Fault diagnosis method for OLTC based on improved semi-supervised ladder networks
On-load tap changers (OLTC) have complex mechanical and electrical structures, which are the key component for the on-load voltage regulation of transformers. Currently, due to the sample data which are not easy to be labeled, it is difficult to effectively train the OLTC mechanical fault diagnosis...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Electric Power Engineering Technology
2023-03-01
|
| Series: | 电力工程技术 |
| Subjects: | |
| Online Access: | https://www.epet-info.com/dlgcjsen/article/abstract/220324374 |
| _version_ | 1797859022760574976 |
|---|---|
| author | ZHENG Shangzhi ZHONG Linlin WANG Tonglei GAO Bingtuan |
| author_facet | ZHENG Shangzhi ZHONG Linlin WANG Tonglei GAO Bingtuan |
| author_sort | ZHENG Shangzhi |
| collection | DOAJ |
| description | On-load tap changers (OLTC) have complex mechanical and electrical structures, which are the key component for the on-load voltage regulation of transformers. Currently, due to the sample data which are not easy to be labeled, it is difficult to effectively train the OLTC mechanical fault diagnosis models based on vibration signals. To improve the fault diagnostic accuracy for OLTC with limited labeled data, a fault diagnosis method based on Bayesian optimization-convolutional ladder networks (BO-ConvLN) is proposed in this paper. Firstly, the ladder networks are used as a semi-supervised learning method for the feature extraction of vibration signals, which is guided by a large amount of unlabeled data, leading to the enhanced diagnostic ability of ladder networks only with a small amount of labeled data. Then, the fully-connected layers are replaced by convolutional operators in the ladder networks to better extract the features of non-stationary vibration signals. Furthermore, Bayesian optimization is used to optimize the high-dimensional hyperparameters of ladder networks, witch significantly improves the diagnostic accuracy of the model within limited time cost. The experiment results show that the diagnostic accuracy for the three types of faults, namely transmission shaft jams, poor switch lubrication, and top cover looseness, is 91.67% with a label count of only 40, which demonstrates the effectiveness of BO-ConvLN in the fault diagnosis. |
| first_indexed | 2024-04-09T21:22:47Z |
| format | Article |
| id | doaj.art-78539e599c7343e49115dbb232a6e47c |
| institution | Directory Open Access Journal |
| issn | 2096-3203 |
| language | zho |
| last_indexed | 2024-04-09T21:22:47Z |
| publishDate | 2023-03-01 |
| publisher | Editorial Department of Electric Power Engineering Technology |
| record_format | Article |
| series | 电力工程技术 |
| spelling | doaj.art-78539e599c7343e49115dbb232a6e47c2023-03-28T03:31:10ZzhoEditorial Department of Electric Power Engineering Technology电力工程技术2096-32032023-03-0142219720510.12158/j.2096-3203.2023.02.023220324374Fault diagnosis method for OLTC based on improved semi-supervised ladder networksZHENG Shangzhi0ZHONG Linlin1WANG Tonglei2GAO Bingtuan3School of Electrical Engineering, Southeast University, Nanjing 210096, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 210096, ChinaElectric Power Research Institute of State Grid Jiangsu Electric Power Co., Ltd., Nanjing 211103, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 210096, ChinaOn-load tap changers (OLTC) have complex mechanical and electrical structures, which are the key component for the on-load voltage regulation of transformers. Currently, due to the sample data which are not easy to be labeled, it is difficult to effectively train the OLTC mechanical fault diagnosis models based on vibration signals. To improve the fault diagnostic accuracy for OLTC with limited labeled data, a fault diagnosis method based on Bayesian optimization-convolutional ladder networks (BO-ConvLN) is proposed in this paper. Firstly, the ladder networks are used as a semi-supervised learning method for the feature extraction of vibration signals, which is guided by a large amount of unlabeled data, leading to the enhanced diagnostic ability of ladder networks only with a small amount of labeled data. Then, the fully-connected layers are replaced by convolutional operators in the ladder networks to better extract the features of non-stationary vibration signals. Furthermore, Bayesian optimization is used to optimize the high-dimensional hyperparameters of ladder networks, witch significantly improves the diagnostic accuracy of the model within limited time cost. The experiment results show that the diagnostic accuracy for the three types of faults, namely transmission shaft jams, poor switch lubrication, and top cover looseness, is 91.67% with a label count of only 40, which demonstrates the effectiveness of BO-ConvLN in the fault diagnosis.https://www.epet-info.com/dlgcjsen/article/abstract/220324374on-load tap changer (oltc)fault diagnosisvibration signalsladder networkssemi-supervised learningbayesian optimization |
| spellingShingle | ZHENG Shangzhi ZHONG Linlin WANG Tonglei GAO Bingtuan Fault diagnosis method for OLTC based on improved semi-supervised ladder networks 电力工程技术 on-load tap changer (oltc) fault diagnosis vibration signals ladder networks semi-supervised learning bayesian optimization |
| title | Fault diagnosis method for OLTC based on improved semi-supervised ladder networks |
| title_full | Fault diagnosis method for OLTC based on improved semi-supervised ladder networks |
| title_fullStr | Fault diagnosis method for OLTC based on improved semi-supervised ladder networks |
| title_full_unstemmed | Fault diagnosis method for OLTC based on improved semi-supervised ladder networks |
| title_short | Fault diagnosis method for OLTC based on improved semi-supervised ladder networks |
| title_sort | fault diagnosis method for oltc based on improved semi supervised ladder networks |
| topic | on-load tap changer (oltc) fault diagnosis vibration signals ladder networks semi-supervised learning bayesian optimization |
| url | https://www.epet-info.com/dlgcjsen/article/abstract/220324374 |
| work_keys_str_mv | AT zhengshangzhi faultdiagnosismethodforoltcbasedonimprovedsemisupervisedladdernetworks AT zhonglinlin faultdiagnosismethodforoltcbasedonimprovedsemisupervisedladdernetworks AT wangtonglei faultdiagnosismethodforoltcbasedonimprovedsemisupervisedladdernetworks AT gaobingtuan faultdiagnosismethodforoltcbasedonimprovedsemisupervisedladdernetworks |