A self-organizing neural network approach for the design of cellular manufacturing systems

Hong Chul Lee, César O. Malavé, Satheesh Ramachandran

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

The crux problem of group technology (GT) is the identification of part families requiring similar manufacturing processes and the rearrangement of machines to minimize the number of parts that visit more than one machine cell. This paper presents an improved method for part family formation, machine cell identification, bottleneck machine detection and the natural cluster generation using a self-organizing neural network. In addition, the generalization ability of the neural network makes it possible to assign the new parts to the existing machine cells without repeating the entire computational process. A computer program is developed to illustrate the effectiveness of this heuristic method by comparing it with the optimal technique for large-scale problems.

Original languageEnglish
Pages (from-to)325-332
Number of pages8
JournalJournal of Intelligent Manufacturing
Volume3
Issue number5
DOIs
Publication statusPublished - 1992 Oct 1
Externally publishedYes

Fingerprint

Cellular manufacturing
Neural networks
Group technology
Heuristic methods
Computer program listings

Keywords

  • cellular manufacturing system
  • cluster analysis
  • generalization
  • Group technology
  • neural network

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Artificial Intelligence

Cite this

A self-organizing neural network approach for the design of cellular manufacturing systems. / Lee, Hong Chul; Malavé, César O.; Ramachandran, Satheesh.

In: Journal of Intelligent Manufacturing, Vol. 3, No. 5, 01.10.1992, p. 325-332.

Research output: Contribution to journalArticle

@article{dec7a2a1b2ef418c88e4164baeea7720,
title = "A self-organizing neural network approach for the design of cellular manufacturing systems",
abstract = "The crux problem of group technology (GT) is the identification of part families requiring similar manufacturing processes and the rearrangement of machines to minimize the number of parts that visit more than one machine cell. This paper presents an improved method for part family formation, machine cell identification, bottleneck machine detection and the natural cluster generation using a self-organizing neural network. In addition, the generalization ability of the neural network makes it possible to assign the new parts to the existing machine cells without repeating the entire computational process. A computer program is developed to illustrate the effectiveness of this heuristic method by comparing it with the optimal technique for large-scale problems.",
keywords = "cellular manufacturing system, cluster analysis, generalization, Group technology, neural network",
author = "Lee, {Hong Chul} and Malav{\'e}, {C{\'e}sar O.} and Satheesh Ramachandran",
year = "1992",
month = "10",
day = "1",
doi = "10.1007/BF01577273",
language = "English",
volume = "3",
pages = "325--332",
journal = "Journal of Intelligent Manufacturing",
issn = "0956-5515",
publisher = "Springer Netherlands",
number = "5",

}

TY - JOUR

T1 - A self-organizing neural network approach for the design of cellular manufacturing systems

AU - Lee, Hong Chul

AU - Malavé, César O.

AU - Ramachandran, Satheesh

PY - 1992/10/1

Y1 - 1992/10/1

N2 - The crux problem of group technology (GT) is the identification of part families requiring similar manufacturing processes and the rearrangement of machines to minimize the number of parts that visit more than one machine cell. This paper presents an improved method for part family formation, machine cell identification, bottleneck machine detection and the natural cluster generation using a self-organizing neural network. In addition, the generalization ability of the neural network makes it possible to assign the new parts to the existing machine cells without repeating the entire computational process. A computer program is developed to illustrate the effectiveness of this heuristic method by comparing it with the optimal technique for large-scale problems.

AB - The crux problem of group technology (GT) is the identification of part families requiring similar manufacturing processes and the rearrangement of machines to minimize the number of parts that visit more than one machine cell. This paper presents an improved method for part family formation, machine cell identification, bottleneck machine detection and the natural cluster generation using a self-organizing neural network. In addition, the generalization ability of the neural network makes it possible to assign the new parts to the existing machine cells without repeating the entire computational process. A computer program is developed to illustrate the effectiveness of this heuristic method by comparing it with the optimal technique for large-scale problems.

KW - cellular manufacturing system

KW - cluster analysis

KW - generalization

KW - Group technology

KW - neural network

UR - http://www.scopus.com/inward/record.url?scp=0000251299&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0000251299&partnerID=8YFLogxK

U2 - 10.1007/BF01577273

DO - 10.1007/BF01577273

M3 - Article

VL - 3

SP - 325

EP - 332

JO - Journal of Intelligent Manufacturing

JF - Journal of Intelligent Manufacturing

SN - 0956-5515

IS - 5

ER -