Analog Circuit Soft Fault Diagnosis based on PCA and PSO-SVM

Abstract

Regarding to the complexity and diversity of analog circuit fault, a principal component analysis(PCA) and particle swarm optimization(PSO) support vector machine(SVM) analog circuit fault diagnosis method is proposed. It uses principal component analysis and data normalization as preprocessing, then reduced dimension fault feature is putted into support vector machine to diagnosis, and particle swarm optimization is used to optimize the penalty parameters and the kernel parameters of SVM, that improve the recognition rate of the fault diagnosis. The simulation results show that the proposed diagnosis model can perform analog circuit fault diagnosis effectively, and has higher fault diagnosis rates.

Analog Circuit Fault Diagnosis Method Based on Preferred Wavelet Packet and ELM

“…In order to extract the effective features of the circuit, we must choose the optimal wavelet basis for wavelet packet decomposition. Therefore, this paper proposes the concept of feature deviation as the selection measure to determine the optimal wavelet base, which is defined as: the deviation between the fault feature and the normal state feature can be calculated by formula (11). …”

“…The support vector machine based on statistical learning theory has improved its generalization performance compared with traditional neural networks. However, due to the need to specify the kernel function and kernel parameters, the application of SVM is seriously restricted [11][12] .…”

Wavelet-Based Feature Extraction in Fault Diagnosis for Biquad High-Pass Filter Circuit

“…Some researchers have used various fault information content as a measure to extract the fault features, such as information cost function [22], sensitivity of characteristic parameter [23], feature departure degree [24], and principle based on minimum redundancy maximum relevance [25]. These approaches, however, usually require various types of faults posterior probability distribution functions and the density functions of observed values, which are usually hard to obtain.…”

Automatic parametric fault detection in complex analog systems based on a method of minimum node selection

“…It also provides sufficient classification results in noisy conditions. The objects presented by Rutkowski and Grzechca (2009), Guo et al (2014) or Sun et al (2013) are characterized by a small number of parameters (from 7 to 16 elements). The SVM presented there is used for classification purposes in fault detection.…”

“…The SVM classifier has been used in diagnostics of electronic circuits (Tadeusiewicz and Korzybski, 2000;Rutkowski and Grzechca, 2009;Guo et al, 2014;Sun et al, 2013;Bilski, 2011;Sałat and Osowski, 2011). Although this tool is versatile to work with data of various complexities, the process of optimal kernel selection and its parameters must be conducted for each system separately (Bilski, 2011).…”