The use of fuzzy logic and neural networks models for sensory properties prediction from process and structure parameters of knitted fabrics

  • Authors:

  • Selsabil El-Ghezal Jeguirim;Amal Babay Dhouib;Mahdi Sahnoun;Morched Cheikhrouhou;Laurence Schacher;Dominique Adolphe

  • Affiliations:

  • Textile Research Unit of ISET of Ksar-Hellal, Ksar Hellal, Tunisia 5070;Textile Research Unit of ISET of Ksar-Hellal, Ksar Hellal, Tunisia 5070;Textile Research Unit of ISET of Ksar-Hellal, Ksar Hellal, Tunisia 5070;Textile Research Unit of ISET of Ksar-Hellal, Ksar Hellal, Tunisia 5070;ENSISA, Laboratoire de Physique et Mécanique Textiles (LPMT), UMR 7189 CNRS/UHA, Mulhouse Cedex, France 68093;ENSISA, Laboratoire de Physique et Mécanique Textiles (LPMT), UMR 7189 CNRS/UHA, Mulhouse Cedex, France 68093

  • Venue:
  • Journal of Intelligent Manufacturing
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

In a competitive business environment, the textile industrialists intend to propose diversified products according to consumers preference. For this purpose, the integration of sensory attributes in the process parameters choice seems to be a useful alternative. This paper provides fuzzy and neural models for the prediction of sensory properties from production parameters of knitted fabrics. The prediction accuracy of these models was evaluated using both the root mean square error (RMSE) and mean relative percent error (MRPE). The results revealed the models ability to predict tactile sensory attributes based on the production parameters. The comparison of the prediction performances showed that the neural models are slightly powerful than the fuzzy models.