Fault detection in complex analog circuits using Support Vector Machines

Adrian Bilski, Jacek Wojciechowski

Abstract

The aim of this paper is to bring the reader closer to the diagnostics of complex analog systems with parametric faults, using Support Vector Machine (SVM) as a tool for fault location. The results of diagnostics of a video enhancer and two low-pass filters with the help of SVM network are presented, and various SVM kernel functions tested. A strategy for finding the optimal kernels and their parameters for the particular system under test is proposed. This paper is focused on linear systems diagnostics.

Keywords

Complex analog systems, Support Vector Machine, parametric fault detection

Download

IMEKO-TC10-2013-008.pdf

DOI

-

IMEKO TC

TC10 - Measurement for Diagnostics, Optimization and Control

Back to the proceedings