Evaluating and Comparing the Physical Properties of Spliced Yarns by Regression and Neural Network Techniques

摘要

Different spliced yarn properties (strength, bending, abrasion, and appearance) are merged into a single score, also known as the total score, which is then used to analyze the overall performance of the yarns. A regression model and neural network model are set up according to the total score to predict the performance of the spliced yarns, and the two analysis techniques are compared. According to the analytical results, the neural network model gives a more accurate prediction than the regression model.