Predicting bursting strength of cotton plain knitted fabrics using intelligent techniques

The bursting strength of cotton plain knitted fabrics is predicted before m anufacturing using intelligent techniques of neural network and neuro-fuzzy approaches in this research. Among many parameters that affect fabric burs ting strength, fabric weight, yarn breaking strength, and yarn breaking elo ngation are input elements for the predictions. In this research, both the multi-layer feed-forward neural network and adaptive network-based fuzzy in ference system, a combination of a radial basis neural network and the Suge no-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 .