Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Hybrid feature selection approach for power transformer fault diagnosis based on support vector machine and genetic algorithm

Journal Article · · IET Generation, Transmission, & Distribution
; ; ; ; ; ;
To further improve fault diagnosis accuracy, a new hybrid feature selection approach combined with a genetic algorithm (GA) and support vector machine (SVM) is presented in this study. Adaptive synthetic technique and arctangent transformation method are adopted to improve the statistical property of the training set (IEC TC10 dataset). Five filter methods based on different evaluation metrics are employed to rank 48 input features derived from dissolved gas analysis (DGA). Then, feature combination methods are applied to aggregate feature ranks and form a lower-dimension candidate feature subset. The GA-SVM model is implemented to optimise parameters and select optimal feature subsets. 5-fold cross-validation accuracy of the GA-SVM is used to evaluate fault diagnosis capability of feature subsets and finally, a novel subset is determined as the optimal feature subset. Accuracy comparison manifests the superiority of the optimal feature subsets over that of conventional approaches. Besides, generalisation and robustness of the optimal subset are validated by testing DGA samples from the local power utility. Results indicate that the optimal feature subset obtained by the proposed method can significantly improve the accuracies of power transformer fault diagnosis.
Research Organization:
Argonne National Laboratory (ANL)
Sponsoring Organization:
National High Technology Research and Development Program of China; USDOE Office of Energy Efficiency and Renewable Energy (EERE)
DOE Contract Number:
AC02-06CH11357
OSTI ID:
1577086
Journal Information:
IET Generation, Transmission, & Distribution, Journal Name: IET Generation, Transmission, & Distribution Journal Issue: 21 Vol. 12; ISSN 1751-8687
Country of Publication:
United States
Language:
English

References (24)

Optimal scheduling for maintenance period of generating units using a hybrid scatter-genetic algorithm journal January 2015
Learning from Imbalanced Data journal September 2009
A review of faults detectable by gas-in-oil analysis in transformers journal May 2002
Support vector machine with genetic algorithm for forecasting of key-gas ratios in oil-immersed transformer journal April 2009
Using dissolved gas analysis results to detect and isolate the internal faults of power transformers by applying a fuzzy logic method journal July 2017
Interpretation of DGA for transformer fault diagnosis with complementary SaE-ELM and arctangent transform journal February 2016
Optimal dissolved gas ratios selected by genetic algorithm for power transformer fault diagnosis based on support vector machine journal April 2016
LIBSVM: A library for support vector machines journal April 2011
Hybrid RVM–ANFIS algorithm for transformer fault diagnosis journal September 2017
Fault Diagnosis of Power Transformers Using Computational Intelligence: A Review journal January 2012
Statistical Machine Learning and Dissolved Gas Analysis: A Review journal October 2012
Comprehensive approach for hybrid AC/DC distribution network planning using genetic algorithm journal November 2017
Dissolved gas analysis method based on novel feature prioritisation and support vector machine journal September 2014
Fault diagnosis of power transformer based on multi-layer SVM classifier journal July 2005
Selection of Most Relevant Input Parameters Using Waikato Environment for Knowledge Analysis for Gene Expression Programming Based Power Transformer Fault Diagnosis journal November 2014
Diagnosis of Power Transformer Faults Based on Multi-layer Support Vector Machine Hybridized with Optimization Methods journal October 2016
Recent advances on SVM based fault diagnosis and process monitoring in complicated industrial processes journal January 2016
Interpretation of gas-in-oil analysis using new IEC publication 60599 and IEC TC 10 databases journal March 2001
Fault diagnosis of power transformers using multi-class least square support vector machines classifiers with particle swarm optimisation journal January 2011
Improvement of power transformer insulation diagnosis using oil characteristics data preprocessed by SMOTEBoost technique journal October 2014
Hybrid feature selection by combining filters and wrappers journal July 2011
A review of feature selection techniques in bioinformatics journal August 2007
A new fault diagnostic technique in oil-filled electrical equipment; the dual of Duval triangle journal December 2016
A Review of Dissolved Gas Analysis in Power Transformers journal January 2012

Similar Records

Developing a new transformer fault diagnosis system through evolutionary fuzzy logic
Journal Article · Mon Mar 31 23:00:00 EST 1997 · IEEE Transactions on Power Delivery · OSTI ID:492195
An Integrated Method of ANFIS and Dempster-Shafer Theory for Fault Diagnosis of Power Transformer
Journal Article · Wed Jan 31 23:00:00 EST 2018 · IEEE Transactions on Dielectrics and Electrical Insulation · OSTI ID:1489758
An expert system for transformer fault diagnosis using dissolved gas analysis
Journal Article · Thu Dec 31 23:00:00 EST 1992 · IEEE Transactions on Power Delivery (Institute of Electrical and Electronics Engineers); (United States) · OSTI ID:6502944

Related Subjects