A neural network for dispatching rule selection in a job shop

Ahmed El-Bouri, Pramit Shah

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

This paper investigates an intelligent system that selects dispatching rules to apply locally for each machine in a job shop. Randomly generated problems are scheduled using optimal permutations of three different dispatching rules on five machines. A neural network is then trained to associate between a statistical characterization of the job mix in each of these problems, with the best combination of dispatching rules to use. Once trained, the neural network is able to recommend for new problems a dispatching rule to use on each machine. Two networks are trained separately for minimizing makespan and the mean flowtime in the job shop. Test results show that the combinations of dispatching rules suggested by the trained networks produce better results, for both objectives, than the alternative of using a single rule common to all machines.

Original languageEnglish
Pages (from-to)342-349
Number of pages8
JournalInternational Journal of Advanced Manufacturing Technology
Volume31
Issue number3-4
DOIs
Publication statusPublished - Nov 2006

Fingerprint

Neural networks
Intelligent systems

Keywords

  • Dispatching rules
  • Job shop
  • Makespan
  • Mean flowtime
  • Neural networks

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

A neural network for dispatching rule selection in a job shop. / El-Bouri, Ahmed; Shah, Pramit.

In: International Journal of Advanced Manufacturing Technology, Vol. 31, No. 3-4, 11.2006, p. 342-349.

Research output: Contribution to journalArticle

@article{4e171977239141e59311a3a0647f030d,
title = "A neural network for dispatching rule selection in a job shop",
abstract = "This paper investigates an intelligent system that selects dispatching rules to apply locally for each machine in a job shop. Randomly generated problems are scheduled using optimal permutations of three different dispatching rules on five machines. A neural network is then trained to associate between a statistical characterization of the job mix in each of these problems, with the best combination of dispatching rules to use. Once trained, the neural network is able to recommend for new problems a dispatching rule to use on each machine. Two networks are trained separately for minimizing makespan and the mean flowtime in the job shop. Test results show that the combinations of dispatching rules suggested by the trained networks produce better results, for both objectives, than the alternative of using a single rule common to all machines.",
keywords = "Dispatching rules, Job shop, Makespan, Mean flowtime, Neural networks",
author = "Ahmed El-Bouri and Pramit Shah",
year = "2006",
month = "11",
doi = "10.1007/s00170-005-0190-y",
language = "English",
volume = "31",
pages = "342--349",
journal = "International Journal of Advanced Manufacturing Technology",
issn = "0268-3768",
publisher = "Springer London",
number = "3-4",

}

TY - JOUR

T1 - A neural network for dispatching rule selection in a job shop

AU - El-Bouri, Ahmed

AU - Shah, Pramit

PY - 2006/11

Y1 - 2006/11

N2 - This paper investigates an intelligent system that selects dispatching rules to apply locally for each machine in a job shop. Randomly generated problems are scheduled using optimal permutations of three different dispatching rules on five machines. A neural network is then trained to associate between a statistical characterization of the job mix in each of these problems, with the best combination of dispatching rules to use. Once trained, the neural network is able to recommend for new problems a dispatching rule to use on each machine. Two networks are trained separately for minimizing makespan and the mean flowtime in the job shop. Test results show that the combinations of dispatching rules suggested by the trained networks produce better results, for both objectives, than the alternative of using a single rule common to all machines.

AB - This paper investigates an intelligent system that selects dispatching rules to apply locally for each machine in a job shop. Randomly generated problems are scheduled using optimal permutations of three different dispatching rules on five machines. A neural network is then trained to associate between a statistical characterization of the job mix in each of these problems, with the best combination of dispatching rules to use. Once trained, the neural network is able to recommend for new problems a dispatching rule to use on each machine. Two networks are trained separately for minimizing makespan and the mean flowtime in the job shop. Test results show that the combinations of dispatching rules suggested by the trained networks produce better results, for both objectives, than the alternative of using a single rule common to all machines.

KW - Dispatching rules

KW - Job shop

KW - Makespan

KW - Mean flowtime

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=33751081510&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33751081510&partnerID=8YFLogxK

U2 - 10.1007/s00170-005-0190-y

DO - 10.1007/s00170-005-0190-y

M3 - Article

AN - SCOPUS:33751081510

VL - 31

SP - 342

EP - 349

JO - International Journal of Advanced Manufacturing Technology

JF - International Journal of Advanced Manufacturing Technology

SN - 0268-3768

IS - 3-4

ER -