Data augmentation for fault diagnosis of oil-immersed power transformer
110 kV oil immersed transformer is a key part of the power transmission and transformation system, which determines the power quality and transmission efficiency. Its fault diagnosis can greatly reduce the maintenance cost and improve the economy. At present, the methods of transformer fault diagnos...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Energy Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352484723008533 |
| _version_ | 1827582174288674816 |
|---|---|
| author | Ke Li Jian Li Qi Huang Yuhui Chen |
| author_facet | Ke Li Jian Li Qi Huang Yuhui Chen |
| author_sort | Ke Li |
| collection | DOAJ |
| description | 110 kV oil immersed transformer is a key part of the power transmission and transformation system, which determines the power quality and transmission efficiency. Its fault diagnosis can greatly reduce the maintenance cost and improve the economy. At present, the methods of transformer fault diagnosis have a strong dependence on the original data, and the size of the original data directly affects the effect of fault diagnosis. In order to change this situation and achieve higher accuracy of transformer fault diagnosis, this paper firstly uses the Conditional Variational Automatic Encoder (CVAE) composed of full connection layers to expand the original samples under each fault category. After data augmentation, the convolutional neural network (CNN) with strong feature extraction ability is selected as the classifier. Finally, the CVAE-CNN model is validated using public dataset and the result is compared to other machine learning algorithms. |
| first_indexed | 2024-03-08T22:46:43Z |
| format | Article |
| id | doaj.art-e1d74daf13b14c3d8b8d61e35c645223 |
| institution | Directory Open Access Journal |
| issn | 2352-4847 |
| language | English |
| last_indexed | 2024-03-08T22:46:43Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Reports |
| spelling | doaj.art-e1d74daf13b14c3d8b8d61e35c6452232023-12-17T06:38:51ZengElsevierEnergy Reports2352-48472023-10-01912111219Data augmentation for fault diagnosis of oil-immersed power transformerKe Li0Jian Li1Qi Huang2Yuhui Chen3Sichuan Provincial Key Lab of Power System Wide Area Measurement and Control, School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan 611731, ChinaSichuan Provincial Key Lab of Power System Wide Area Measurement and Control, School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan 611731, China; Corresponding author.Sichuan Provincial Key Lab of Power System Wide Area Measurement and Control, School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan 611731, China; College of Nuclear Technology and Automation Engineering, Chengdu University of Technology, Chengdu, Sichuan 610059, ChinaSichuan Provincial Key Lab of Power System Wide Area Measurement and Control, School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan 611731, China110 kV oil immersed transformer is a key part of the power transmission and transformation system, which determines the power quality and transmission efficiency. Its fault diagnosis can greatly reduce the maintenance cost and improve the economy. At present, the methods of transformer fault diagnosis have a strong dependence on the original data, and the size of the original data directly affects the effect of fault diagnosis. In order to change this situation and achieve higher accuracy of transformer fault diagnosis, this paper firstly uses the Conditional Variational Automatic Encoder (CVAE) composed of full connection layers to expand the original samples under each fault category. After data augmentation, the convolutional neural network (CNN) with strong feature extraction ability is selected as the classifier. Finally, the CVAE-CNN model is validated using public dataset and the result is compared to other machine learning algorithms.http://www.sciencedirect.com/science/article/pii/S2352484723008533Fault diagnosisConvolution neural networkConditional variational auto-encoderData augmentation |
| spellingShingle | Ke Li Jian Li Qi Huang Yuhui Chen Data augmentation for fault diagnosis of oil-immersed power transformer Energy Reports Fault diagnosis Convolution neural network Conditional variational auto-encoder Data augmentation |
| title | Data augmentation for fault diagnosis of oil-immersed power transformer |
| title_full | Data augmentation for fault diagnosis of oil-immersed power transformer |
| title_fullStr | Data augmentation for fault diagnosis of oil-immersed power transformer |
| title_full_unstemmed | Data augmentation for fault diagnosis of oil-immersed power transformer |
| title_short | Data augmentation for fault diagnosis of oil-immersed power transformer |
| title_sort | data augmentation for fault diagnosis of oil immersed power transformer |
| topic | Fault diagnosis Convolution neural network Conditional variational auto-encoder Data augmentation |
| url | http://www.sciencedirect.com/science/article/pii/S2352484723008533 |
| work_keys_str_mv | AT keli dataaugmentationforfaultdiagnosisofoilimmersedpowertransformer AT jianli dataaugmentationforfaultdiagnosisofoilimmersedpowertransformer AT qihuang dataaugmentationforfaultdiagnosisofoilimmersedpowertransformer AT yuhuichen dataaugmentationforfaultdiagnosisofoilimmersedpowertransformer |