=Paper=
{{Paper
|id=Vol-2404/paper05
|storemode=property
|title=Intelligent Agents Supporting Digital Factories
|pdfUrl=https://ceur-ws.org/Vol-2404/paper05.pdf
|volume=Vol-2404
|authors=Nicola Bicocchi,Giacomo Cabri,Letizia Leonardi,Giulio Salierno
|dblpUrl=https://dblp.org/rec/conf/woa/BicocchiCLS19
}}
==Intelligent Agents Supporting Digital Factories==
https://ceur-ws.org/Vol-2404/paper05.pdf
Workshop "From Objects to Agents" (WOA 2019)
Intelligent Agents Supporting Digital Factories
Nicola Bicocchi∗ , Giacomo Cabri∗ , Letizia Leonardi∗ , Giulio Salierno∗
∗ Università di Modena e Reggio Emilia, Italy,
{nicola.bicocchi, giacomo.cabri, letizia.leonardi, giulio.salierno}@unimore.it
Abstract—Intelligent agents represent a widely exploited digital factories as a key paradigm embracing multiple aspects
paradigm of the Distributed Artificial Intelligence (DAI). They related to the digitialization of factories.
have been applied in many fields, and recently they have appeared The rest of this paper is organized as follows. Section II
also in the digital factory field. Digital factories are abstractions of
real factories, which enable high-level management of factories’ presents the existing approaches that exploit intelligent agents
processes, along with their automatization. So, the real factories in digital factories, starting from some existing surveys re-
can dynamically adapt their processes to unexpected situations. lated to those topics (Section II-A). Section III discusses the
In this paper, we survey different works at the state of the presented approaches and reports the advantages and limita-
art that show how intelligent agents can support digital factories, tions of adopting agent-based technologies in digital factories.
along with the limitations of their application. A discussion about
the advantages of intelligent agents and the open issues completes
Finally, Section IV concludes the paper and sketches future
the paper. directions.
Index Terms—Intelligent Agents, Digital Factory, Industrial
IoT.
II. I NTELLIGENT AGENTS FOR D IGITAL FACTORIES
This section is devoted to present the work related to
I. I NTRODUCTION intelligent agents applied to the field of in digital factories.
Some surveys already exist and we summarize them for
Digital factories [1] represent a key enabling paradigm completeness’s sake (Subsection II-A). Then, we present the
for the next generation of smart manufacturing. Digital tech- existing approaches, divided into three subsections:
nologies promote the integration of traditional product design • Agent-based decentralized management
processes, manufacturing processes, and general collaborative • Agent-based data management
business processes in order to bridge the gap between design • Agent-based architectures
and manufacturing processes of a traditional factory [2]. To Of course, not all reported works fit perfectly in a category,
this end, the digital factory covers the entire product lifecycle but we think that this can be useful to have an idea about the
ranging from the product design stage down to product plan- topics addressed by the existing works.
ning and realization. The new wave of technologies that could
lead to the fourth industrial revolution, the so-called Industry A. Surveys in the Literature
4.0, is further multiplying the opportunities to get access to In the literature we can find some surveys of the researches
global supply and sale markets. related to the application of the AI technologies to the
Intelligent agents [3] are decentralized software components manufacturing field. we think that they can be useful to
that exhibit some main features, such as autonomy, reactiv- readers interested in the topic; nevertheless, the rest of the
ity, proactivity and sociality, which can be enhanced with paper will focus on intelligent agents (which can be conceived
other ones such as mobility and learning ability; all these as a specific AI technology) and digital factories (which can
features lead them to be “intelligent” in a Distributed Artificial be seen as an implementation of intelligent manufacturing).
