Failure Rate Prediction of a Power Transformer: A Decomposition-Based Bayesian Deep Learning Method

Power transformers, as essential equipment for electricity transmission, may fail due to insulation degradation. Predicting the failure rate of power transformers precisely is beneficial to decision-making. Currently, uncertainties of the prediction have not been deeply discussed. Besides, predictio...

Full description

Saved in:
Bibliographic Details
Main Authors: Weixin Zhang, Changzheng Shao, Wei Huang, Bo Hu, Jiahao Yan, Kaigui Xie, Maosen Cao, Zhengze Wei
Format: Article
Language:English
Published: China electric power research institute 2025-01-01
Series:CSEE Journal of Power and Energy Systems
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10026211/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770742934142976
author Weixin Zhang
Changzheng Shao
Wei Huang
Bo Hu
Jiahao Yan
Kaigui Xie
Maosen Cao
Zhengze Wei
author_facet Weixin Zhang
Changzheng Shao
Wei Huang
Bo Hu
Jiahao Yan
Kaigui Xie
Maosen Cao
Zhengze Wei
author_sort Weixin Zhang
collection DOAJ
description Power transformers, as essential equipment for electricity transmission, may fail due to insulation degradation. Predicting the failure rate of power transformers precisely is beneficial to decision-making. Currently, uncertainties of the prediction have not been deeply discussed. Besides, prediction accuracy is not high enough. This paper proposes a decomposition-based Bayesian deep learning (BDL) method to predict the failure rate of power transformers. Both the model uncertainty related to distribution of the model's weights and the inherent uncertainty associated with random noise can be captured by BDL. Uncertainties of prediction results are depicted with confidence intervals. Moreover, prediction accuracy is improved using variational mode decomposition (VMD). Numerical experiments have been carried out based on oil chromatographic data of power transformers from the Chongqing grid to validate effectiveness of the proposed method.
format Article
id doaj-art-031ed608a49c41fca859cdd33ba25b60
institution DOAJ
issn 2096-0042
language English
publishDate 2025-01-01
publisher China electric power research institute
record_format Article
series CSEE Journal of Power and Energy Systems
spelling doaj-art-031ed608a49c41fca859cdd33ba25b602025-08-20T03:02:54ZengChina electric power research instituteCSEE Journal of Power and Energy Systems2096-00422025-01-011141596160910.17775/CSEEJPES.2021.0488010026211Failure Rate Prediction of a Power Transformer: A Decomposition-Based Bayesian Deep Learning MethodWeixin Zhang0Changzheng Shao1Wei Huang2Bo Hu3Jiahao Yan4Kaigui Xie5Maosen Cao6Zhengze Wei7School of Electrical Engineering, Chongqing University,State Key Laboratory of Power Transmission Equipment Technology,Chongqing,China,400044School of Electrical Engineering, Chongqing University,State Key Laboratory of Power Transmission Equipment Technology,Chongqing,China,400044School of Electrical Engineering, Chongqing University,State Key Laboratory of Power Transmission Equipment Technology,Chongqing,China,400044School of Electrical Engineering, Chongqing University,State Key Laboratory of Power Transmission Equipment Technology,Chongqing,China,400044School of Electrical Engineering, Chongqing University,State Key Laboratory of Power Transmission Equipment Technology,Chongqing,China,400044School of Electrical Engineering, Chongqing University,State Key Laboratory of Power Transmission Equipment Technology,Chongqing,China,400044School of Electrical Engineering, Chongqing University,State Key Laboratory of Power Transmission Equipment Technology,Chongqing,China,400044School of Electrical Engineering, Chongqing University,State Key Laboratory of Power Transmission Equipment Technology,Chongqing,China,400044Power transformers, as essential equipment for electricity transmission, may fail due to insulation degradation. Predicting the failure rate of power transformers precisely is beneficial to decision-making. Currently, uncertainties of the prediction have not been deeply discussed. Besides, prediction accuracy is not high enough. This paper proposes a decomposition-based Bayesian deep learning (BDL) method to predict the failure rate of power transformers. Both the model uncertainty related to distribution of the model's weights and the inherent uncertainty associated with random noise can be captured by BDL. Uncertainties of prediction results are depicted with confidence intervals. Moreover, prediction accuracy is improved using variational mode decomposition (VMD). Numerical experiments have been carried out based on oil chromatographic data of power transformers from the Chongqing grid to validate effectiveness of the proposed method.https://ieeexplore.ieee.org/document/10026211/Bayesian deep learningdissolved gas analysisfailure rate predictionlong short-term memoryvariational mode decomposition
spellingShingle Weixin Zhang
Changzheng Shao
Wei Huang
Bo Hu
Jiahao Yan
Kaigui Xie
Maosen Cao
Zhengze Wei
Failure Rate Prediction of a Power Transformer: A Decomposition-Based Bayesian Deep Learning Method
CSEE Journal of Power and Energy Systems
Bayesian deep learning
dissolved gas analysis
failure rate prediction
long short-term memory
variational mode decomposition
title Failure Rate Prediction of a Power Transformer: A Decomposition-Based Bayesian Deep Learning Method
title_full Failure Rate Prediction of a Power Transformer: A Decomposition-Based Bayesian Deep Learning Method
title_fullStr Failure Rate Prediction of a Power Transformer: A Decomposition-Based Bayesian Deep Learning Method
title_full_unstemmed Failure Rate Prediction of a Power Transformer: A Decomposition-Based Bayesian Deep Learning Method
title_short Failure Rate Prediction of a Power Transformer: A Decomposition-Based Bayesian Deep Learning Method
title_sort failure rate prediction of a power transformer a decomposition based bayesian deep learning method
topic Bayesian deep learning
dissolved gas analysis
failure rate prediction
long short-term memory
variational mode decomposition
url https://ieeexplore.ieee.org/document/10026211/
work_keys_str_mv AT weixinzhang failureratepredictionofapowertransformeradecompositionbasedbayesiandeeplearningmethod
AT changzhengshao failureratepredictionofapowertransformeradecompositionbasedbayesiandeeplearningmethod
AT weihuang failureratepredictionofapowertransformeradecompositionbasedbayesiandeeplearningmethod
AT bohu failureratepredictionofapowertransformeradecompositionbasedbayesiandeeplearningmethod
AT jiahaoyan failureratepredictionofapowertransformeradecompositionbasedbayesiandeeplearningmethod
AT kaiguixie failureratepredictionofapowertransformeradecompositionbasedbayesiandeeplearningmethod
AT maosencao failureratepredictionofapowertransformeradecompositionbasedbayesiandeeplearningmethod
AT zhengzewei failureratepredictionofapowertransformeradecompositionbasedbayesiandeeplearningmethod