Applications of agent-based systems in intelligent manufacturing: An updated review

doi:10.1016/j.aei.2006.05.004

Advanced Engineering Informatics

Volume 20, Issue 4, October 2006, Pages 415-431

https://doi.org/10.1016/j.aei.2006.05.004 Get rights and content

Abstract

Agent technology has been recognized as a promising paradigm for next generation manufacturing systems. Researchers have attempted to apply agent technology to manufacturing enterprise integration, enterprise collaboration (including supply chain management and virtual enterprises), manufacturing process planning and scheduling, shop floor control, and to holonic manufacturing as an implementation methodology. This paper provides an update review on the recent achievements in these areas, and discusses some key issues in implementing agent-based manufacturing systems such as agent encapsulation, agent organization, agent coordination and negotiation, system dynamics, learning, optimization, security and privacy, tools and standards.

Introduction

Global competition and rapidly changing customer requirements are forcing major changes in the production styles and configuration of manufacturing organizations. Increasingly, traditional centralized and sequential manufacturing process planning, scheduling, and control mechanisms are being found insufficiently flexible to respond to changing production styles and high-mix low-volume production environments. The traditional approaches limit the expandability and reconfigurability of the manufacturing systems. The centralized hierarchical organization may also result in much of the system being shut down by a single point of failure, as well as plan fragility and increased response overheads. Agent technology provides a natural way to address such problems, and to design and implement efficient distributed intelligent manufacturing systems.

The concept of a software agent can be traced back to Hewitt’s Actor Model aiming at solving large problems [55]. Recently, agent technology has been considered as an important approach for developing industrial distributed systems [60], [61]. It has particularly been recognized as a promising paradigm for next generation manufacturing systems [122], [123]. Researchers have attempted to apply agent technology to manufacturing enterprise integration, enterprise collaboration (including supply chain management and virtual enterprises), manufacturing process planning and scheduling, shop floor control, and to holonic manufacturing as an implementation methodology. Our previous survey paper [122] provides a review of the literature until 1998. This paper provides an update review on the recent achievements in these areas, and discusses some key issues in implementing agent-based intelligent manufacturing systems.

Section snippets

Requirements for next generation manufacturing systems

The manufacturing enterprises of the 21st century are in an environment where markets are frequently shifting, new technologies are continuously emerging, and competition is globally increasing. Manufacturing strategies should therefore shift to support global competitiveness, new product innovation and customization, and rapid market responsiveness. The next generation manufacturing systems will thus be more strongly time-oriented (or highly responsive), while still focusing on cost and

Agent-based systems for intelligent manufacturing

In this section we review some related projects, in a tabular format, giving for each item where available: project name, working group (in reference citation format), application domains and main features. The projects are classified into five categories: (1) enterprise integration; (2) enterprise collaboration (including supply chain management, virtual enterprises and other collaboration types); (3) manufacturing process planning and scheduling; (4) manufacturing shop floor control; and (5)

Key issues in implementing agent-based manufacturing systems

Key issues related to agent-based cooperative systems, such as representation, ontology management, agent structure, system architecture, communication, system dynamics, overall system control, conflict resolution, legacy systems integration and external interfaces, have been discussed in [123]. Most of these issues are also applicable in agent-based manufacturing systems. In this section, we discuss those key issues especially related to agent-based manufacturing according to our first-hand

Concluding remarks

Software agents and their applications in intelligent manufacturing have been studied for about two decades. However, industrial applications are still rare compared with other technologies such as Distributed Objects and Web-based technologies. This might be primarily due to the fact that the majority of research and development work in this area has been done within the academic community. This situation may change since FIPA joined IEEE Computer Society as one of its standards committee,

References (159)

