A Predicting Model Construction of Bond Qualities after Wash of Fabric Composites
This article reports the construction of principal-BP neural network for predicting the bond quality of fabric composites after wash. The parameters of fabrics and interlinings are analyzed by principal analysis and eight principal components are obtained in the first article. A BP neural network with a single hidden layer is constructed including eight input nodes, six hidden nodes and four output nodes. During training the network with a backpropagation algorithm, the eight principal components are used as input parameters, while bond qualities are used as output parameters. The weight values are modified with momentum and learning rate selfadaptation to solve the two defects of the BP network. All original data are preprocessed and the learning process is successful in achieving a global error minimum. The bond qualities can be predicted with this training network and there is a good agreement between the predicted and tested values.
principal component BP neural network fabric composite bond quality
WANG Jing
Art College, Shandong University of Technology, Zibo Shandong 255049, P.R.China Fashion institute, Donghua University, Shanghai 200051, P.R.China
国际会议
The 12th International Wool Research Conference(第十二届国际羊毛会议12th IWRC)
上海
英文
757-760
2010-10-19(万方平台首次上网日期,不代表论文的发表时间)