6572, 2013. ing over 80 SCI-indexed papers, over 20 IEEE transactions/journal papers,
[81] T. Wang, S. Guo, and C.-G. Lee, ‘‘Manufacturing task semantic 12 ESI Highly Cited Papers, and 4 ESI Hot Papers. His research inter-ests
model-ing and description in cloud manufacturing system,’’ Int. J. Adv. include cyber-physical systems, industry 4.0, smart factory, indus-trial big
Manuf. Technol., vol. 71, nos. 9 12, pp. 2017 2031, 2014. data, industrial robot and Internet of Vehicles. His research results have been
[82] Y. Alsa and V. Vyatkin, ‘‘Ontology-based recon guration agent for published in several famous journals, such as the IEEE T RANSACTIONS ON
intel-ligent mechatronic systems in exible manufacturing,’’ Robot. INDUSTRIAL INFORMATICS, the IEEE COMMUNICATIONS SURVEYS
Comput.-Integr. Manuf., vol. 26, no. 4, pp. 381 391, 2010. AND TUTORIALS, the IEEE Communications Magazine, the IEEE TRANSACTIONS
[83] X. Chang, R. Rai, and J. Terpenny, ‘‘Development and utilization ON INTELLIGENT TRANSPORTATION SYSTEMS, the IEEE Network, the IEEE WIRELESS
of ontologies in design for manufacturing,’’ J. Mech. Des., vol. 132, no. COMMUNICATIONS, the IEEE SYSTEMS JOURNAL, the IEEE SENSORS JOURNAL, the IEEE
2, p. 021009, 2010. INTERNET OF THINGS JOURNAL, and the ACM Transac-
[84] J.-F. Wan, D. Li, H.-H. Yan, and P. Zhang, ‘‘Fuzzy feedback scheduling tions on Embedded Computing Systems. He is a Senior Member of CMES
algorithm based on central processing unit utilization for a software-based
and CCF. He is the General Chair of the 2016 International Confer-ence on
computer numerical control system,’’ Proc. Inst. Mech. Eng., B, J. Eng.
Industrial IoT Technologies and Applications and the 7th EAI International
Manuf., vol. 224, no. 7, pp. 1133 1143, 2010.
Conference on Cloud Computing (CloudComp 2016). He is currently an
[85]Z. Song, Y. Sun, J. Wan, and P. Liang, ‘‘Data quality management Associate Editor for the IEEE ACCESS and on the Editorial Board of PLOS One.
for service-oriented manufacturing cyber-physical systems,’’ Comput. He is also a Managing Editor for the International Journal of Autonomous and
Elect. Eng., vol. 64, pp. 34 44, Nov. 2017, doi: 10.1016/j.compeleceng.
Adaptive Communications Systems and the International Journal of Arts and
2016.08.010.2016.
Technology and a Leading Guest Edi-tor for several SCI-indexed journals,
[86] W. Yuan, P. Deng, T. Taleb, J. Wan, and C. Bi, ‘‘An unlicensed taxi
iden-ti cation model based on big data analysis,’’ IEEE Trans. Intell. such as the IEEE S YSTEMS JOURNAL, the IEEE ACCESS, the Computer Networks
Transp. Syst., vol. 17, no. 6, pp. 1703 1713, Jun. 2016. (Elsevier), the Mobile Net-works and Applications, the Computers and
Electrical Engineering, and the Microprocessors and Microsystems.
[87]Y. Xu, Y. Sun, J. Wan, X. Liu, and Z. Song, ‘‘Industrial big data for fault
According to Google Scholar, his published work has been cited over 3800
diagnosis: Taxonomy, review, and applications,’’ IEEE Access, to be
published, doi: 10.1109/ACCESS.2017.2731945.2017. times (H-index D 31). His SCI other citations (sum of times cited without self-
[88] J. Wan et al., ‘‘A manufacturing big data solution for active citations) reached 1104 (H-index D 19) times according to Web of Science
preventive maintenance,’’ IEEE Trans. Ind. Informat., vol. 13, no. 4, pp. Core Collection.
2039 2047, Aug. 2017.
LEI SHU (SM’16) is currently a Lincoln Profes-sor with
[89] I. Regev and D. Benson-Karhi, ‘‘Segmentation models for the duration
the University of Lincoln, U.K., and a Distinguished
of expected preventive maintenance in semiconductor fabs,’’ IEEE Trans.
Semicond. Manuf., vol. 29, no. 3, pp. 223 229, Aug. 2016. Professor with Nanjing Agricultural University, China.
[90] H. M. Hashemian and W. C. Bean, ‘‘State-of-the-art predictive He is also the Director of the NAU-Lincoln Joint
main-tenance techniques,’’ IEEE Trans. Instrum. Meas., vol. 60, no. 10, Research Center of Intelligent Engineering. He has
pp. 3480 3492, Oct. 2011. authored over 350 papers in related conferences,
journals, and books in the area of sensor networks. His
[91]J. Xiong, Q. Zhang, J. Wan, L. Liang, P. Cheng, and Q. Liang, ‘‘Data fusion main research eld is wireless sensor networks. He was
method based on mutual dimensionless,’’ IEEE/ASME Trans. Mechatronics, to be
a recipient of the GlobeCom 2010 and ICC 2013 Best
published, doi: 10.1109/TMECH.2017.2759791.2017.
Paper Award
[92] L. Graening and B. Sendhoff, ‘‘Shape mining: A holistic data
mining approach for engineering design,’’ Adv. Eng. Informat., vol. 28, and the IEEE Systems Journal 2017 Best Paper Award. He has served
no. 2, pp. 166 185, 2014. as a TPC member for over 150 conferences, such as ICDCS, DCOSS,
[93] J. W. Williams et al., ‘‘Semantics for big data access & integration: MASS, ICC, GlobeCom, ICCCN, WCNC, and ISCC. He has also served
Improving industrial equipment design through increased data usability,’’ as the Co-Chair for over 50 international conferences and workshops,
in Proc. IEEE Int. Conf. Big Data (Big Data), Santa Clara, CA, USA, such as IWCMC, ICC, ISCC, ICNC, and Chinacom, the Symposium Co-
Oct./Nov. 2015, pp. 1103 1112. Chair for IWCMC 2012 and ICC 2012, the General Co-Chair for
[94] J. K. Bae and J. Kim, ‘‘Product development with data mining Chinacom 2014, Qshine 2015, CollaborateCom 2017, and Mobiquitous
techniques: A case on design of digital camera,’’ Expert Syst. Appl., vol. 2018, and as the Steering Chair and the TPC Chair for InisCom 2015.
38, no. 8, pp. 9274 9280, 2011. He has been serving as an Editor-in-Chief for the EAI endorsed
[95]S. Wang, J. Wan, D. Li, and C. Zhang, ‘‘Implementing smart factory of Transactions on Industrial Networks and Intelligent Systems and as an
industrie 4.0: An outlook,’’ Int. J. Distrib. Sensor Netw., vol. 2016, Jan. 2016, Associate Editor for the IEEE T RANSACTIONS ON INDUSTRIAL INFORMATICS, the IEEE
Art. no. 3159805, doi: 10.1155/2016/3159805. Communications Magazine, the IEEE SYSTEMS JOURNAL, and the IEEE ACCESS.
[96]S. Wang, J. Wan, M. Imran, D. Li, and C. Zhang, ‘‘Cloud-based smart
man-ufacturing for personalized candy packing application,’’ J. Supercomput., PENG LI received the bachelor’s and master’s
to be published, doi: 10.1007/s11227-016-1879-4.2016. degrees in process automation from the Technical
University of Dresden, Germany, in 2013. He is
BAOTONG CHEN received the B.A. degree in currently a Research Assistant with the Institute
mechanical engineering from the Nanyang Insti- Industrial IT, Ostwestfalen-Lippe University of
tute of Technology, China, 2014. He is currently Applied Science, Lemgo, Germany. His research
pursuing the Ph.D. degree with the School of focuses on machine learning, data mining, infor-
Mechanical and Automotive Engineering, South mation modeling, and their application in the cyber-
China University of Technology, China. His physical-production-systems.
research interests include cyber-physical systems,
industrial wireless networks, Internet of Things,
and embedded control systems.

