Applying Fuzzy Logic and Neural Networks to Total Hand Evaluation of Knitted Fabrics

Abstract

This study of two new total hand simulating methods for knits uses fuzzy theory and neural networks. One method, a neural network system trained with a back-propaga tion algorithm, performs functional mapping between mechanical properties and the resulting total hand values of the fuzzy predicting method. The second method, a fuzzy-neural network system, uses the fuzzy membership function, weighted factor vector, and error back-propagation algorithm. The principal mechanical properties of stretchiness, bulkiness, flexibility, distortion, weight, and surface roughness of the knitted fabrics are correlated with experimentally determined Kawabata total hand values and fuzzy transformed overall hand values. Fuzzy and neural networks agree better with the subjective test results than the KES-FB system. The mechanical prop erties are fuzzified by fuzzy membership functions, then trained to predict the total hand value of outerwear knitted fabrics. In each case, the prediction error is less than the standard deviation of experimentation, and the optimum structure is investigated. These two systems, which use the Pascal programming language, produce objective ratings of outerwear knit fabrics.