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

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
Externally publishedYes
Event2009 IEEE Power and Energy Society General Meeting, PES '09 - Calgary, AB, Canada
Duration: Jul 26 2009Jul 30 2009

Other

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

Fingerprint

Gas fuel analysis
Genetic programming
Power transformers
Feature extraction
Support vector machines
Classifiers
Neural networks

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

Cite this

Shintemirov, A., Tang, W. H., Wu, Q. H., & Fitch, J. (2009). Genetic programming feature extraction with bootstrap for dissolved gas analysis of power transformers. In 2009 IEEE Power and Energy Society General Meeting, PES '09 [5275606] https://doi.org/10.1109/PES.2009.5275606

Genetic programming feature extraction with bootstrap for dissolved gas analysis of power transformers. / Shintemirov, A.; Tang, W. H.; Wu, Q. H.; Fitch, J.

2009 IEEE Power and Energy Society General Meeting, PES '09. 2009. 5275606.

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

Shintemirov, A, Tang, WH, Wu, QH & Fitch, J 2009, Genetic programming feature extraction with bootstrap for dissolved gas analysis of power transformers. in 2009 IEEE Power and Energy Society General Meeting, PES '09., 5275606, 2009 IEEE Power and Energy Society General Meeting, PES '09, Calgary, AB, Canada, 7/26/09. https://doi.org/10.1109/PES.2009.5275606
Shintemirov A, Tang WH, Wu QH, Fitch J. Genetic programming feature extraction with bootstrap for dissolved gas analysis of power transformers. In 2009 IEEE Power and Energy Society General Meeting, PES '09. 2009. 5275606 https://doi.org/10.1109/PES.2009.5275606
Shintemirov, A. ; Tang, W. H. ; Wu, Q. H. ; Fitch, J. / Genetic programming feature extraction with bootstrap for dissolved gas analysis of power transformers. 2009 IEEE Power and Energy Society General Meeting, PES '09. 2009.
@inproceedings{b26849c64a7e41f0a574680f84524ad9,
title = "Genetic programming feature extraction with bootstrap for dissolved gas analysis of power transformers",
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.",
keywords = "Bootstrap, Dissolved gas analysis, Fault classification, Feature extraction, Genetic programming, K-nearest neighbor, Neural networks, Power transformer, Support vector machine",
author = "A. Shintemirov and Tang, {W. H.} and Wu, {Q. H.} and J. Fitch",
year = "2009",
doi = "10.1109/PES.2009.5275606",
language = "English",
isbn = "9781424442416",
booktitle = "2009 IEEE Power and Energy Society General Meeting, PES '09",

}

TY - GEN

T1 - Genetic programming feature extraction with bootstrap for dissolved gas analysis of power transformers

AU - Shintemirov, A.

AU - Tang, W. H.

AU - Wu, Q. H.

AU - Fitch, J.

PY - 2009

Y1 - 2009

N2 - 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.

AB - 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.

KW - Bootstrap

KW - Dissolved gas analysis

KW - Fault classification

KW - Feature extraction

KW - Genetic programming

KW - K-nearest neighbor

KW - Neural networks

KW - Power transformer

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=71849098817&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=71849098817&partnerID=8YFLogxK

U2 - 10.1109/PES.2009.5275606

DO - 10.1109/PES.2009.5275606

M3 - Conference contribution

SN - 9781424442416

BT - 2009 IEEE Power and Energy Society General Meeting, PES '09

ER -