Intelligence (DAI) fashion [4]. Thanks to these features, a
proper implementation adds flexibility to software systems and [7] presents a survey focusing on Multi-Agent Systems
applications thus leveraging the development of autonomous (MASs). As application field, it is limited to the manufacturing
systems [5], [6]. production, while our survey concern digital factories in
In this paper, we propose a survey of agent-based ap- general, which involve also other manufacturign aspects.
proaches in the digital factory field. Thanks to the previously The paper proposes a classification of the MAS into
mentioned features, intelligent agents have been considered in two main categories: centralized multi-agent coordination
the development of digital abstractions aiming at providing a and decentralized multi-agent coordination. The former
means to manage real factories and all the required interactions exploits a coordinator agent that manages all other agents
in a flexible way. and comprises a facilitator agent, which coordinate the
Some surveys have already been proposed [7], [8], [9] in the communication between agents, and a mediator agent,
field; we report about their results, but we point out that our which takes decisions on low-level aspects. In the latter
work is more specific on the one hand, because we focus on the category, agents have a high degree of autonomy, and thus
agent methodologies for the realization of digital factory tasks, the control is spread over all agents. The paper highlights the
and more general on the other hand, because we consider advantages of exploiting agents in manufacturing systems,
29
Workshop "From Objects to Agents" (WOA 2019)
mainly in terms of coordination of manufacturing components. them to sequence their plans of operation and to adjust the
timing of those manufacturing operations cooperatively. A
[8] presents a survey of technologies for Industry 4.0 frequent issue in manufacturing contexts consists, in fact, of
classifying previous works into five categories: jobs with rigid plans. Established approaches usually perform
• Concept and perspectives of Industry 4.0 conflict resolution in a way that forces involved agents to wait
• CPS-based Industry 4.0 until they are allowed to sequence and time the next operation.
• Interoperability of Industry 4.0 The assumption behind those approaches is removed in [11],
• Key technologies of Industry 4.0 thus allowing operations to be scheduled in parallel. More
• Applications of Industry 4.0 specifically, the authors discuss an innovative mechanism
The intelligent agents represent a future direction of enabling the emergence of manufacturer operation schedules
Cyber-Physical Systems (CPS) and also as a key technology from a generic collection of decentralized algorithms. This
at the base of several aspects such as products, orders, mechanism allows agents to independently sequence their
machine processes, controls; in addition, agents can provide operations with regard to their constraints while enabling
interoperability among the participants in the manufacturing cooperation.
product chain. As case studies for assessing the proposal, the MT6, MT10,
and LA19 job scheduling problems were used. Furthermore,
[9] discusses the use of agent-based methodologies in an industrial use case was detailed to provide context to
projects in the field of Cyber-Physical Production Systems the manufacturing environment under investigation. It has
(CPPS), which can be considered part of digital factories. Two been shown that agents could generate plans of operations
aspects are identified in order to classify the existing projects. by executing in parallel thus reducing the computation and
The former is the CPPS type, which can be one or more of communications efforts 10X and 5X respectively. It has also
the following: been found that the proposed family of algorithms are capable
of addressing disturbances such as delays and last rush jobs.
• Demonstrators
2) Decentralized and on-the-fly agent-based service re-
• Smart manufacturing approaches
configuration in manufacturing systems: The work reported
• Electric Grid applications
in [12] deals with the problem of service manufacturing recon-
• Architectures
figuration in industrial manufacturing systems. In this work,
The latter aspect considered is the ISA 95 levels [10], which the authors examined the service reconfiguration problem in
can be: a real-time constrained environment. In particular, concerning
• Device Level (L1) the physical equipment of the factory which reconfiguration
• Supervisory Control And Data Acquisition or SCADA is only possible when it satisfy timing requirements. To this
Level (L2) end, the author proposes a system for identifying dynamic
• Manufacturing Operations Management or MOM Level reconfiguration opportunities as well as the selection of the
(L3) best reconfiguration strategies to optimize productivity. The
• Enterprise or ERP Level (L4) proposed MAS consist of three-type of agents: Resource Agent
In addition, the authors define requirements for agent-based (RA) which encapsulate the physical operation of a machine
methodologies in order to be suitable for the development of as a service. Product Agent (PA) represents a service consumer
CPPS, as follows: and fulfill the production demand by creating new products.
• Minimal conditions PA and RA have different services reconfiguration needs.