6518 VOLUME 6, 2018

B. Chen et al.: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges

MITHUN MUKHERJEE (S’10 M’16) received the BOXING YIN received the B.A. degree from the
B.E. degree in electronics and communication School of Electrical Engineering and
engineering from the University Institute of Tech- Automation, Zhejiang University of Science and
nology, Burdwan University, India, in 2007, the Technology, China, in 2016. He is currently
M.E. degree in information and communication pursuing the M.S. degree with the School of
engineering from the Indian Institute of Engineer- Jiangxi Electrical Engi-neering and Automation,
ing Science and Technology at Shibpur, Shibpur, University of Science and Technology of China,
India, in 2009, and the Ph.D. degree in electrical China. His research interests include industrial
engineering from IIT Patna, Patna, India, in 2015. big data and machine learning.
He is currently a specially assigned Researcher
with the Guangdong Provincial Key Lab of Petrochemical Equipment Fault
Diagnosis, Guangdong University of Petrochemical Technology, China. His
research interests include wireless sensor networks, wireless communica-
tions, energy harvesting, and fog computing. He was a recipient of the EAI
WICON 2016 and IEEE SigTelCom 2017 Best Paper Award. He was a Guest
Editor of the IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, the IEEE
ACCESS, the Mobile Networks and Applications (ACM/Springer), and the
Sensors. He has been serving as a Special Issue Editor for the EAI
endorsed Transactions on Industrial Networks and Intelligent Systems.

VOLUME 6, 2018 6519