A Method for Fault Diagnosis in Analog Circuits Based on Neural Network Information Fusion Technique and Wavelet Analysis
Peng Liang-yu · Microelectronics & Computer · 2009
A new method for fault diagnosis of analogue circuits based on neural network information fusion technique about dynamic supply current and output voltage is presented.Firstly,energy fault features of two kinds of different sampled signal are extracted,then they are normalization preprocessed and vector associated,finally,they are inputed neural network and trained.Simulation results illustrate that this method is better than single signal fault diagnosis and has many powerful features,such as diagnosing and locating faults quickly and exactly.