A Novel Approach of Analog Fault Classification Using a Support Vector Machines Classifier

Abstract

In order to make the analog fault classification more accurate, we present a method based on the Support Vector Machines Classifier (SVC) with wavelet packet decomposition (WPD) as a preprocessor. In this paper, the conventional one-against-rest SVC is resorted to perform a multi-class classification task because this classifier is simple in terms of training and testing. However, this SVC needs all decision functions to classify the query sample. In our study, this classifier is improved to make the fault classification task more fast and efficient. Also, in order to reduce the size of the feature samples, the wavelet packet analysis is employed. In our investigations, the wavelet analysis can be used as a tool of feature extractor or noise filter and this preprocessor can improve the fault classification resolution of the analog circuits. Moreover, our investigation illustrates that the SVC can be applicable to the domain of analog fault classification and this novel classifier can be viewed as an alternative for the back-propagation (BP) neural network classifier.

A Novel Approach To Diagnosis Of Analog Circuit Incipient Faults Based On KECA And OAO LSSVM

“…Let us assume the tolerances of resistors and capacitors are 5%. Generally, a component is considered to be faulty when its value has deviated from its nominal value by about 50% [2−16], [18,19], [21−23], therefore a component with a 25% deviation from its nominal value is considered to indicate an incipient fault in the work. 100 output sample data for each fault class have been collected.…”

“…During the recent few years, there has been useful research into the analog circuit fault diagnosis at board, system, and chip levels [1−16], [18,19], [21−23]. The feature extraction and classifier selection are two main problems which need to be addressed in the analog circuit fault diagnosis.…”

“…However, it has some disadvantages, as: failing to obtain local optimal solution, a low convergence rate, and poor generalization. The support vector machine (SVM) [17] accounts for the trade-off between learning ability and generalizing ability by minimizing the structure risk, and has been used to the analog circuit fault diagnosis [18,19]. The least squares support vector machine (LSSVM) enhances the SVM formulation by adopting a least-squares linear system as the loss function [20], which can reduce the computation complexity and improve the performance.…”

Histogram of Oriented Gradients with Cell Average Brightness for Human Detection

“…The SVM is a well-known method of classification with a solid mathematical background, where the learning phase is reasonably short, but the classification stage requires a significant number of multiplications and additions. The SVM has been successfully applied to many different problems [7,8]. The boosting classifier consists of a cascade of "weak" classifiers, where early stages of the cascade reject most negative data.…”

Diagnosis of Incipient Faults in Nonlinear Analog Circuits

“…It is more difficult to diagnose soft faults than hard faults because the features of the soft fault cases of the CUT are not significant. In recent years, many methods such as the fault dictionary method [5,6], the neural network [7][8][9][10], fuzzy analysis [11,12], the FNLP method [13], the wavelet preprocessing [14], the test-point node selection [15] , PCA method [16] and the support vector machine algorithm [17][18][19] have been presented for fault diagnosis of analog circuits.…”