Near optimal jobshop scheduling using neural network parallel computing

Akira Hanada, Kouhei Ohnishi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

A parallel algorithm based on the neural network model for jobshop scheduling problem is presented in this paper. In the manufacturing system, it is becoming more complex to manage operations of facilities, because of many requirements and constraints such as to increase product throughput, reduce work-in-process and keep the due date. The goal of the proposed parallel algorithm is to find a near-optimum scheduling solution for the given schedule. The proposed parallel algorithm requires N × N processing elements (neurons) where N is the number of operations. Our empirical study on the sequential shows the behavior of the system.

Original languageEnglish
Title of host publicationPlenary Session, Emerging Technologies, and Factory Automation
Editors Anon
PublisherPubl by IEEE
Pages315-320
Number of pages6
ISBN (Print)0780308913
Publication statusPublished - 1993 Dec 1
EventProceedings of the 19th International Conference on Industrial Electronics, Control and Instrumentation - Maui, Hawaii, USA
Duration: 1993 Nov 151993 Nov 18

Publication series

NameIECON Proceedings (Industrial Electronics Conference)
Volume1

Other

OtherProceedings of the 19th International Conference on Industrial Electronics, Control and Instrumentation
CityMaui, Hawaii, USA
Period93/11/1593/11/18

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Near optimal jobshop scheduling using neural network parallel computing'. Together they form a unique fingerprint.

Cite this