Predicting twist contraction in chenille yarn using mathematical and statistical approaches

In this study, the effective factors on twist contraction of chenille yarn that is a kind of fancy yarn were investigated with theoretical and statistical approaches. The aim of this investigation was to develop a model to predict the twist contraction in chenille yarn before production. In the theoretical approach, we developed a mathematical model by geometrical methods. Twenty-seven different chenille yarn samples were produced according to an experimental design containing different levels of effective factors. In statistical approach, the data sets were divided into two parts as 20 and 7. A stepwise regression analysis was applied to 20 of all and acquired a significant model. The remaining data sets were used for verification. Finally, the mathematical and statistical models were verified and compared their performance to estimate twist contraction. As a result, it has proved that the performance of regression model is slightly better than the mathematical model. However, both of the models can give acceptable predicted values for twist contraction in chenille yarns.