Improved Winding Mechanical Fault Type Classification Methods Based on Polar Plots and Multiple Support Vector Machines
The accurate and fast diagnosis of transformer winding deformation faults is of significance to power suppliers and utilities. An improved winding mechanical deformation fault classification method is proposed. In this study, the transformer frequency response data is used to draw polar plots, and t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9273015/ |
| id |
doaj-9c671598a76f43baa0f61be1930d12d6 |
|---|---|
| record_format |
Article |
| spelling |
doaj-9c671598a76f43baa0f61be1930d12d62021-03-30T04:04:27ZengIEEEIEEE Access2169-35362020-01-01821627121628210.1109/ACCESS.2020.30412989273015Improved Winding Mechanical Fault Type Classification Methods Based on Polar Plots and Multiple Support Vector MachinesJiangnan Liu0https://orcid.org/0000-0002-6606-3755Zhongyong Zhao1https://orcid.org/0000-0002-4089-4470Kai Pang2Dong Wang3Chao Tang4https://orcid.org/0000-0002-5572-2671Chenguo Yao5College of Engineering and Technology, Southwest University, Chongqing, ChinaCollege of Engineering and Technology, Southwest University, Chongqing, ChinaElectric Power Research Institute, State Grid Henan Electric Power Company, Henan, ChinaElectric Power Research Institute, State Grid Henan Electric Power Company, Henan, ChinaCollege of Engineering and Technology, Southwest University, Chongqing, ChinaState Key Laboratory of Power Transmission Equipment and System Security and New Technology, Chongqing University, Chongqing, ChinaThe accurate and fast diagnosis of transformer winding deformation faults is of significance to power suppliers and utilities. An improved winding mechanical deformation fault classification method is proposed. In this study, the transformer frequency response data is used to draw polar plots, and then its texture features are extracted for fault classification. The classification model constructed by multiple support vector machines is successfully obtained and shows good classification effect. Besides, this article uses an improved genetic algorithm based on the Emperor-Selective mating scheme and catastrophic operation, to optimize the parameters of support vector machine. The feasibility and accuracy of the proposed method are verified with experimental data obtained from a model transformer, and the proposed method is demonstrated to exhibit better performance compared with the traditional method.https://ieeexplore.ieee.org/document/9273015/Transformersfault diagnosisfault detectionfrequency responsesupport vector machinesgenetic algorithms |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Jiangnan Liu Zhongyong Zhao Kai Pang Dong Wang Chao Tang Chenguo Yao |
| spellingShingle |
Jiangnan Liu Zhongyong Zhao Kai Pang Dong Wang Chao Tang Chenguo Yao Improved Winding Mechanical Fault Type Classification Methods Based on Polar Plots and Multiple Support Vector Machines IEEE Access Transformers fault diagnosis fault detection frequency response support vector machines genetic algorithms |
| author_facet |
Jiangnan Liu Zhongyong Zhao Kai Pang Dong Wang Chao Tang Chenguo Yao |
| author_sort |
Jiangnan Liu |
| title |
Improved Winding Mechanical Fault Type Classification Methods Based on Polar Plots and Multiple Support Vector Machines |
| title_short |
Improved Winding Mechanical Fault Type Classification Methods Based on Polar Plots and Multiple Support Vector Machines |
| title_full |
Improved Winding Mechanical Fault Type Classification Methods Based on Polar Plots and Multiple Support Vector Machines |
| title_fullStr |
Improved Winding Mechanical Fault Type Classification Methods Based on Polar Plots and Multiple Support Vector Machines |
| title_full_unstemmed |
Improved Winding Mechanical Fault Type Classification Methods Based on Polar Plots and Multiple Support Vector Machines |
| title_sort |
improved winding mechanical fault type classification methods based on polar plots and multiple support vector machines |
| publisher |
IEEE |
| series |
IEEE Access |
| issn |
2169-3536 |
| publishDate |
2020-01-01 |
| description |
The accurate and fast diagnosis of transformer winding deformation faults is of significance to power suppliers and utilities. An improved winding mechanical deformation fault classification method is proposed. In this study, the transformer frequency response data is used to draw polar plots, and then its texture features are extracted for fault classification. The classification model constructed by multiple support vector machines is successfully obtained and shows good classification effect. Besides, this article uses an improved genetic algorithm based on the Emperor-Selective mating scheme and catastrophic operation, to optimize the parameters of support vector machine. The feasibility and accuracy of the proposed method are verified with experimental data obtained from a model transformer, and the proposed method is demonstrated to exhibit better performance compared with the traditional method. |
| topic |
Transformers fault diagnosis fault detection frequency response support vector machines genetic algorithms |
| url |
https://ieeexplore.ieee.org/document/9273015/ |
| work_keys_str_mv |
AT jiangnanliu improvedwindingmechanicalfaulttypeclassificationmethodsbasedonpolarplotsandmultiplesupportvectormachines AT zhongyongzhao improvedwindingmechanicalfaulttypeclassificationmethodsbasedonpolarplotsandmultiplesupportvectormachines AT kaipang improvedwindingmechanicalfaulttypeclassificationmethodsbasedonpolarplotsandmultiplesupportvectormachines AT dongwang improvedwindingmechanicalfaulttypeclassificationmethodsbasedonpolarplotsandmultiplesupportvectormachines AT chaotang improvedwindingmechanicalfaulttypeclassificationmethodsbasedonpolarplotsandmultiplesupportvectormachines AT chenguoyao improvedwindingmechanicalfaulttypeclassificationmethodsbasedonpolarplotsandmultiplesupportvectormachines |
| _version_ |
1724182435332096000 |