A novel power transformer fault diagnosis method based on data augmentation for KPCA and deep residual network
Because transformer plays an important role in power system, it rarely runs in fault or abnormal state. Therefore, it is difficult to obtain sufficient transformer fault samples. In this paper, aiming at the problem of less fault sample data and data imbalance, a novel data augmentation method based...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-09-01
|
| Series: | Energy Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S235248472300642X |
| _version_ | 1797688415777456128 |
|---|---|
| author | Xiaozhi Liu Jie Xie Yanhong Luo Dongsheng Yang |
| author_facet | Xiaozhi Liu Jie Xie Yanhong Luo Dongsheng Yang |
| author_sort | Xiaozhi Liu |
| collection | DOAJ |
| description | Because transformer plays an important role in power system, it rarely runs in fault or abnormal state. Therefore, it is difficult to obtain sufficient transformer fault samples. In this paper, aiming at the problem of less fault sample data and data imbalance, a novel data augmentation method based on kernel principal component analysis is proposed to non-linearly map the original data to a high-dimensional feature space. In this way, the new sample data retaining the feature information of the original data can be obtained. Second, the deep residual network is introduced with the identity path to construct the fault diagnosis model, which enables the weight parameters to be effectively transferred and updated. The simulation results show that the proposed method can effectively expand the data samples with high similarity with the original data, and the residual network model has strong feature extraction ability, which improves the accuracy of fault diagnosis. |
| first_indexed | 2024-03-12T01:31:38Z |
| format | Article |
| id | doaj.art-c73ec964e2a84c42a2d18cb71c11002f |
| institution | Directory Open Access Journal |
| issn | 2352-4847 |
| language | English |
| last_indexed | 2024-03-12T01:31:38Z |
| publishDate | 2023-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Reports |
| spelling | doaj.art-c73ec964e2a84c42a2d18cb71c11002f2023-09-12T04:15:47ZengElsevierEnergy Reports2352-48472023-09-019620627A novel power transformer fault diagnosis method based on data augmentation for KPCA and deep residual networkXiaozhi Liu0Jie Xie1Yanhong Luo2Dongsheng Yang3College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, 110819, ChinaCollege of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, 110819, ChinaCorresponding author.; College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, 110819, ChinaCollege of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, 110819, ChinaBecause transformer plays an important role in power system, it rarely runs in fault or abnormal state. Therefore, it is difficult to obtain sufficient transformer fault samples. In this paper, aiming at the problem of less fault sample data and data imbalance, a novel data augmentation method based on kernel principal component analysis is proposed to non-linearly map the original data to a high-dimensional feature space. In this way, the new sample data retaining the feature information of the original data can be obtained. Second, the deep residual network is introduced with the identity path to construct the fault diagnosis model, which enables the weight parameters to be effectively transferred and updated. The simulation results show that the proposed method can effectively expand the data samples with high similarity with the original data, and the residual network model has strong feature extraction ability, which improves the accuracy of fault diagnosis.http://www.sciencedirect.com/science/article/pii/S235248472300642XKPCAData augmentationDeep residual networksPower transformersFault diagnosis |
| spellingShingle | Xiaozhi Liu Jie Xie Yanhong Luo Dongsheng Yang A novel power transformer fault diagnosis method based on data augmentation for KPCA and deep residual network Energy Reports KPCA Data augmentation Deep residual networks Power transformers Fault diagnosis |
| title | A novel power transformer fault diagnosis method based on data augmentation for KPCA and deep residual network |
| title_full | A novel power transformer fault diagnosis method based on data augmentation for KPCA and deep residual network |
| title_fullStr | A novel power transformer fault diagnosis method based on data augmentation for KPCA and deep residual network |
| title_full_unstemmed | A novel power transformer fault diagnosis method based on data augmentation for KPCA and deep residual network |
| title_short | A novel power transformer fault diagnosis method based on data augmentation for KPCA and deep residual network |
| title_sort | novel power transformer fault diagnosis method based on data augmentation for kpca and deep residual network |
| topic | KPCA Data augmentation Deep residual networks Power transformers Fault diagnosis |
| url | http://www.sciencedirect.com/science/article/pii/S235248472300642X |
| work_keys_str_mv | AT xiaozhiliu anovelpowertransformerfaultdiagnosismethodbasedondataaugmentationforkpcaanddeepresidualnetwork AT jiexie anovelpowertransformerfaultdiagnosismethodbasedondataaugmentationforkpcaanddeepresidualnetwork AT yanhongluo anovelpowertransformerfaultdiagnosismethodbasedondataaugmentationforkpcaanddeepresidualnetwork AT dongshengyang anovelpowertransformerfaultdiagnosismethodbasedondataaugmentationforkpcaanddeepresidualnetwork AT xiaozhiliu novelpowertransformerfaultdiagnosismethodbasedondataaugmentationforkpcaanddeepresidualnetwork AT jiexie novelpowertransformerfaultdiagnosismethodbasedondataaugmentationforkpcaanddeepresidualnetwork AT yanhongluo novelpowertransformerfaultdiagnosismethodbasedondataaugmentationforkpcaanddeepresidualnetwork AT dongshengyang novelpowertransformerfaultdiagnosismethodbasedondataaugmentationforkpcaanddeepresidualnetwork |