Title :
Prediction of Fabric Subjective Thermal-wet Comfort Properties Based on BP Neural Network
Author :
Baozhu, Ke ; Cong Shan
Author_Institution :
Fashion Inst., Shanghai Univ. of Eng. Sci., Shanghai, China
Abstract :
In this paper, six thermal-wet comfort objective evaluation indexes of 36 kinds of knitted fabrics such as air permeability rate, moisture transmission rate, wicking height, moisture regain rate, moisture diffusion rate and thermal resistance were tested and analyzed. And then the 36 kinds of knitted fabrics were made into the same style clothes. Four thermal-wet comfort subjective evaluation indexes of these clothes such as hot feeling, wet feeling, sticky feeling and cold feeling after exercise were assessed by human body wearing tests. 28 kinds of the fabrics were selected to establish the prediction model between the objective evaluation indexes and the subjective evaluation indexes based on BP neural network. The other 8 kinds of the fabrics were used to validate the accuracy of the model. The results showed that the model can effectively predict the fabric subjective thermal-wet comfort properties.
Keywords :
backpropagation; fabrics; neural nets; production engineering computing; protective clothing; BP neural network; cold feeling; fabric subjective thermal wet comfort properties; hot feeling; human body; knitted fabrics; sticky feeling; thermal-wet comfort objective evaluation indexes; wet feeling; Artificial neural networks; Fabrics; Indexes; Moisture; Predictive models; Thermal resistance; Training; BP neural network; prediction; thermal-wet comfort;
Conference_Titel :
Artificial Intelligence and Computational Intelligence (AICI), 2010 International Conference on
Conference_Location :
Sanya
Print_ISBN :
978-1-4244-8432-4
DOI :
10.1109/AICI.2010.59