Neural modelling of polypropylene fibre processing: Predicting the structure and properties and identifying the control parameters for specified fibres

G. Allan, R. Yang, A. Fotheringham, R. Mather

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

This paper describes the application of artificial intelligence to data derived from polypropylene drawing carried out at Galashiels using designed experiments. The topology of the data is visualised in two dimensions with respect to specific properties to be modelled, as a quality check on the process data. A series of neural network models are used successfully to predict the tenacity, elongation, modulus and heat shrinkage and also the crystallographic order and polymer chains orientation of the output fibres from the draw parameters values. A software harness is constructed for using the neural predictors to find the draw parameters which come closest to achieving any specified combination of fibre properties. © 2001 Kluwer Academic Publishers.

Original languageEnglish
Pages (from-to)3113-3118
Number of pages6
JournalJournal of Materials Science
Volume36
Issue number13
DOIs
Publication statusPublished - 1 Jul 2001

Fingerprint Dive into the research topics of 'Neural modelling of polypropylene fibre processing: Predicting the structure and properties and identifying the control parameters for specified fibres'. Together they form a unique fingerprint.

  • Cite this