Simulation Analysis of Fault Feature Extraction and Fusion for Analog Circuits Based on Information Fusion

摘要

In the fault diagnosis of analog circuit, the fault feature extraction is a very important link, and the results of the extraction directly impact on the accuracy of the final fault diagnosis. Because of the limitation of single fault feature extraction method, We used wavelet packet analysis and principal component analysis (PCA) to extract fault features simultaneously in this paper, and constructed three different feature vector fusion models. The results of the fusion models are then fed into a fault classifier model based on support vector machines to obtain the diagnostic results. The simulation results show that the proposed method can effectively improve the correctness of fault diagnosis compared with single fault feature extraction method.