Fault Diagnosis Optimization Method of Analog Circuit Based on Matrix Model

Abstract

In view of the limitations of artificial neural network, support vector machine (SVM) and other artificial intelligence algorithms have limitations: they need a large number of training samples, and the algorithm takes a long time. This paper proposes an analog circuit fault diagnosis method based on matrix feature analysis. The method establishes an output response matrix in which the elements change when the circuit fails. By comparing the difference between the fault-free output matrix and the fault output matrix, faults can be diagnosed. According to the matrix theory, the spectral radius of the matrix and the maximum singular value of the perturbation matrix are used to describe the difference. In a single fault mode, conic curve fitting can realize fault diagnosis, fault location and parameter identification. The international standard circuit Sallen_Key circuit is taken as the verification object, and the results show that the method can judge the fault of analog circuit and locate the fault well. By this method, the fault diagnosis rate is as high as 99.85%, and the circuit can be measured by locating the fault to determine the measurable components of the circuit.