Analog circuits fault diagnosis based on serial support vector multi-classifier

A support vector multiclassification methodology was proposed. Several binary support vector binary classifiers, each of which equipped with a feature extractor based on kernel principle components analysis, were organized in a serial structure. Its training process and classification algorithm were described. The BP net classifier, RBF net classifier, traditional support vector multi-classifier and serial support vector multi-classifier (SSVC) were used for analog circuit fault diagnosis. Compared with BP net and RBF net classifiers, support vector approach has significantly better classification accuracy on test patterns. The SSVC affords top diagnosis accuracy among these classifiers and outperforms traditional support vector multi-calssifier dramatically in training and classification efficiency.