• Intelligent characteristics attributes RA covers the changes of structure of a composed service
• Formalized modeling terms while PA focuses on changing the services catalog as well
• Systems and human integration needs as modification of their behavior. The MAS is enriched with
Starting from the above aspects, the authors classify the early detection of reconfiguration opportunities. To this end,
existing agent-based methodologies concluding that they have the detection of a reconfiguring phase is performed through
several attributes to meet the CPPS requirements, but some continuously collecting data and analyzing them to trigger
specific requirements still need attention from the developers; a reconfiguration opportunity (i.e., changing in a service,
in particular, they mention vertical integration, human inte- degradation of service performances, trend or pattern in a
gration, proactivity and abstraction. The lack of proactivity service performance). When an event is triggered, a set com-
and abstraction is surprising, because they are two of the prising possible service reconfiguration strategies is computed
main features of agents [3]. The other two features are instead by each agent. To reduce the space of strategies generated
expected and are worth being subject of future researches. by a single agent, a matching mechanism is proposed to
analyze the performance of a strategy in a given context.
B. Agent-based Decentralized Management The feasibility of a reconfiguration strategy is evaluated us-
1) Knowledge and agent-based system for decentralized ing the JENA framework which exploits semantic reasoning
scheduling in manufacturing: In [11], authors propose an about the logic of a solution to assess its applicability. In
innovative group of algorithms for agent systems allowing the end, an optimal reconfiguration strategy is selected by
30
Workshop "From Objects to Agents" (WOA 2019)
ranking feasible solutions using a multi-criteria function which entities. The negotiation takes place between an agent, elected
quantifies the benefit of adopting a strategy on the other. as a manager, and the other agents (named contractors). The
For a collaborative environment comprised of multi-agents, agent manager is capable of initiating new rounds and taking
an interaction protocol is proposed to ensure that a selected decisions based on the received messages sent by the agent
strategy is optimal for the whole system. The proposed service contractors.
reconfiguration approach is evaluated on a real-case scenario A typical negotiation involves the following steps: 1) A
of a manufacturing system comprised of five workstations manager initiates a new task. 2) Each contractor either send a
connected by a conveyor system. The results reported by the bid message to take part in a new round or a busy message.
authors demonstrate the benefit of a service reconfiguration Depending on received messages, the manager ranks bidders
mechanism with an increasing of the productivity. Moreover, according to a predefined set of layered rules. As an example,
the proposed interaction protocol shows the advantage of the task of finding a conveying path requires to determine the
distributing the service reconfiguration problem as the number next available hop of the route. In this scenario, the agent
of generated candidate strategies increase. manager will select the highest-ranked bidder as the winner
3) Potential of a Multi-Agent System Approach for Produc- of the negotiation, and it becomes the next hop of the path.
tion Control in Smart Factories: The paper [13] presents a Conditions of deadlock between multi-function and multi-
multi-agent framework for control, planning and scheduling occurrence agents are further examined, and a solution based
production autonomously and adaptively. The model is built on congestion control is presented. In contrast to other strate-
from real data of a production line of an automotive and then it gies (i.e., functional redundancy and replication of agents)
is simulated to evaluate the performance. Six types of agents which cannot guarantee deadlock prevention, the proposed
are defined to control the production, and in particular, the mechanism effectively prevent deadlock even if less efficient
supervisor agent communicates real-time information about compared to the other approaches.
the status of the product agents and machine agents. Based 2) Data-driven decision making for supply chain networks
on the received messages, the coordinator agent selects the with agent-based computational experiment: One of the key
machine that will perform the next job adopting a two-step issues in supply chain networks is decision making for solv-
decision rule. The decision rule takes into consideration the ing operational problems. Authors of [15] recognizing the
type of the task as well as the availability of a machine to importance of business analytics based on multi-dimensional
carry out the job. MAS performances are evaluated on four data and decision support systems, propose a data-driven
scenarios in which the model is compared with the traditional methodology for decision support in supply chain networks.
