Fault classification using SVM

Mani Swetha Mandava, Devika Jadhav, Roshan Ramakrishna Naik

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Analog circuits are abundantly used in today's world. Unexpected failures might result in grave repercussions which is why their fault diagnosis is of utmost importance. We put forward an innovative fault classifier technique using Support Vector Machines (SVM) to identify whether the circuit is functioning properly and to identify the fault. We first train the SVM with sample voltages of a simple RLC circuit obtained by simulating this circuit on MATLAB. Fault classification can then be done accurately and precisely by the SVM. Simulations are done on MATLAB to calculate the accuracy and precision of this system.

Original languageEnglish
Title of host publicationProceeding - 2015 IEEE International Circuits and Systems Symposium, ICSyS 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages17-21
Number of pages5
ISBN (Electronic)9781479917310
DOIs
Publication statusPublished - 27-01-2016
Externally publishedYes
EventIEEE International Circuits and Systems Symposium, ICSyS 2015 - Langkawi, Malaysia
Duration: 02-09-201504-09-2015

Conference

ConferenceIEEE International Circuits and Systems Symposium, ICSyS 2015
CountryMalaysia
CityLangkawi
Period02-09-1504-09-15

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Instrumentation

Fingerprint Dive into the research topics of 'Fault classification using SVM'. Together they form a unique fingerprint.

Cite this