Recognition of partial discharge in GIS based on image feature fusion
Partial discharge (PD) is a significant electrical fault in gas-insulated switchgear (GIS), with various types posing different risks to insulation. Accurate identification of PD types is essential for enhancing GIS management and ensuring the reliability of electrical grids. This study proposes a n...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2024-10-01
|
| Series: | AIMS Energy |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/energy.2024052 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590280595865600 |
|---|---|
| author | Ziqiang Xu Honghua Xu Chao Yuan Shoulong Chen Yini Chen |
| author_facet | Ziqiang Xu Honghua Xu Chao Yuan Shoulong Chen Yini Chen |
| author_sort | Ziqiang Xu |
| collection | DOAJ |
| description | Partial discharge (PD) is a significant electrical fault in gas-insulated switchgear (GIS), with various types posing different risks to insulation. Accurate identification of PD types is essential for enhancing GIS management and ensuring the reliability of electrical grids. This study proposes a novel approach for PD identification in GIS integrating completed local binary pattern (CLBP) feature extraction, feature engineering, and an optimized support vector machine (SVM). PD faults were simulated in GIS and phase-resolved pulse sequence (PRPS) data for four different forms of PD were gathered. CLBP was used to extract image features, and then the support vector machine recursive feature elimination (SVM-RFE) algorithm was used to evaluate feature importance. Then, linear discriminant analysis (LDA) was used to fuse the selected features and reduce redundancy. The fused features were classified using a bald eagle search algorithm combined with differential evolution (IBES)-optimized SVM, achieving a recognition accuracy of 99.38%. The results indicate that the proposed method effectively distinguishes between different PD PRPS patterns in GIS. |
| format | Article |
| id | doaj-art-b7c1afeebcc3409681e27fb907a0968f |
| institution | Kabale University |
| issn | 2333-8334 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | AIMS Energy |
| spelling | doaj-art-b7c1afeebcc3409681e27fb907a0968f2025-01-24T01:35:07ZengAIMS PressAIMS Energy2333-83342024-10-011261096111210.3934/energy.2024052Recognition of partial discharge in GIS based on image feature fusionZiqiang Xu0Honghua Xu1Chao Yuan2Shoulong Chen3Yini Chen4Nanjing Power Supply Company, State Grid Jiangsu Electric Power Co., Ltd, Nanjing 210000, ChinaNanjing Power Supply Company, State Grid Jiangsu Electric Power Co., Ltd, Nanjing 210000, ChinaNanjing Power Supply Company, State Grid Jiangsu Electric Power Co., Ltd, Nanjing 210000, ChinaNanjing Power Supply Company, State Grid Jiangsu Electric Power Co., Ltd, Nanjing 210000, ChinaNanjing Power Supply Company, State Grid Jiangsu Electric Power Co., Ltd, Nanjing 210000, ChinaPartial discharge (PD) is a significant electrical fault in gas-insulated switchgear (GIS), with various types posing different risks to insulation. Accurate identification of PD types is essential for enhancing GIS management and ensuring the reliability of electrical grids. This study proposes a novel approach for PD identification in GIS integrating completed local binary pattern (CLBP) feature extraction, feature engineering, and an optimized support vector machine (SVM). PD faults were simulated in GIS and phase-resolved pulse sequence (PRPS) data for four different forms of PD were gathered. CLBP was used to extract image features, and then the support vector machine recursive feature elimination (SVM-RFE) algorithm was used to evaluate feature importance. Then, linear discriminant analysis (LDA) was used to fuse the selected features and reduce redundancy. The fused features were classified using a bald eagle search algorithm combined with differential evolution (IBES)-optimized SVM, achieving a recognition accuracy of 99.38%. The results indicate that the proposed method effectively distinguishes between different PD PRPS patterns in GIS.https://www.aimspress.com/article/doi/10.3934/energy.2024052phase-resolved pulse sequencegas-insulated switchgearsupport vector machineintelligent optimization algorithmlocal binary patterns |
| spellingShingle | Ziqiang Xu Honghua Xu Chao Yuan Shoulong Chen Yini Chen Recognition of partial discharge in GIS based on image feature fusion AIMS Energy phase-resolved pulse sequence gas-insulated switchgear support vector machine intelligent optimization algorithm local binary patterns |
| title | Recognition of partial discharge in GIS based on image feature fusion |
| title_full | Recognition of partial discharge in GIS based on image feature fusion |
| title_fullStr | Recognition of partial discharge in GIS based on image feature fusion |
| title_full_unstemmed | Recognition of partial discharge in GIS based on image feature fusion |
| title_short | Recognition of partial discharge in GIS based on image feature fusion |
| title_sort | recognition of partial discharge in gis based on image feature fusion |
| topic | phase-resolved pulse sequence gas-insulated switchgear support vector machine intelligent optimization algorithm local binary patterns |
| url | https://www.aimspress.com/article/doi/10.3934/energy.2024052 |
| work_keys_str_mv | AT ziqiangxu recognitionofpartialdischargeingisbasedonimagefeaturefusion AT honghuaxu recognitionofpartialdischargeingisbasedonimagefeaturefusion AT chaoyuan recognitionofpartialdischargeingisbasedonimagefeaturefusion AT shoulongchen recognitionofpartialdischargeingisbasedonimagefeaturefusion AT yinichen recognitionofpartialdischargeingisbasedonimagefeaturefusion |