scheduler. An enhancement common to all the experiments is A four-dimensional-flow model is proposed to satisfy data
represented by the flexibility introduced by the MAS. requirements of decision-making. In this work, agents are
Thanks to the capability of assigning a priority value to the employed in a computational experiment to generates a com-
production of a batch and the ability to enqueue products for prehensive operational dataset of a supply chain thus verify the
delayed manufacturing, the production becomes more flexible solution produced in the decision making. In particular, a data-
compared to the traditional scheduling system. Additional driven decision-making framework for supply chain networks
experiments are further described in order to evaluate the is proposed, and two solutions based on business analytics
capabilities of the MAS to react to machines failures. The are put forward. The framework is evaluated on a real-
real-time communication between the coordinator agent and case scenario of a five-echelon manufacturing supply chain
the supervisor agent allows the system to be aware of machine network. In particular, results demonstrated the effectiveness
failures and react by assigning the task to the first non-faulty of the proposed four-dimensional-flow model in representing
machine. Finally, from a performance evaluation perspective, operations typical of supply chain networks. The agent-based
the MAS simulation help to focus not only on the scheduling computational experiment allowed to generate a comprehen-
efficiency but in general to the overall system performances in sive dataset but also to verify solution of decision making. The
particular cases where machines are added or removed from data-driven methodology presented offers a valuable tool for
the shop floor. the decision-making process into the supply chain domain.
3) Intelligent sustainable supplier selection using multi-
C. Agent-based Data Management agent technology: Theory and application for Industry 4.0
1) A self-organized multi-agent system with big database supply chains: Ghadimi et al. [16] analyze the problem of
feedback and coordination: Authors of [14] propose a concep- suppliers evaluation and selection for the management of sup-
tual smart factory framework based on a multi-agent system. ply chains (Scs) within the context of Industry 4.0. Although
The manufacturing shop floor is composed of four different the problem has been addressed before, sustainable supplier
categories of autonomous agents, which share common knowl- selection needs are further investigated to enhance green and
edge and communicate with each other to reach a system-wide lean Scs concepts into Industry 4.0. To this end, the authors
goal. In order to overcome limited decision capabilities of propose a MAS for sustainable supplier selection. The process
agents caused by poor knowledge of the environment in which of supplier evaluation conducted in their work is divided into
they act, a Contract Net Protocol mechanism is proposed to four steps as follows: i) Identification of components and
enhance cooperation and collaboration among the distributed products to be supplied. ii) Definition of impact factors of
31
Workshop "From Objects to Agents" (WOA 2019)
sustainability typically defined by manufacturer requirements agents. Each and every type of agent is focused on different
and then utilized during the supplier evaluation phase. iii) manufacturing-related functions. Agents use the most proper
Suppliers assessment is conducted via data gathered on the methods for communicating their internal reasoning data.
basis of manufacturer requirements. iv) Suppliers evaluation is Furthermore, a mechanism based on the cloud network has
based on a score which permits to evaluate their capabilities been introduced for coordinating the agents. For eliminating
in terms of sustainability. eventual local optima in the case of distributed scheduling,
The evaluation process is modeled as a MAS in which the cloud-assisted layer collects data from the lower layer and
negotiation takes place between a buyer (manufacturer) who defines the optimal scheduling policy through data analysis.
collaborate with multiple sellers (suppliers). The proposed These policies are fed back to the plants for assisted scheduling
architecture of the MAS is composed of three-layer named in form of suggestions.
as interface layer, technical layer, and data resource layer. Experimental results have shown that this architecture can
The interface layer allows both manufacturers and suppliers to be deployed to build smart manufacturing system with limited
update information utilized during the evaluation process. The efforts and can improve the capabilities of adaptation and
resource layer is comprised of the data management systems robustness of manufacturing system when dealing with multi-
which store both information provided by the manufacturers product problems. Finally, the results showed that the dynamic
and suppliers as well as the evaluation performance score scheduling policy proposed has clear advantages over more
of each supplier. The technical layer mediates between other traditional and static scheduling policies. In particular, CASOA
layers to retrieve data for the evaluation process of the sup- showed remarkable robustness and capacity of adaption to
pliers. The MAS developed by using the JADE framework frequent product changes and inferences to the production
consists of one container which will be ideally hosted by process.
