Designing neural networks for manufacturing process control systems

C. H. Messom, C. J. Hinde, A. A. West, D. J. Williams

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

3 Citations (Scopus)

Abstract

The design of neural networks for the control of discrete manufacturing processes is addressed. Rather than treating the networks as adaptive black boxes, an architecture that links the weights associated with the nodes and thus allows the relationships and internal structure to be tightly constrained is introduced. The constrained search space gives greater confidence in the internal representations that have been induced by the training set and therefore about the correct behavior of the network between the given limits. The method is illustrated by applying it to the dispensing of adhesives.

Original languageEnglish
Title of host publicationProceedings of the 1992 IEEE International Symposium on Intelligent Control
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages423-429
Number of pages7
ISBN (Electronic)0780305469
DOIs
Publication statusPublished - 1 Jan 1992
EventIEEE International Symposium on Intelligent Control 1992 - Glasgow, Scotland, United Kingdom
Duration: 11 Aug 199213 Aug 1992
https://ieeexplore.ieee.org/xpl/conhome/629/proceeding (Proceedings)

Publication series

NameIEEE International Symposium on Intelligent Control - Proceedings
Volume1992-August

Conference

ConferenceIEEE International Symposium on Intelligent Control 1992
Abbreviated titleISIC 1992
Country/TerritoryUnited Kingdom
CityGlasgow, Scotland
Period11/08/9213/08/92
Internet address

Cite this