Prediction of thin place of polyester/cotton ring yarn properties from process parameters by using neural network and regression analysis

摘要

This paper presents a comparative study of two modeling methods for predicting the thin place of polyester/cotton ring yarn. The results from these two series of models have been compared with the measured values respectively, proving that the accuracy of the ANN model is better and higher than that of linear multiple regression model. The experimental results and the corresponding analysis show that the ANN model is an efficient techniques for the quality prediction and has wide prospect in the application of ring spinning production system. better than that of linear multiple regression model.