PARAMETRIC FAULT LOCATION OF ELECTRICAL CIRCUIT USING SUPPORT VECTOR MACHINE

S. Osowski, T. Markiewicz, R. Salat

Abstract

The paper is concerned with the application of the Support Vector Machine to the discovering of the parametric fault in analog electrical circuits. The recognition of fault is based on the measurements of the accessible terminal voltage and current of the circuit at the set of frequencies. The SVM network fulfills the role of the recognizing system and of the classifier. The numerical results of recognition of faulty elements in the LC filter of the ladder network structure are presented and discussed in the paper.

Keywords

SVM classifiers, parametric fault detection, diagnosis of circuits

Download

PWC-2006-TC10-001u.pdf

DOI

-

IMEKO TC

TC10 - Measurement for Diagnostics, Optimization and Control

Back to the proceedings