The prediction of warp breakage rate of weaving by considering sized yarn quality using artificial neural network theory

Abstract

Artificial neural network methods are established and designed to predict the warp breakage rate. The objective of this paper is to investigate the predictability of the warp breakage rate from a sizing yarn quality index using a feed-forward back-propagation network in an artificial neural network system. In order to achieve the objective, a series of trial is conducted. The good correlation between predicted and actual warp breakage rates indicates that warp breakage rates can be predicted by neural networks, the model with a single tanh hidden layer with 8 neurons is able to produce better predictions than the other models of this particular data set in the work. The experimental results and the corresponding analysis show that the artificial neural network model is an efficient technique for the quality prediction and has wide prospect in the application of the textile industry.