Prediction and analysis of fabric-evoked prickle properties of different textile woven fabrics using Artificial Neural Networks method
This paper aims to discuss the design and development of an Artificial Neural Networks (ANNs) model to understand a human perception of the tactile prickliness properties of textile wear fabric materials, and create an objective system to express those prickle perceptions in terms of measurable mechanical properties. The objective and also subjective hand measurement of the textile materials used for wear fabric has been check up on with consideration given the aspects of both dermatitis and comfort. In this study, attempt to predict the prickliness (itchiness) of wear fabric by their physical properties using a back-propagation network and a stepwise regression. Handle properties of fabrics were measured by universal test equipment (KES-F) and total prickle-score (TPS) values of the wear fabrics were determined by a group of panelists consisting of some textile experts. The optimum construction of neural network was investigated through the change of layer and neuron number. The results showed that the back-propagation network could predict the (TPS) values of wear fabric with a meaningful difference. These wear fabrics were used to show that the results of neural network were in good agreement with subjective test results.