Optimization Through Artificial Neural Network and Compare with Response Surface Methodology for Multiples Yield

Abstract

Cotton slub yarn is widely used in denomination and any other casual, physical and mechanical Conditions. The data for the underlying purpose was collected from the Department of Polymer Engineering, National Textile University, and Faisalabad. R-Programming language software is used for analysis. The output of cotton depends on several factors whose cumulative influence on Process efficiency has a direct influence. The purpose of the research was to optimize the 100% cotton slub yarn model (slub length, slub thickness, pause length and linear density) for multiples yield (elongation, imperfection, strength, coefficient of mass variation and hairiness) as Optimizing is a way of identifying and enhancing the performance of the constructed framework by assessing a set of quality parameters, such as process efficiency using two methods response- surface methodology (RSM) and artificial neural network (ANN) and the results are compared using mean square error (MSE). Furthermore, coefficients of determination () and the mean square error root (RMSE) are used for greater accuracy. However, the ANN has consistently performed better than the RSM in all the aspects. The final selected ANN model was able to simultaneously predict the five output parameters with an RMSE of 0.229.