Wavelet neural network based fault diagnosis in nonlinear analog circuits

doi:10.1016/S1004-4132(06)60089-3

Journal of Systems Engineering and Electronics ›› 2006, Vol. 17 ›› Issue (3): 521-526.doi: 10.1016/S1004-4132(06)60089-3

出版日期:2006-09-25 发布日期:2006-09-25

Wavelet neural network based fault diagnosis in nonlinear analog circuits

Yin Shirong, Chen Guangju & Xie Yongle

School of Automation Engineering, Univ. of Electronic Science and Technology of China, Chengdu 610054, P. R. China

Online:2006-09-25 Published:2006-09-25

摘要/Abstract

Abstract:

The theories of diagnosing nonlinear analog circuits by means of the transient response testing are studied. Wavelet analysis is made to extract the transient response signature of nonlinear circuits and compress the signature dada. The best wavelet function is selected based on the between-category total scatter of signature. The

fault dictionary of nonlinear circuits is constructed based on improved back-propagation (BP) neural network. Experimental results demonstrate that the method proposed has high diagnostic sensitivity and fast fault identification

and deducibility.

Key words: fault diagnosis')">

fault diagnosis,

')">neural networks