Using designed experiments to produce robust neural network models of manufacturing processes

David W. Coit, Alice E. Smith

Research output: Contribution to conferencePaperpeer-review

7 Scopus citations

Abstract

Neural networks are beginning to be used for modeling of complex systems, often in process and quality control of manufacturing processes. Since neural networks are wholly empirical models, the resulting model is highly dependent on the data used to construct it. Using data from production lines ensures integrity, however may produce biased samples which do not reflect the entire range of domain operation. Supplementing production observations with data gathered from designed experiments alleviates this problem of overly focused data sets. This paper describes this designed experiment supplemental approach as it was used on two research projects involving complex manufacturing processes.

Original languageAmerican English
Pages229-238
Number of pages10
StatePublished - 1995
Externally publishedYes
EventProceedings of the 1995 4th Industrial Engineering Research Conference - Nashville, TN, USA
Duration: May 24 1995May 25 1995

Other

OtherProceedings of the 1995 4th Industrial Engineering Research Conference
CityNashville, TN, USA
Period5/24/955/25/95

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'Using designed experiments to produce robust neural network models of manufacturing processes'. Together they form a unique fingerprint.

Cite this