Prediction of end breakage rates of cotton yarn in ring spinning processing by applying neural network approach and regression analysis theory

Abstract

In this work, the artificial neural network and multiple regression methods are used for predicting the end breakage rates of cotton ring spinning yarn. The developed models were assessed by verifying mean square error (MSE) and correlation coefficient (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) of test data prediction. The results indicated that the artificial neural network model has better performance in comparison with the multiple regression models. The difference between the mean square error of predicting in these two models for predicting end breakage rate is high. It has been observed that the performance of ANN seems to be better than that of the multiple regression model.