TY - JOUR
T1 - Power transformer fault classification based on dissolved gas analysis by implementing bootstrap and genetic programming
AU - Shintemirov, A.
AU - Tang, W.
AU - Wu, Q. H.
N1 - Funding Information:
Manuscript received March 3, 2007; revised October 18, 2007 and March 3, 2008. Current version published December 22, 2008. The work of A. Shin-temirov was supported by the Center for International Programs of the Ministry of Education and Science of the Republic of Kazakhstan under the Presidential Bolashak Scholarship and the JSC “Science Fund” within the frame of the “Sharyktau” competition. This paper was recommended by Associate Editor Y. Jin.
Copyright:
Copyright 2009 Elsevier B.V., All rights reserved.
PY - 2009
Y1 - 2009
N2 - This paper presents an intelligent fault classification approach to power transformer dissolved gas analysis (DGA), dealing with highly versatile or noise-corrupted data. Bootstrap and genetic programming (GP) are implemented to improve the interpretation accuracy for DGA of power transformers. Bootstrap preprocessing is utilized to approximately equalize the sample numbers for different fault classes to improve subsequent fault classification with GP feature extraction. GP is applied to establish classification features for each class based on the collected gas data. 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 classification accuracies of the combined GP-ANN, GP-SVM, and GP-KNN classifiers are compared with the ones derived from ANN, SVM, and KNN classifiers, respectively. The test results indicate that the developed preprocessing approach can significantly improve the diagnosis accuracies for power transformer fault classification.
AB - This paper presents an intelligent fault classification approach to power transformer dissolved gas analysis (DGA), dealing with highly versatile or noise-corrupted data. Bootstrap and genetic programming (GP) are implemented to improve the interpretation accuracy for DGA of power transformers. Bootstrap preprocessing is utilized to approximately equalize the sample numbers for different fault classes to improve subsequent fault classification with GP feature extraction. GP is applied to establish classification features for each class based on the collected gas data. 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 classification accuracies of the combined GP-ANN, GP-SVM, and GP-KNN classifiers are compared with the ones derived from ANN, SVM, and KNN classifiers, respectively. The test results indicate that the developed preprocessing approach can significantly improve the diagnosis accuracies for power transformer fault classification.
KW - Bootstrap
KW - Dissolved gas analysis (DGA)
KW - Fault classification
KW - Feature extraction
KW - Genetic programming
KW - K-nearest neighbor (KNN)
KW - Neural networks
KW - Power transformer
KW - Support vector machine (SVM)
UR - http://www.scopus.com/inward/record.url?scp=58649122867&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=58649122867&partnerID=8YFLogxK
U2 - 10.1109/TSMCC.2008.2007253
DO - 10.1109/TSMCC.2008.2007253
M3 - Article
AN - SCOPUS:58649122867
VL - 39
SP - 69
EP - 79
JO - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews
JF - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews
SN - 1094-6977
IS - 1
ER -