H.R. Choi et al.
An agent for selecting optimal order set in EC marketplace
DSS
(2004)
H. Corsten et al.
Opportunistic coordination of operations in job shop production
Technovation
(2004)
N.A. Duffie et al.
Real-time distributed scheduling of heterarchical manufacturing systems
JMS
(1994)
S. Galland et al.
MaMA-S: an introduction to a methodological approach for the simulation of distributed industrial systems
IJPE
(2003)
I.J. Jeong et al.
A distributed scheduling methodology for a two-machine flowshop using cooperative interaction via multiple coupling agents
JMS
(2002)
H.Z. Jia et al.
An adaptive and upgradable agent-based system for coordinated product development and manufacture
RCIM
(2004)
A. Karageorgos et al.
Agent-based optimisation of logistics and production planning
EAAI
(2003)
M.K. Lim et al.
An integrated agent-based approach for responsive control of manufacturing resources
Computers and Industrial Engineering
(2004)
A. Azevedo, C. Torscano, J.P. Sousa, An order planning system to support networked supply chains, in: Proc. of...
A. Babanov et al.
Asking the right question: risk and expectation in multiagent contracting
AIEDAM
(2003)

A. Babayan et al.

Solving the n-job 3-stage flexible flowshop scheduling problem using an agent-based approach

International Journal of Production Research

(2004)

A.D. Baker, Manufacturing control with a market-driven contract net, PhD Thesis, Rensselaer Polytechnic Institute, NY,...

A.D. Baker et al.

Agents and the Internet: Infrastructure for mass customization

IEEE Internet Computing

(1999)

S. Barber, E. White, A. Goel, D. Han, J. Kim, H. Li, T.H. Liu, C.E. Martin, R. McKay, Sensible agent problem-solving...

J. Barry, M. Aparicio, T. Durniak, P. Herman, J. Karuturi, C. Woods, C. Gilman, H. Lam, R. Ramnath, NIIIP-SMART: an...

H. Baumgaertel, U. John, Combining agent-based supply net simulation and constraint technology for highly efficient...

N.M. Berry, S. Kumura, Evaluating the design and development of Reagere, in: Working Notes of the ABM (Agent-Based...

G. Biswas, S. Bagchi, A. Saad, Holonic planning and scheduling for assembly tasks, Technical Report, TR CIS-95-01,...

B. Bjork, J. Wix, An introduction to STEP, Technical Report, VTT Technical Research Centre of Finland and Wix McLelland...

C.F. Bremer et al.

Global virtual business – a systematic approach for exploiting business opportunities in dynamic markets

IJAM

(1999)

R. Brennan, S. Balasubramanian, D.H. Norrie, Dynamic control architecture for advanced manufacturing systems, in: Proc....

M. Bruccoleri et al.

Distributed intelligent control of exceptions in reconfigurable manufacturing systems

International Journal of Production Research

(2003)

S. Brückner, J. Wyns, P. Peeters, M. Kollingbaum, Designing agents for the manufacturing process control, in: Proc. of...

D. Brugali, G. Menga, S. Galarraga, Inter-company supply chains integration via mobile agents, in: Proc. of...

J. Budenske, A. Ahamad, E. Chartier, Agent-based architecture for exchanging modeling data between applications, in:...

P. Burke et al.

The distributed asynchronous scheduler

S. Bussmann, An agent-oriented architecture for holonic manufacturing control, in: Proc. of IMS1998, Lausanne,...

S. Bussmann, K. Schild, An agent-based approach to the control of flexible production systems, in: Proc. of the 8th...

J. Butler et al.

ADDYMS: Architecture for distributed dynamic manufacturing scheduling

L.M. Camarinha-Matos et al.

Infrastructure for Virtual Enterprise

(1999)

Y.S. Chan et al.

Case-based modification for optimization agents: AGENT-OPT’

DSS

(2004)

H.R. Choi, H.S. Kim, Y.J. Park, Multi-agent-based negotiation support system for order based manufacturers, in: Proc....

H.S. Choi et al.

Shop-floor scheduling at shipbuilding yards using the multiple intelligent agent system

Journal of Intelligent Manufacturing

(1997)

J.H. Christensen, P.J. Struger, D.H. Norrie, C. Schaeffer, Material handling requirements in holonic manufacturing...

