Chaos Method for Analog Circuit Fault Diagnosis
Xinmin Zhao · Hu'nan Shifan Daxue xuebao. Ziran kexue ban · 2012
A systematic method of analog circuits fault diagnosis based on chaotic neural network is proposed in order to overcome the shortcomings that the selection of structure and weights are critical for neural networks(NN) when they are used for fault diagnosis.Chaos variables are applied in searching for neural network structure,in which node numbers of hidden layer and all weight parameters of neural network are in chaotic state.All neural network structure is dynamic.Then,a globally optimal or approximate globally optimal neural network structure is found according to performance standard from dynamic neural networks.Finally,feature vectors under certain states could be classified using the optimized neural network.Simulation results show that the method can be used in the fault diagnosis of analog circuits effectively and reliably.