a manufacturing company while other containers will be 2) An agent-based monitoring architecture for plug and
maintained by suppliers connected to the main container. produce based manufacturing systems: The article [18] pro-
Agents of different containers interact using a FIPA proto- poses a MAS architecture to support the monitoring of a
col to fulfill the evaluation process following a predefined shop floor in the case of dynamic entities join or leave
schema. Authors also introduce the designed evaluation model the system thus changing the network topology. The pro-
used by the decision-maker agent in order to periodically posed architecture is based on three different agents. A low-
evaluate the geographically dispersed suppliers. A FIS model level agent is responsible for abstracting a physical resource
is proposed to deal with uncertainty and lack of magnitude (CNC, machine, robot). At a higher level, the monitoring
of sustainability information. The evaluation of the data is agent abstracts low-level components to represent a high-
based on fuzzy set theory. To evaluate the sustainability of level subsystem. This agent receives data from both devices
the MAS an implementation of a real-case scenario regarding positioned on the field and lowest-layer agents. Finally, a
the medical sector is proposed. The scenario consists of one coordinator agent is responsible for monitoring the system
manufacturer providing electronic medical devices and nine behavior in terms of subsystems as well as single components.
suppliers producing different components. Results had shown A knowledge base containing a set of predefined rules allows
an improvement in terms of economic sustainability increase each agent to determine useful events to be aware of. Inter-
the performance evaluation score of suppliers. Therefore, this layer communication is based on CNP (Contract net Protocol)
information is propagated to the right supply chain member in and the Foundation for Intelligent Physical Agents (FIPA)
time. In conclusion, the developed MAS promote to enhance request protocol. The CNP protocol is used to perform task
sustainability among supply chain networks in the context of negotiation, while the FIPA protocol is adopted to establish
industry 4.0 by enabling interconnection among Scs, Real-time point-to-point communication between agents. This archi-
information, decentralization, and reduced human interaction. tecture presents a benefit in terms of enhanced monitoring
performances thanks to a decentralized analysis of the raw
D. Agent-based Architectures data. External components such as remote servers are involved
1) CASOA: An Architecture for Agent-Based Manufacturing in incrementing the computational capabilities and therefore
System in the Context of Industry 4.0: In [17], authors present processing a massive amount of data. The system results in
a self-organizing architecture making use of agents commu- better and accurate monitoring.
nicating and negotiating through a cloud network. Knowl- 3) Agent-based fault tolerant framework for manufacturing
edge is organized into representations based on ontologies process automation: Agent-based approaches are often used
for providing the basis for decision-making. Thus, agents for dealing with manufacturing-related disruptions regarding
can reconfigure their network in a prompt and collaborative machine faults. disruption of manufacturing processes, in fact,
way. Because the interactions among agents in distributed adversely affect productivity and efficiency while down times
systems are often difficult to be understood and predicted, affect the whole chain of value.
their interaction behaviour has been modeled as a hierarchical Widely used solutions to these issues are centralized and
structure. mostly focused on the detection and isolation of a particular
The architecture has been assembled around agents of disruption. Unfortunately, this kind of centralized approaches
four types: suggestion, product, machining, and conveying suffers of time lags between the moment in which data are
32
Workshop "From Objects to Agents" (WOA 2019)
analyzed and a response is generated. productivity; they cannot be disregarded by the digital
[19] proposes an alternative approach for mitigating dis- counterpart, and from this point of view intelligent agents
ruptions by deploying a fault tolerant framework based on may be inadequate to tackle them. This aspect must be
agent technologies. The technique is adopted for handling further investigated and deserves appropriate solutions.
