Wind Turbine Fault Identification in Sample Imbalance Scenarios Using FRBCS With GAN Oversampling and Metric Learning
The operation data from different wind turbines (WTs) is not universal, due to the influence of installation, location, and environmental conditions, which caused incomplete and imbalanced fault sample data, and influenced the fault identification accuracy. Therefore, this paper proposes a fuzzy rul...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10815943/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849311834242285568 |
|---|---|
| author | Changsheng Kang Xiaoyi Qian Lixin Wang Ziheng Dai Shuai Guan Yi Zhao Wenyao Sun |
| author_facet | Changsheng Kang Xiaoyi Qian Lixin Wang Ziheng Dai Shuai Guan Yi Zhao Wenyao Sun |
| author_sort | Changsheng Kang |
| collection | DOAJ |
| description | The operation data from different wind turbines (WTs) is not universal, due to the influence of installation, location, and environmental conditions, which caused incomplete and imbalanced fault sample data, and influenced the fault identification accuracy. Therefore, this paper proposes a fuzzy rule-based classification system (FRBCS) based on generative adversarial network (GAN) oversampling and metric learning. The GAN oversampling algorithm is introduced to eliminate the imbalance of the actual samples, and the metric learning algorithm (MLA) is adopted to improve the separability of different fault samples of the FRBCS. 10 common faults of megawatt-level WTs are used to validate the effectiveness of the proposed method, the results show that the proposed method effectively improves fault identification accuracy in the presence of imbalanced fault samples. |
| format | Article |
| id | doaj-art-0ceb5840f6c34eb6ac9936097a31f084 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-0ceb5840f6c34eb6ac9936097a31f0842025-08-20T03:53:17ZengIEEEIEEE Access2169-35362025-01-0113788647887410.1109/ACCESS.2024.352258710815943Wind Turbine Fault Identification in Sample Imbalance Scenarios Using FRBCS With GAN Oversampling and Metric LearningChangsheng Kang0https://orcid.org/0009-0006-3994-7834Xiaoyi Qian1https://orcid.org/0000-0002-3926-6813Lixin Wang2https://orcid.org/0009-0009-9281-0249Ziheng Dai3https://orcid.org/0009-0002-5596-5734Shuai Guan4Yi Zhao5Wenyao Sun6Liaoning Key Laboratory of Power Grid Energy Conservation and Control, Shenyang Institute of Engineering, Shenyang, ChinaLiaoning Key Laboratory of Power Grid Energy Conservation and Control, Shenyang Institute of Engineering, Shenyang, ChinaLiaoning Key Laboratory of Power Grid Energy Conservation and Control, Shenyang Institute of Engineering, Shenyang, ChinaLiaoning Key Laboratory of Power Grid Energy Conservation and Control, Shenyang Institute of Engineering, Shenyang, ChinaLiaoning Key Laboratory of Power Grid Energy Conservation and Control, Shenyang Institute of Engineering, Shenyang, ChinaLiaoning Key Laboratory of Power Grid Energy Conservation and Control, Shenyang Institute of Engineering, Shenyang, ChinaLiaoning Key Laboratory of Power Grid Energy Conservation and Control, Shenyang Institute of Engineering, Shenyang, ChinaThe operation data from different wind turbines (WTs) is not universal, due to the influence of installation, location, and environmental conditions, which caused incomplete and imbalanced fault sample data, and influenced the fault identification accuracy. Therefore, this paper proposes a fuzzy rule-based classification system (FRBCS) based on generative adversarial network (GAN) oversampling and metric learning. The GAN oversampling algorithm is introduced to eliminate the imbalance of the actual samples, and the metric learning algorithm (MLA) is adopted to improve the separability of different fault samples of the FRBCS. 10 common faults of megawatt-level WTs are used to validate the effectiveness of the proposed method, the results show that the proposed method effectively improves fault identification accuracy in the presence of imbalanced fault samples.https://ieeexplore.ieee.org/document/10815943/Fault identificationfuzzy rule-based classification systemgenerative adversarial networkimbalanced datasetmetric learningwind turbine |
| spellingShingle | Changsheng Kang Xiaoyi Qian Lixin Wang Ziheng Dai Shuai Guan Yi Zhao Wenyao Sun Wind Turbine Fault Identification in Sample Imbalance Scenarios Using FRBCS With GAN Oversampling and Metric Learning IEEE Access Fault identification fuzzy rule-based classification system generative adversarial network imbalanced dataset metric learning wind turbine |
| title | Wind Turbine Fault Identification in Sample Imbalance Scenarios Using FRBCS With GAN Oversampling and Metric Learning |
| title_full | Wind Turbine Fault Identification in Sample Imbalance Scenarios Using FRBCS With GAN Oversampling and Metric Learning |
| title_fullStr | Wind Turbine Fault Identification in Sample Imbalance Scenarios Using FRBCS With GAN Oversampling and Metric Learning |
| title_full_unstemmed | Wind Turbine Fault Identification in Sample Imbalance Scenarios Using FRBCS With GAN Oversampling and Metric Learning |
| title_short | Wind Turbine Fault Identification in Sample Imbalance Scenarios Using FRBCS With GAN Oversampling and Metric Learning |
| title_sort | wind turbine fault identification in sample imbalance scenarios using frbcs with gan oversampling and metric learning |
| topic | Fault identification fuzzy rule-based classification system generative adversarial network imbalanced dataset metric learning wind turbine |
| url | https://ieeexplore.ieee.org/document/10815943/ |
| work_keys_str_mv | AT changshengkang windturbinefaultidentificationinsampleimbalancescenariosusingfrbcswithganoversamplingandmetriclearning AT xiaoyiqian windturbinefaultidentificationinsampleimbalancescenariosusingfrbcswithganoversamplingandmetriclearning AT lixinwang windturbinefaultidentificationinsampleimbalancescenariosusingfrbcswithganoversamplingandmetriclearning AT zihengdai windturbinefaultidentificationinsampleimbalancescenariosusingfrbcswithganoversamplingandmetriclearning AT shuaiguan windturbinefaultidentificationinsampleimbalancescenariosusingfrbcswithganoversamplingandmetriclearning AT yizhao windturbinefaultidentificationinsampleimbalancescenariosusingfrbcswithganoversamplingandmetriclearning AT wenyaosun windturbinefaultidentificationinsampleimbalancescenariosusingfrbcswithganoversamplingandmetriclearning |