Prediction of Rotor Spun Yarn Strength Using Adaptive Neuro-fuzzy Inference System and Linear Multiple Regression Methods

This paper presents a comparison study of two models for predicting the strength of rotor spun cotton yarns from fiber properties. The adaptive neuro-fuzzy system inference （ANFIS） and Multiple Linear Regression models are used to predict the rotor spun yarn strength. Fiber properties and yam count are used as inputs to train the two models and the count-strength-product （CSP） was the targel. The predictive performances of the two models are estimated and compared. We found that the ANFIS has a better predictive power in comparison with linear multiple regression model. The impact of each fiber property is also illustrated.