A Model Construction about Predicting the Rate of Dimensional Change after Wash of Fabric Composites

Abstract:

This article reports the construction of a model for predicting the rate of dimensional change of fabric composites after wash. The mechanical properties of the fabrics and fused interlinings were tested in FAST system and KES system and the parameters of fabrics and interlinings are analyzed by a objective mathematic method. Through this method, eight principal components are obtained. A BP neural network with a single hidden layer is constructed including eight input nodes, six hidden nodes and one output nodes. During training the network with a back-propagation algorithm, the eight principal components are used as input parameters, while the rate of dimensional change are used as output parameters. All original data are preprocessed and the learning process is successful in achieving a global error minimum. The the rate of dimensional change can be predicted with this training network and there is a good agreement between the predicted and tested values.

• Periodical: Advanced Materials Research (Volumes 332-334)
• Pages: 496-499
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.332-334.496
• Online since: September 2011
• Authors: Jing Wang, Jin Ying Song, Ai Qing Tang
• Keywords: Fabric Composite, Neural Network (NN), Principal Component, Rate of Dimensional Change

References

[1] J, Fan., Leeuwner, W., and Hunter, L.: Textile Res.J. 67(2) (1997), p.137

[2] J, Fan., Leeuwner, W., and Hunter, L.: Textile Res.J. 67(3) (1997), p.194

[3] J, Fan., Leeuwner, W., and Hunter, L.: Textile Res.J. 67(4) (1997), p.258

[4] J, Fan., and Y, N.NG.: Textile Res.J 71(8) (2001), p.661

[5] Jeong, S.H., and Jung, H.Kim.: Textile Res. J.70(11) (2000), p.1005

[6] Jeong, S.H., and Barker, R.L.: Journal of Korea Fiber Society.33(1996), p.83

[7] Jeong, S.H., Choi, Y.Y., and Barker, R.L.: Journal of Korea Fiber Society.33(1996), p.905