fault detection and identification and for further investing the
root cause of the disruption. Once a disruption is identified, a IV. C ONCLUSIONS AND F UTURE W ORK
weight is assigned to it, and the eventual corrective mechanism In this paper, we analyzed the current trends in the im-
is executed. plementation of agent-based digital factories. As shown by
This agent-based model has been tested on an asphalt the mentioned works, the adoption agent-based architectures
manufacturing plant. Results showed a reduction in downtime optimize many of the tasks of traditional factories by exploting
around 5%. Additionally, 37% reduction in the number of agent characteristics. Although, the effectiveness of agents
failures has been noticed. This can lead to an increase of promotes a concrete support for the digitalization of traditional
about 5% in the overall productive activity. As a consequence, manufacturing tasks, the number of implementations in the
this method offers a promising opportunity for enhancing the industry is not significant; we think that this is due to the
overall efficiency of manufacturing plants when compared to limitations analyzed in the paper and briefly sketched in three
more traditional approaches. key points as follows:
1) Simplicity of agent interactions is required to have
III. S UMMARY systems easier to design and more controllable. This
The literature presents a small number of approaches in prerequisite is fundamental in order to keep as simple
which intelligent agents are applied to digital factories. The as possible the management of complex manufacturing
concept of digital factory can be found in different shapes, tasks and their integration.
among which Smart manufacturing, Industry 4.0, Cyber- 2) The involvement of humans [20] is an important aspect
Physical Production Systems, Smart factories; we consider when real factories are managed through digital abstrac-
them as sorts of “implementations” of the more general tions, thus human plays an active roles and therefore
concept of digital factory, but still very interesting also because must be considered as part of the digital processes.
they can propose different points of view. 3) Real-Time constraint in a MAS, need to be further
The survey of the approaches we have proposed highlights examined in order to fulfill timing requirements of
the advantages of applying intelligent agents in digital facto- tasks and services of IoT based digital factories. The
ries; the main ones turn out to be: enablement of a digital twin models in a digital factory
• Autonomy. Agents can manage the real factory reducing
requires real-time data exchange among the virtual and
the need for human intervention. the real factory. In this scenario, legacy manufacturing
• Adaptation. Agents can rely on different plans in order
systems must be integrated with high end manufacturing
to flexibly adapt to different situations. equipments IoT devices, robotic arms, and robots to en-
• Decentralization. Agents allow for scalable decentralized
able a flexible and transparent real-time communication.
solutions with neither bottlenecks nor single points of On the other side, the advantages of the application of agents
failure. in a digital factory are mainly related to autonomy, adaptation,
• Robustness. Agents can react to an unpredicted situation decentralization, and robustness. These advantages enable the
in a flexible way and grant reduction in the process applicability of the agent paradigm to the digital factory field
downtime. in order to fulfill various manufacturing tasks related to digital
factory lifecycle. With regard to future work, we point out
From our survey emerges that there are also some limi-
interoperability issues intra- and inter-factories since it is
tations; in particular, agent-based approaches can be further
a key issue that not only leverage the adoption of digital
improved in the following directions:
factories and its effectiveness [21], but also promotes the
• Simplicity. The autonomy of the agents leads to complex
enablement of new form of collaborations between enterprises.
interactions that could be difficult to define and manage; The interoperability challenges between digital factories can
this calls for a simpler means to enable the management be tackled through the adoption of agent-based systems.
of interactions, possible customized to the digital factories
field. This can increase the acceptance of intelligent ACKNOWLEDGMENT
agents in digital factories. This work has been supported by the European Commission
• Human integration. Despite the decreasing of human
through the H2020 project FIRST virtual Factories: Inter-
intervention, what emerges is that humans’ contribution operation suppoRting buSiness innovaTion (grant agreement
is still an important part of real factories, and their #734599).
involvement in the system (usually called “human in the
loop”) cannot be avoided in digital factories. R EFERENCES
• Real-Time. Several tasks in real factories are likely [1] U. Bracht and T. Masurat, “The digital factory between vision and
to have real-time constraints that influence the overall reality,” Computers in industry, vol. 56, no. 4, pp. 325–333, 2005.
33
Workshop "From Objects to Agents" (WOA 2019)
[2] T. Jianzhong, “Application status and prospects of digital factory,” “Potential of a multi-agent system approach for production control in
Innovation Technology, vol. 5, pp. 35 – 37, 2017. smart factories,” vol. 51, 06 2018, pp. 1459–1464.
