The use of artificial neural networks to estimate thermal resistance of knitted fabrics

This study aims to develop a model for the prediction of thermal resistance of fleece fabric by using regression analysis and artificial neural network technique. primarily fleece fabrics protect human body from heat loss during cold weather. its second purpose is to absorb sweat from human skin. fleece fabric is commonly used to make sweatshirts,trousers,and jackets for cold weather. higher thermal resistance of fleece is one of the main demands of users. many factors can influence the thermal resistance efficiency of fleece. we have used porosity,thickness of fabric,thermal conductivity of fabric,overall moisture management capacity,thermal absorptivity,percentage of cotton,and polyester and planner weight as independent variables for the prediction of thermal resistance of fleece fabric. we have found that there was a significant difference between regression and artificial neural network analysis in the selection of most significant factor. nevertheless,both models are significant. moreover,we have also found that there is a significant correlation between two most significant variables selected during regression analysis and artificial neural network. keeping all these in view,we can say that both models are capable of finding the thermal resistance of fabric despite the fact that artificial neural network techniques give better explanations.