New Approaches to Establishing Translation Equations for the Total Hand Value of Fabric

• Published in: Textile research journal Vol. 74; no. 6; pp. 528 - 534
• Main Authors: Shyr, Tien-Wei, Lai, Shin-Song, Lin, Jer-Yan
• Format: Journal Article
• Language: English
• Published: Thousand Oaks, CA SAGE Publications 01.06.2004; Sage Publications Ltd
• Subjects: Artificial neural networks; Cotton; equations; Experiments; Fabrics; Mathematical analysis; Mathematical models; Mechanical properties; neural networks; Polyesters; Regression; regression analysis; textile fibers; textile industry; Textiles; Transformations; Translations; woven fabrics
• ISSN: 0040-5175; 1746-7748
• DOI: 10.1177/004051750407400611

The aim of this study is to take new approaches using a one-step transformation process to establish translation equations for total hand evaluations of fabrics by employing a stepwise regression method and an artificial neural network. The key mechanical prop erties selected from sixteen fabric mechanical properties based on a KES system, using the stepwise regression selection method, are the parameters. The translation equations are developed directly with parameters without a primary hand value transformation process. In this study, 114 polyester/cotton blended woven fabrics are selected for investigation. From the results, four mechanical properties LC, 2HG, B, and WT are the parameters for developing the translation equations. The correlation coefficients of the translation equa tions developed from the stepwise regression and artificial neural network methods are 0.925 and 0.955, respectively. Both translation equations have high correlation coeffi cients between the calculated and practical values. The approaches are identified effec tively to develop translation equations for new fabrics in the textile industry.