Predicting bursting strength of cotton plain knitted fabrics using intelligent techniques

Ertugrul S., UCAR N.

TEXTILE RESEARCH JOURNAL, vol.70, no.10, pp.845-851, 2000 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 70 Issue: 10
  • Publication Date: 2000
  • Doi Number: 10.1177/004051750007001001
  • Journal Name: TEXTILE RESEARCH JOURNAL
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.845-851
  • Istanbul Technical University Affiliated: No

Abstract

The bursting strength of cotton plain knitted fabrics is predicted before manufacturing using intelligent techniques of neural network and neuro-fuzzy approaches in this research. Among many parameters that affect fabric bursting strength, fabric weight, yarn breaking strength, and yarn breaking elongation are input elements for the predictions. In this research, both the multi-layer feed-forward neural network and adaptive network-based fuzzy inference system, a combination of a radial basis neural network and the Sugeno-Takagi fuzzy system, are studied. Both systems have the ability to learn training data successfully, and testing errors are small enough to give an approximate knowledge of the bursting strength of the fabric to be knitted.