An Adaptive Neural Network System for Prediction of Thermal Protective Performance of Fabrics

摘要：

Thermal protective performance is very importantfor heat protective clothing.Based on Matlab neuralnetwork toolbox,an adaptive BP neural network witha single hidden layer is constructed to predict thermalprotective performance of fabrics.The networkconsists of nine input nodes,eleven hidden nodes,andone output node.The input variables are fabric weight,thickness,weave,warp density,weft density,warpyarn count,weft yarn count,LOI,and Qmax,whileTPP rating is used as output variable.In the trainingprocess,the connection weights are modified withgradient-descent algorithm and adaptive learning rateto solve two defects of the BP network.After training,the predicted ability of the proposed neural network istested The results show a good correlation betweenpredicted values and experimental values.Theadaptive BP neural network can be applied to predictthe thermal protective performance of fabric.

作者: Zhiying Cui Weiyuan Zhang

作者单位: Fashion Institute,Donghua University,Shanghai,P.R.China,200051

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 837-841

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）