[3] M. Wooldridge, An introduction to multiagent systems. John Wiley & [14] S. Wang, J. Wan, D. Zhang, D. Li, and C. Zhang, “Towards smart factory
Sons, 2009. for industry 4.0: A self-organized multi-agent system with big data based
[4] J. Ferber and G. Weiss, Multi-agent systems: an introduction to dis- feedback and coordination,” Computer Networks, vol. 101, 01 2016.
tributed artificial intelligence. Addison-Wesley Reading, 1999, vol. 1. [15] Q. Long, “Data-driven decision making for supply chain networks with
[5] C. Savaglio, G. Fortino, M. Ganzha, M. Paprzycki, C. Bădică, and agent-based computational experiment,” Knowledge-Based Systems, vol.
M. Ivanović, Agent-Based Computing in the Internet of Things: A 141, pp. 55–66, 2018.
Survey. Cham: Springer International Publishing, 2018, pp. 307–320. [16] P. Ghadimi, C. Wang, M. K. Lim, and C. Heavey, “Intelligent
[6] G. Fortino, W. Russo, C. Savaglio, W. Shen, and M. Zhou, “Agent- sustainable supplier selection using multi-agent technology: Theory and
oriented cooperative smart objects: From iot system design to implemen- application for industry 4.0 supply chains,” Computers and Industrial
tation,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, Engineering, vol. 127, pp. 588–600, 2019. [Online]. Available:
vol. 48, no. 11, pp. 1939–1956, Nov 2018. www.scopus.com
[7] G. Andreadis, P. Klazoglou, K. Niotaki, and K.-D. Bouzakis, “Classifi-
[17] H. Tang, D. Li, S. Wang, and Z. Dong, “Casoa: An architecture for
cation and review of multi-agents systems in the manufacturing section,”
agent-based manufacturing system in the context of industry 4.0,” IEEE
Procedia Engineering, vol. 69, pp. 282–290, 2014.
Access, vol. 6, pp. 12 746–12 754, 2018.
[8] Y. Lu, “Industry 4.0: A survey on technologies, applications and open
research issues,” Journal of Industrial Information Integration, vol. 6, [18] A. Dionisio Rocha, R. Peres, and J. Barata, “An agent based monitoring
pp. 1–10, 2017. architecture for plug and produce based manufacturing systems,” in 2015
[9] S. L. A. Cruz and B. Vogel-Heuser, “Comparison of agent oriented IEEE 13th International Conference on Industrial Informatics (INDIN),
software methodologies to apply in cyber physical production systems,” July 2015, pp. 1318–1323.
in 2017 IEEE 15th International Conference on Industrial Informatics [19] Z. A. Khan, M. T. Khan, I. Ul Haq, and K. Shah, “Agent-based fault
(INDIN). IEEE, 2017, pp. 65–71. tolerant framework for manufacturing process automation,” International
[10] Y. Lu, K. C. Morris, and S. Frechette, “Current standards landscape Journal of Computer Integrated Manufacturing, pp. 1–10, 2019.
for smart manufacturing systems,” National Institute of Standards and [20] D. Romero, J. Stahre, T. Wuest, O. Noran, P. Bernus, Å. Fast-Berglund,
Technology, NISTIR, vol. 8107, p. 39, 2016. and D. Gorecky, “Towards an operator 4.0 typology: a human-centric
[11] S. Saeidlou, M. Saadat, and G. D. Jules, “Knowledge and agent- perspective on the fourth industrial revolution technologies,” in Pro-
based system for decentralised scheduling in manufacturing,” Cogent ceedings of the International Conference on Computers and Industrial
Engineering, no. just-accepted, 2019. Engineering (CIE46), Tianjin, China, 2016, pp. 29–31.
[12] N. Rodrigues, E. Oliveira, and P. Leitão, “Decentralized and on-the-fly [21] N. Bicocchi, G. Cabri, F. Mandreoli, and M. Mecella, “Dealing with data
agent-based service reconfiguration in manufacturing systems,” Comput- and software interoperability issues in digital factories,” in Proceedings
ers in Industry, vol. 101, pp. 81–90, 2018. of the 25th International Conference on Transdisciplinary Engineering.
[13] M. Leusin, M. Kck, E. Frazzon, M. Uriona Maldonado, and M. Freitag, IOSpress, 7 2018.
34