Analog circuit fault diagnosis using wavelet feature optimization approach

Wavelet analysis based analog circuit fault detecting sensitivity and feature extraction optimization methods are studied. Good localization on time-frequency domain of wavelet transformation provides better feature representation for faulty circuits than unitary time or frequency domain analysis. However, different wavelets express diverse resolution for fault recognition. Root mean square (RMS) score is proposed for measuring fault detecting sensitivity of wavelets for analog circuits in this paper. According to separating distance for classification, a measure criterion is presented for optimal wavelet basis selection, which leads to acquire better fault feature extraction. Neural network classifiers are constructed to classify various faults of a benchmark circuit. The fault classes can be separated more easily with fault features extracted by wavelet optimally chosen. Experiments were implemented for five wavelets in fault detection and identification. The experimental results show that this method can effectively improve fault diagnosis accuracy.