R.S. Cost, T. Finin, Y. Labrou, X. Luan, Y. Peng, I. Soboroff, J. Mayfield, A. Boughannam, An agent-based...

P.I. Cowling et al.

Dynamic scheduling of steel casting and milling using multi-agents

PPC

(2004)

M.R. Cutkosky et al.

PACT: An experiment in integrating concurrent engineering systems

IEEE Computer

(1993)

M.R. Cutkosky et al.

Madefast: Collaborative engineering over the Internet

Communication of the ACM

(1996)

N.A. Duffie et al.

Non-hierarchical control of manufacturing systems

JMS

(1986)

T. Finin, R. Fritzon, D. McKay, R. McEntire, KQML - A Language and protocol for knowledge and information exchange,...

K. Fischer, The design of an intelligent manufacturing system, in: Proc. of CKBS’94, University of Keele, England,...

K. Fischer, J.P. Muller, M. Pischel, D. Schier, A model for cooperative transportation scheduling, in: Proc. of...

G. Fleury, J.Y. Goujon, M. Gourgand, P. Lacomme, Multi-agent approach for manufacturing systems optimization, in: Proc....

S.P. Fonseca, M.L. Griss, R. Letsinger, Agent behavior architectures: a MAS framework comparison, in: Proc. of...

K. Fordyce et al.

Logistics management system (LMS): integrating decision technologies for dispatch scheduling in semiconductor manufacturing

M.S. Fox, J.F. Chionglo, M. Barbuceanu, The integrated supply chain management system, Internal Report, Dept. of...

D. Frey, T. Stockheim, P.-O. Woelk, R. Zimmermann, Integrated multi-agent-based supply chain management, in: Proc. of...

M. Genesereth, R.E. Fikes, Knowledge Interchange Format, Version 3.0, Reference Manual, Technical Report Logic-92-1,...

M. Genesereth et al.

Software agents

Communications of the ACM

(1994)

Cited by (461)

