GAN and CNN for imbalanced partial discharge pattern recognition in GIS
Abstract The convolutional neural network (CNN) achieves excellent performance in pattern recognition owing to its powerful automatic feature extraction capability and outstanding classification performance. However, the actual samples obtained are unbalanced, and accurate diagnoses are difficult fo...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2022-06-01
|
Series: | High Voltage |
Online Access: | https://doi.org/10.1049/hve2.12135 |
_version_ | 1811226431309479936 |
---|---|
author | Yanxin Wang Jing Yan Zhou Yang Qianzhen Jing Jianhua Wang Yingsan Geng |
author_facet | Yanxin Wang Jing Yan Zhou Yang Qianzhen Jing Jianhua Wang Yingsan Geng |
author_sort | Yanxin Wang |
collection | DOAJ |
description | Abstract The convolutional neural network (CNN) achieves excellent performance in pattern recognition owing to its powerful automatic feature extraction capability and outstanding classification performance. However, the actual samples obtained are unbalanced, and accurate diagnoses are difficult for the existing methods. A classification method for partial discharge (PD) pattern recognition in gas‐insulated switchgear (GIS) that uses a generative adversarial network (GAN) and CNN on unbalanced samples is proposed. First, a novel Wasserstein dual discriminator GAN is used to generate data to equalise the unbalanced samples. Second, a decomposed hierarchical search space is used to automatically construct an optimal diagnostic CNN. Finally, PD pattern recognition classification in GIS of the unbalanced samples is realised by the GAN and CNN. The experimental results show that the GAN and CNN methods proposed in this study have a pattern recognition accuracy of 99.15% on unbalanced samples, which is significantly higher than that obtained by other methods. Therefore, the method proposed in this study is more suitable for industrial applications. |
first_indexed | 2024-04-12T09:24:59Z |
format | Article |
id | doaj.art-b9796f48ca534c7c847c5ac1f630966b |
institution | Directory Open Access Journal |
issn | 2397-7264 |
language | English |
last_indexed | 2024-04-12T09:24:59Z |
publishDate | 2022-06-01 |
publisher | Wiley |
record_format | Article |
series | High Voltage |
spelling | doaj.art-b9796f48ca534c7c847c5ac1f630966b2022-12-22T03:38:31ZengWileyHigh Voltage2397-72642022-06-017345246010.1049/hve2.12135GAN and CNN for imbalanced partial discharge pattern recognition in GISYanxin Wang0Jing Yan1Zhou Yang2Qianzhen Jing3Jianhua Wang4Yingsan Geng5State Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong University Xi'an Shaanxi ChinaState Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong University Xi'an Shaanxi ChinaSchool of Computer Science Xi'an Jiaotong University Xi'an Shaanxi ChinaState Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong University Xi'an Shaanxi ChinaState Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong University Xi'an Shaanxi ChinaState Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong University Xi'an Shaanxi ChinaAbstract The convolutional neural network (CNN) achieves excellent performance in pattern recognition owing to its powerful automatic feature extraction capability and outstanding classification performance. However, the actual samples obtained are unbalanced, and accurate diagnoses are difficult for the existing methods. A classification method for partial discharge (PD) pattern recognition in gas‐insulated switchgear (GIS) that uses a generative adversarial network (GAN) and CNN on unbalanced samples is proposed. First, a novel Wasserstein dual discriminator GAN is used to generate data to equalise the unbalanced samples. Second, a decomposed hierarchical search space is used to automatically construct an optimal diagnostic CNN. Finally, PD pattern recognition classification in GIS of the unbalanced samples is realised by the GAN and CNN. The experimental results show that the GAN and CNN methods proposed in this study have a pattern recognition accuracy of 99.15% on unbalanced samples, which is significantly higher than that obtained by other methods. Therefore, the method proposed in this study is more suitable for industrial applications.https://doi.org/10.1049/hve2.12135 |
spellingShingle | Yanxin Wang Jing Yan Zhou Yang Qianzhen Jing Jianhua Wang Yingsan Geng GAN and CNN for imbalanced partial discharge pattern recognition in GIS High Voltage |
title | GAN and CNN for imbalanced partial discharge pattern recognition in GIS |
title_full | GAN and CNN for imbalanced partial discharge pattern recognition in GIS |
title_fullStr | GAN and CNN for imbalanced partial discharge pattern recognition in GIS |
title_full_unstemmed | GAN and CNN for imbalanced partial discharge pattern recognition in GIS |
title_short | GAN and CNN for imbalanced partial discharge pattern recognition in GIS |
title_sort | gan and cnn for imbalanced partial discharge pattern recognition in gis |
url | https://doi.org/10.1049/hve2.12135 |
work_keys_str_mv | AT yanxinwang ganandcnnforimbalancedpartialdischargepatternrecognitioningis AT jingyan ganandcnnforimbalancedpartialdischargepatternrecognitioningis AT zhouyang ganandcnnforimbalancedpartialdischargepatternrecognitioningis AT qianzhenjing ganandcnnforimbalancedpartialdischargepatternrecognitioningis AT jianhuawang ganandcnnforimbalancedpartialdischargepatternrecognitioningis AT yingsangeng ganandcnnforimbalancedpartialdischargepatternrecognitioningis |