SVM Method for Diagnosing Analog Circuits Fault Based on Testability Analysis

In this paper a new method for diagnosing analog circuits fault is presented. The proposed method use the testability analysis of the circuit under test (CUT) to determine an optimal set of testable components (OSTC), and support vector machine (SVM) was introduced to identify the analog circuits fault. Testability analysis theoretically determines all of the diagnosable components. SVM has good characteristics of simple structure and strong generalization ability. Experimental results show that the proposed method for diagnosing analog circuits fault using testability analysis and SVM is superior to the others and to increase the fault diagnosis accuracy.