K/S value prediction of cotton fabric using PSO-LSSVM

Abstract

Cotton is one of the world’s most common natural clothing materials. It is dyed mainly using the exhaustion, cold pad-batch, and pad-dry-pad-steam dyeing methods. The K/S value, an important index for measuring the depth of color, of cotton fabric dyed with reactive dyes is greatly influenced by various factors of the dyeing process. In this study, three models were developed incorporating least squares support vector machine (LSSVM) to predict the K/S values of dyed cotton fabrics, while particle swarm optimization (PSO) was applied to optimize and tune the parameters of the LSSVM model (PSO-LSSVM). Model inputs include dye concentration and process conditions, which are both easily obtainable variables. The K/S values from the PSO-LSSVM model are consistent with actual measured K/S values of dyed cotton fabrics. Moreover, a comparison among PSO-LSSVM, LSSVM and back propagation neural network results shows the superiority of the PSO-LSSVM approach. Results of this work indicate that a PSO-LSSVM model is a powerful tool for predicting the K/S value in cotton fabric dyed with reactive dye and thus a means to improve production processes and reduce costs.