Transformer dissolved gas analysis using least square support vector machine and bootstrap

Tang Wenhu, Shintemirov Almas, Q. H. Wu

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

15 Citations (Scopus)

Abstract

This paper presents a least square support vector machine (LS-SVM) approach to dissolved gas analysis (DGA) problems for power transformers. Two methods are employed to improve the diagnosis accuracy for DGA analysis. Firstly, bootstrap preprocessing is utilised to equalise the sample numbers for different fault types. Then, the preprocessed samples are inputted to a classier for fault classification. For comparison purposes, four classifiers are utilised, i.e. artificial neural network (ANN), K-nearest neighbour (ANN), simple SVM and LS-SVM. The classification accuracy of LS-SVM is then compared with the ones of ANN, KNN and a simple SVM. The results indicate that the LS-SVM approach can significantly improve the diagnosis accuracies for transformer fault classification.

Original languageEnglish
Title of host publicationProceedings of the 26th Chinese Control Conference, CCC 2007
Pages482-486
Number of pages5
DOIs
Publication statusPublished - Dec 1 2007
Event26th Chinese Control Conference, CCC 2007 - Zhangjiajie, China
Duration: Jul 26 2007Jul 31 2007

Publication series

NameProceedings of the 26th Chinese Control Conference, CCC 2007

Other

Other26th Chinese Control Conference, CCC 2007
CountryChina
CityZhangjiajie
Period7/26/077/31/07

Keywords

  • Bootstrap
  • Dissolved gas analysis
  • Least square support vector machine
  • Transformer

ASJC Scopus subject areas

  • Computer Science Applications
  • Control and Systems Engineering
  • Applied Mathematics
  • Modelling and Simulation

Fingerprint Dive into the research topics of 'Transformer dissolved gas analysis using least square support vector machine and bootstrap'. Together they form a unique fingerprint.

  • Cite this

    Wenhu, T., Almas, S., & Wu, Q. H. (2007). Transformer dissolved gas analysis using least square support vector machine and bootstrap. In Proceedings of the 26th Chinese Control Conference, CCC 2007 (pp. 482-486). [4347139] (Proceedings of the 26th Chinese Control Conference, CCC 2007). https://doi.org/10.1109/CHICC.2006.4347139