The impact of intelligent manufacturing on labor productivity: An empirical analysis of Chinese listed manufacturing companies
2024, International Journal of Production Economics
Integrating a variety of disruptive information technologies and advanced manufacturing technologies, intelligent manufacturing (IM) has been increasingly adopted by manufacturers around the globe. While previous studies have extensively demonstrated the technological characteristics as well as industrial applications of IM, only a few studies have investigated the likely operational performance effects of IM at the firm-level, presumably due to limited data availability. Accordingly, the motivation of this study is to empirically examine the impact of IM adoption on operational performance in terms of labor productivity, and the conditions under which adopters may reap more benefits from IM. We leverage the resource-based view as the theoretical lens and use the difference-in-differences method to analyze the staggered implementation of IM pilot projects with 16,441 firm-year observations between 2010 and 2020 in China. Our results show that the adoption of IM has positive and significant impacts on Chinese listed manufacturing companies’ labor productivity. In addition, manufacturers with higher employee human capital quality and R&D intensity, as well as operating in more competitive industries will enjoy a more salient IM implementation-labor productivity benefit. Overall, our study contributes to the emerging IM literature by providing empirical evidence of the productivity enhancement effect of IM adoption based on large-scale secondary data, and it also supports the view that successful adoption of innovative technology stems from a proper fit between that technology and diverse internal and external contingencies.
Towards resilience in Industry 5.0: A decentralized autonomous manufacturing paradigm
2023, Journal of Manufacturing Systems
Manufacturers are increasingly aware of the importance of system resilience against unexpected disruptive occurrences, such as the recent global Covid-19 pandemic and geopolitical wars in Europe. Meanwhile, Decentralized Autonomous Organization (DAO) is recently envisioned as the Blockchain 3.0 stage, in which enabling DAO in the manufacturing domain could be a promising attempt and will lead to decentralized autonomous manufacturing. Blockchain-enabled smart contracts and decentralized applications have the characteristics of verifiability, decentralization, transparency, autonomy, and tamper-proofing, which can enable a mass individualization paradigm to realize the promising Industry 5.0 vision of resilience. DAO provides a probable manner to regulate cross-prosumer activities under the Industry 5.0 context. Inspired by this vision, our paper reviews the literature on Decentralized Manufacturing (DM) and Autonomous Manufacturing (AM). Then, these two streams of efforts are unified, and a manufacturing paradigm, named Decentralized Autonomous Manufacturing (DAM), is defined towards resilience in Industry 5.0. In this paper, a reference architecture of the DAM is given. Followed by a comprehensive investigation of the key enablers, challenges, and barriers in the implementation of DAM, based on the insights from this analysis, future research directions of DAM are highlighted. We believe that our effort can lay a foundation for positioning DAM in futuristic Industry 5.0 research and engineering practice.
Integration of deep reinforcement learning and multi-agent system for dynamic scheduling of re-entrant hybrid flow shop considering worker fatigue and skill levels
2023, Robotics and Computer-Integrated Manufacturing
In real-life manufacturing systems, production management is often affected by urgent demands and unexpected interruptions, such as new job insertions, machine breakdowns and operator unavailability. In this context, agent-based techniques are useful and able to respond quickly to dynamic disturbances. The ability of agents to recognize their environment and make decisions can be further enhanced by deep reinforcement learning (DRL). This paper investigates a novel dynamic re-entrant hybrid flow shop scheduling problem (DRHFSP) considering worker fatigue and skill levels to minimize the total tardiness of all production tasks. An integrated architecture of DRL and MAS (DRL-MAS) is proposed for real-time scheduling in dynamic environments. Two DRL models are proposed for different sub-decisions, where a reward-shaping technique combining long-term and short-term returns is proposed for the job sequence and machine selection sub-decisions, and an attention-based network is proposed for the worker assignment sub-decision for efficient feature extraction and decision making. Numerical experiments and case studies demonstrate the superior performance of the proposed DRL models compared with existing scheduling strategies.
Digital twins-based flexible operating of open architecture production line for individualized manufacturing
2022, Advanced Engineering Informatics
Individualized manufacturing implies high flexibility of both the hardware and software of the production lines based on a fast physical and logical system (de)commissioning. This paper proposes an open architecture production line (OAPL) design together with a digital twins-based flexible operating approach for individualized manufacturing. Firstly, an OAPL is designed and implemented with physical reconfigurability by orchestrating different open architectural platforms together with open architecture machine tools (OAMTs). Secondly, an open architectural style modeling and configuration method is presented to enable the software reconfigurability of the controls of the OAPL. Thirdly, a digital twin-based online process emulating and multi-physics simulation is integrated to aid the comprehensive characterizing of the operation status of the OAPL. Based on the system reconfigurability and digital twins system, a triple-layer Learning-Optimization-Reacting approach together with an ensemble algorithm for flexible operating of the OAPL is proposed. The digital twins are formed with the ability to flexibly operate the OAPL for catering to different individualized requirements. A demonstrative implementation of a stepping-motor assembly OAPL is presented finally.
Enhanced time-constraint aware tasks scheduling mechanism based on predictive optimization for efficient load balancing in smart manufacturing
2022, Journal of Manufacturing Systems
Smart manufacturing has great potential for developing customized products to meet the dynamic needs of customers and a collaborative network to enhance production efficiency. It is an emerging area with the revolution of business strategies, such as Industry 4.0 and Industrial Internet of the United States of America. IIoT and data-driven technologies, such as AI and ML, have leveraged the production environment by facilitating mass personalized customization of products and improving manufacturing processes collaboratively. However, these technologies are segregated and dispersed in the digitization of manufacturing products and automation of machines in existing manufacturing processes. Therefore, it is a leverage challenge to develop an integrated solution based on IIoT and data-driven technologies for an autonomous manufacturing environment. This research study presents an integrated solution using an enhanced TCA tasks scheduling mechanism based on a predictive optimization approach to improve smart manufacturing production efficiency. The proposed enhanced TCA tasks scheduling mechanism is an improved variant of FEF scheduling that considers accurate decision (prediction) measures and tasks’ minimal (optimal) time to schedule tasks efficiently. This study aims to efficiently plan task execution sequence to increase smart manufacturing productions and efficiency of resource utilization in real-time by maximizing utilization of smart machines, minimizing tasks idle time, and autonomously controlling the smart manufacturing environment through installed sensors and actuators. Furthermore, different evaluation methods are used to analyze the significance of the proposed PO-TCA scheduling mechanism, such as response time, tasks drop rate, tasks starvation rate, and machine utilization rate. The experimental analysis shows that the proposed enhanced PO-TCA scheduling mechanism reduces dropout and starvation rates by 21 % and 17 %, respectively. Our proposed mechanism also improves machine utilization by an average of 18 % compared to the baseline scheduling strategy. Moreover, experimental results signify that the proposed PO-TCA scheduling mechanism improves the utilization of smart machines and minimizes the task’s idle time to achieve a trade-off between tasks response and waiting time.
In-depth analysis on safety and security research based on system dynamics: A bibliometric mapping approach-based study
2022, Safety Science
Safety and security (SS) research based on system dynamics (SD) play a greater theoretical and technical support for hazard identification and accident prevention, which meant SD has become an important method to study the system safety, also that SS research based on SD has entered the application stage. It is a relatively macroscopic understanding of the application of SD to SS research by scholars, and difficult to capture the changes and characteristics of specific topics from the understanding. To get an in-depth understanding of the current research characteristics and development in the research domain, and help researchers dig into the more information from a quantitative perspective, we retrieved 1091 documents about SS-related research based on SD published in the period 2000–2020 from the Web of Science Core Collection database in this paper, the bibliometric analysis and science mapping were carried out. The USA, China, UK, Germany and Australia were the five most contributions to the literature associated with SS research based on SD. In terms of the major sources and co-citation of SS-related research publications, IEEE Transactions on Power System, Safety Science, Energy Policy, System Dynamics Review and Reliability Engineering & System Safety are the five most active journals in this domain. The knowledge base of SS research based on SD focuses on “safety management”, “risk analysis” and “network and information security”. There are some significant differences between the safety and security domains while they are very similar in “risk analysis”. Currently, hotspot topics include “safety management”, “energy security”, “resource utilization” and “industry applications”. “system safety and reliability”, “energy consumption and security” and “power system dynamics and stability” have become the research frontier in the field.

