Prediction of Polypropylene Yarn Shrinkage in the Heat-Setting Process Using the Fuzzy Inference System

Abstract

In the carpet industry, yarn shrinkage is a very important specification, the percent of shrinkage affected by heat setting parameters, time and temperature. In order to obtain the best uniform appearance of carpets, the shrinkage of pile yarns should be minimum in the carpet sizing process. An inappropriate heat set yarn may cause an undesirable shrinkage result and uneven pile height on carpets after the sizing process. It could be useful for manufacturers to understand the optimum condition of heat setting to obtain the low shrinkage of heat set yarns before weaving. Therefore, a fuzzy logic model is designed to predict the shrinkage percentage of polypropylene yarn in different heat setting conditions. Time and temperature are taken into account as input variables and yarn shrinkage is predicted as output. For validation of the model, the yarn samples heat set under various sets of time and temperature and finally yarn shrinkages have been measured experimentally. The result of the fuzzy model prediction compared to regression results and signify the fuzzy results present good and better match with experimental results with the acceptable R2=0.97 and average error (2.59%).