Predicting the tensile properties of cotton/spandex core-spun yarns using artificial neural network and linear regression models

Recently, core-spun yarns showed many improved characteristics. The tensile properties of such yarns are accepted as one of the most important parameters for assessment of yarn quality. The tensile properties decide the performance of post-spinning operations; warping, weaving, and knitting, and the properties of the final textile product; hence, its accurate prediction carries much importance in industrial applications. In this study, artificial neural network (ANN) and multiple regression methods for modeling the tensile properties of cotton/spandex core-spun yarns are investigated. Yarn breaking strength, breaking elongation, and work of rupture of the core-spun yarns are studied. The two models were assessed by verifying root mean square error, mean bias error, and coefficient of determination (R-2-value). The results of this study revealed that ANN has better performance in predicting comparing with multiple linear regression.