Genetic programming feature extraction with bootstrap for dissolved gas analysis of power transformers

A. Shintemirov, W. H. Tang, Q. H. Wu, J. Fitch

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

1 Citation (Scopus)

Abstract

This paper discusses a feature extraction technique with genetic programming (GP) and bootstrap to improve interpretation accuracy of dissolved gas analysis (DGA) fault classification in power transformers, dealing with highly versatile or noise corrupted data. Initial DGA data are preprocessed with bootstrap to equalize the sample numbers for different fault classes, thus improving subsequent extraction of classification features with GP for each fault class. The features extracted with GP are then used as the inputs to artificial neural network (ANN), support vector machine (SVM) and K-nearest neighbor (KNN) classifiers for fault classification. The test results indicate that the proposed preprocessing approach can significantly improve the accuracy of power transformer fault classification based on DGA data.

Original languageEnglish
Title of host publication2009 IEEE Power and Energy Society General Meeting, PES '09
DOIs
Publication statusPublished - 2009
Event2009 IEEE Power and Energy Society General Meeting, PES '09 - Calgary, AB, Canada
Duration: Jul 26 2009Jul 30 2009

Publication series

Name2009 IEEE Power and Energy Society General Meeting, PES '09

Other

Other2009 IEEE Power and Energy Society General Meeting, PES '09
CountryCanada
CityCalgary, AB
Period7/26/097/30/09

Keywords

  • Bootstrap
  • Dissolved gas analysis
  • Fault classification
  • Feature extraction
  • Genetic programming
  • K-nearest neighbor
  • Neural networks
  • Power transformer
  • Support vector machine

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Genetic programming feature extraction with bootstrap for dissolved gas analysis of power transformers'. Together they form a unique fingerprint.

Cite this