View all citing articles on Scopus

^☆: This is an updated version of a previously published survey paper [122].

View full text

Applications of agent-based systems in intelligent manufacturing: An updated review☆

Abstract

Introduction

Section snippets

Requirements for next generation manufacturing systems

Agent-based systems for intelligent manufacturing

Key issues in implementing agent-based manufacturing systems

Concluding remarks

DSS

Technovation

JMS

IJPE

JMS

RCIM

EAAI

Computers and Industrial Engineering

Asking the right question: risk and expectation in multiagent contracting

AIEDAM

Solving the n-job 3-stage flexible flowshop scheduling problem using an agent-based approach

International Journal of Production Research

Agents and the Internet: Infrastructure for mass customization

IEEE Internet Computing

Global virtual business – a systematic approach for exploiting business opportunities in dynamic markets

IJAM

Distributed intelligent control of exceptions in reconfigurable manufacturing systems

International Journal of Production Research

The distributed asynchronous scheduler

ADDYMS: Architecture for distributed dynamic manufacturing scheduling

Infrastructure for Virtual Enterprise

Case-based modification for optimization agents: AGENT-OPT’

DSS

Shop-floor scheduling at shipbuilding yards using the multiple intelligent agent system

Journal of Intelligent Manufacturing

Dynamic scheduling of steel casting and milling using multi-agents

PPC

PACT: An experiment in integrating concurrent engineering systems

IEEE Computer

Madefast: Collaborative engineering over the Internet

Communication of the ACM

Non-hierarchical control of manufacturing systems

JMS

Logistics management system (LMS): integrating decision technologies for dispatch scheduling in semiconductor manufacturing

Software agents

Communications of the ACM