Adaptation and learning in distributed production control

L. Monostori, B. Cs Csáji, B. Kádár

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Distributed (agent-based) control architectures offer prospects of reduced complexity, high flexibility and a high robustness against disturbances in manufacturing. However, it has also turned out that distributed control architectures, usually banning all forms of hierarchy, cannot guarantee optimum performance and the system behaviour can be unpredictable. In the paper machine learning approaches such as neurodynamic programming and simulated annealing are described for managing changes and disturbances in manufacturing systems, and to decrease the computational costs of the scheduling process. The results demonstrate the applicability of the proposed solutions, which can contribute to significant improvements in system performance, keeping the known benefits of distributed control.

Original languageEnglish
Pages (from-to)349-352
Number of pages4
JournalCIRP Annals - Manufacturing Technology
Volume53
Issue number1
Publication statusPublished - 2004

Fingerprint

Production control
Computer programming
Simulated annealing
Learning systems
Scheduling
Costs

Keywords

  • Agent-based manufacturing system
  • Distributed production control
  • Machine learning

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Adaptation and learning in distributed production control. / Monostori, L.; Csáji, B. Cs; Kádár, B.

In: CIRP Annals - Manufacturing Technology, Vol. 53, No. 1, 2004, p. 349-352.

Research output: Contribution to journalArticle

@article{3fe36ee5e7bf43818e8af5947d9fe8da,
title = "Adaptation and learning in distributed production control",
abstract = "Distributed (agent-based) control architectures offer prospects of reduced complexity, high flexibility and a high robustness against disturbances in manufacturing. However, it has also turned out that distributed control architectures, usually banning all forms of hierarchy, cannot guarantee optimum performance and the system behaviour can be unpredictable. In the paper machine learning approaches such as neurodynamic programming and simulated annealing are described for managing changes and disturbances in manufacturing systems, and to decrease the computational costs of the scheduling process. The results demonstrate the applicability of the proposed solutions, which can contribute to significant improvements in system performance, keeping the known benefits of distributed control.",
keywords = "Agent-based manufacturing system, Distributed production control, Machine learning",
author = "L. Monostori and Cs{\'a}ji, {B. Cs} and B. K{\'a}d{\'a}r",
year = "2004",
language = "English",
volume = "53",
pages = "349--352",
journal = "CIRP Annals - Manufacturing Technology",
issn = "0007-8506",
publisher = "Elsevier USA",
number = "1",

}

TY - JOUR

T1 - Adaptation and learning in distributed production control

AU - Monostori, L.

AU - Csáji, B. Cs

AU - Kádár, B.

PY - 2004

Y1 - 2004

N2 - Distributed (agent-based) control architectures offer prospects of reduced complexity, high flexibility and a high robustness against disturbances in manufacturing. However, it has also turned out that distributed control architectures, usually banning all forms of hierarchy, cannot guarantee optimum performance and the system behaviour can be unpredictable. In the paper machine learning approaches such as neurodynamic programming and simulated annealing are described for managing changes and disturbances in manufacturing systems, and to decrease the computational costs of the scheduling process. The results demonstrate the applicability of the proposed solutions, which can contribute to significant improvements in system performance, keeping the known benefits of distributed control.

AB - Distributed (agent-based) control architectures offer prospects of reduced complexity, high flexibility and a high robustness against disturbances in manufacturing. However, it has also turned out that distributed control architectures, usually banning all forms of hierarchy, cannot guarantee optimum performance and the system behaviour can be unpredictable. In the paper machine learning approaches such as neurodynamic programming and simulated annealing are described for managing changes and disturbances in manufacturing systems, and to decrease the computational costs of the scheduling process. The results demonstrate the applicability of the proposed solutions, which can contribute to significant improvements in system performance, keeping the known benefits of distributed control.

KW - Agent-based manufacturing system

KW - Distributed production control

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=3142747619&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3142747619&partnerID=8YFLogxK

M3 - Article

VL - 53

SP - 349

EP - 352

JO - CIRP Annals - Manufacturing Technology

JF - CIRP Annals - Manufacturing Technology

SN - 0007-8506

IS - 1

ER -