摘要
A method for robust analog fault diagnosis using hybrid neural networks is proposed. The primary focus of the paper is to provide robust diagnosis using a mechanism to deal with the problem of element tolerances and reduce testing time. The proposed approach is based on the fault dictionary diagnosis method and backward propagation neural network (BPNN) and the adaptive resonance theory (ART) neural network. Simulation results show that the method is robust and fast for fault diagnosis of analog circuits with tolerances.
A method for robust analog fault diagnosis using hybrid neural networks is proposed. The primary focus of the paper is to provide robust diagnosis using a mechanism to deal with the problem of element tolerances and reduce testing time. The proposed approach is based on the fault dictionary diagnosis method and backward propagation neural network (BPNN) and the adaptive resonance theory (ART) neural network. Simulation results show that the method is robust and fast for fault diagnosis of analog circuits with tolerances.
作者
Ying Deng1, Yigang He1 , Xu He2 ,Yichuang Sun3 1. College of Electrical and Information Engineering,Hunan University, 410082, Changsha, Hunan, China 2. Department of Computer Science, Hunan University, 410082, Changsha, Hunan, China 3. Department of Ele
出处
《湖南大学学报(自然科学版)》
EI
CAS
CSCD
2000年第S2期133-138,共6页
Journal of Hunan University:Natural Sciences