A new stochastic neural network model and its application to grouping parts and tools in flexible manufacturing systems

Ikuo Arizono, H. Ohta, M. Kato, A. Yamamoto

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Recently, some stochastic neural network models have been presented for the purpose of overcoming the defect that the deterministic neural network models do not have the ability to escape from a local optimal solution. However, the specification of the values of various parameters and weights in these stochastic neural network models is more complicated than that in the deterministic neural network models. In this paper, a new stochastic neural network model is proposed in order to reduce the complication of specifying the values of parameters and weights. For a practical purpose, the proposed model is applied to the problem of grouping parts and tools in flexible manufacturing systems (FMSs).

Original languageEnglish
Pages (from-to)1535-1548
Number of pages14
JournalInternational Journal of Production Research
Volume33
Issue number6
DOIs
Publication statusPublished - 1995
Externally publishedYes

Fingerprint

Flexible manufacturing systems
Neural networks
Grouping
Network model
Specifications
Defects

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Management Science and Operations Research
  • Strategy and Management

Cite this

A new stochastic neural network model and its application to grouping parts and tools in flexible manufacturing systems. / Arizono, Ikuo; Ohta, H.; Kato, M.; Yamamoto, A.

In: International Journal of Production Research, Vol. 33, No. 6, 1995, p. 1535-1548.

Research output: Contribution to journalArticle

@article{36a675a4392e4d2a95efa507d7820fef,
title = "A new stochastic neural network model and its application to grouping parts and tools in flexible manufacturing systems",
abstract = "Recently, some stochastic neural network models have been presented for the purpose of overcoming the defect that the deterministic neural network models do not have the ability to escape from a local optimal solution. However, the specification of the values of various parameters and weights in these stochastic neural network models is more complicated than that in the deterministic neural network models. In this paper, a new stochastic neural network model is proposed in order to reduce the complication of specifying the values of parameters and weights. For a practical purpose, the proposed model is applied to the problem of grouping parts and tools in flexible manufacturing systems (FMSs).",
author = "Ikuo Arizono and H. Ohta and M. Kato and A. Yamamoto",
year = "1995",
doi = "10.1080/00207549508930227",
language = "English",
volume = "33",
pages = "1535--1548",
journal = "International Journal of Production Research",
issn = "0020-7543",
publisher = "Taylor and Francis Ltd.",
number = "6",

}

TY - JOUR

T1 - A new stochastic neural network model and its application to grouping parts and tools in flexible manufacturing systems

AU - Arizono, Ikuo

AU - Ohta, H.

AU - Kato, M.

AU - Yamamoto, A.

PY - 1995

Y1 - 1995

N2 - Recently, some stochastic neural network models have been presented for the purpose of overcoming the defect that the deterministic neural network models do not have the ability to escape from a local optimal solution. However, the specification of the values of various parameters and weights in these stochastic neural network models is more complicated than that in the deterministic neural network models. In this paper, a new stochastic neural network model is proposed in order to reduce the complication of specifying the values of parameters and weights. For a practical purpose, the proposed model is applied to the problem of grouping parts and tools in flexible manufacturing systems (FMSs).

AB - Recently, some stochastic neural network models have been presented for the purpose of overcoming the defect that the deterministic neural network models do not have the ability to escape from a local optimal solution. However, the specification of the values of various parameters and weights in these stochastic neural network models is more complicated than that in the deterministic neural network models. In this paper, a new stochastic neural network model is proposed in order to reduce the complication of specifying the values of parameters and weights. For a practical purpose, the proposed model is applied to the problem of grouping parts and tools in flexible manufacturing systems (FMSs).

UR - http://www.scopus.com/inward/record.url?scp=0029326051&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029326051&partnerID=8YFLogxK

U2 - 10.1080/00207549508930227

DO - 10.1080/00207549508930227

M3 - Article

AN - SCOPUS:0029326051

VL - 33

SP - 1535

EP - 1548

JO - International Journal of Production Research

JF - International Journal of Production Research

SN - 0020-7543

IS - 6

ER -