Fault Diagnosis Method Of Analog Circuit Based On Radial Base Function Neural Network

With the rapid development of digital and analog circuit technology,circuit testing and fault diagnosis problems have become more and more important.Due to the continuous development of testing technology and fault diagnosis methods,it has become easier for people to identify and classify faults in the circuit under test(CUT).In recent years,neural network(NN)technology has become the main way to solve the problem of analog circuit fault diagnosis.This paper proposes a neural network method based on radial basis function(RBF),which can well solve the problem of fault diagnosis in analog circuits.The main contents of this paper are as follows:First,the background,significance,research object and problems to be solved of the research on analog circuit fault diagnosis are introduced.Then the neural network method based on radial basis function is introduced,which describes the characteristics of different fault types and can classify different faults.Secondly,in order to verify the fault diagnosis ability of the method proposed in this paper,a simulation study of the active bandpass filter circuit is carried out.Through MATLAB and PSPICE software for fault diagnosis simulation test and fault type data acquisition,PSPICE can model a series of circuit elements,mainly adopting analog circuit form for simulation analysis.Then,the radial basis function neural network method is used to carry out fault diagnosis simulation experiments on the two actual circuits.The two circuits are the FOUR OP-AMP low-pass filter circuit and the Sallen-Key band-pass filter circuit.The fault diagnosis process is shown in the article.The method proposed in this article can effectively locate the fault and classify the fault type.Finally,the method proposed in this paper is compared with back propagation(BP)neural network,support vector machine(SVM)and wavelet neural network and other methods to diagnose the same analog circuit.The comparison results show that the radial basis function neural network method has higher diagnostic accuracy and better performance.