Comparison of Statistical Regression, Fuzzy Regression and Artificial Neural Network Modeling Methodologies in Polyester Dyeing

The aim of this study is to investigate, apply and compare statistical regression, fuzzy regression and artificial neural network (ANN) for modeling the color yield in polyester high temperature (HT) dyeing as a function of disperse dyes concentration, temperature and time. The predictive power of the obtained models was evaluated by means of MSE value. The results showed that the model based on statistical regression did not meet the required conditions to be accepted. However, the ANN model with a minimum MSE showed a better predictive capability than the model based on fuzzy regression, although the fuzzy regression model was also acceptable