Novel MOA Fault Detection Technology Based on Small Sample Infrared Image
This paper proposes a novel metal oxide arrester (MOA) fault detection technology based on a small sample infrared image. The research is carried out from the detection process and data enhancement. A lightweight MOA identification and location algorithm is designed at the edge, which can not only r...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/15/1748 |
| _version_ | 1797525708485951488 |
|---|---|
| author | Baoquan Wei Yong Zuo Yande Liu Wei Luo Kaiyun Wen Fangming Deng |
| author_facet | Baoquan Wei Yong Zuo Yande Liu Wei Luo Kaiyun Wen Fangming Deng |
| author_sort | Baoquan Wei |
| collection | DOAJ |
| description | This paper proposes a novel metal oxide arrester (MOA) fault detection technology based on a small sample infrared image. The research is carried out from the detection process and data enhancement. A lightweight MOA identification and location algorithm is designed at the edge, which can not only reduce the amount of data uploaded, but also reduce the search space of cloud algorithm. In order to improve the accuracy and generalization ability of the defect detection model under the condition of small samples, a multi-model fusion detection algorithm is proposed. Different features of the image are extracted by multiple convolutional neural networks, and then multiple classifiers are trained. Finally, the weighted voting strategy is used for fault diagnosis. In addition, the extended model of fault samples is constructed by transfer learning and deep convolutional generative adversarial networks (DCGAN) to solve the problem of unbalanced training data sets. The experimental results show that the proposed method can realize the accurate location of arrester under the condition of small samples, and after the data expansion, the recognition rate of arrester anomalies can be improved from 83% to 85%, showing high effectiveness and reliability. |
| first_indexed | 2024-03-10T09:16:53Z |
| format | Article |
| id | doaj.art-40d005bf2f9845b8bba440d3e66bb383 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T09:16:53Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-40d005bf2f9845b8bba440d3e66bb3832023-11-22T05:30:18ZengMDPI AGElectronics2079-92922021-07-011015174810.3390/electronics10151748Novel MOA Fault Detection Technology Based on Small Sample Infrared ImageBaoquan Wei0Yong Zuo1Yande Liu2Wei Luo3Kaiyun Wen4Fangming Deng5School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Electrical and Automation Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Mechatronics and Vechicle Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Electrical and Automation Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Electrical and Automation Engineering, East China Jiaotong University, Nanchang 330013, ChinaSchool of Electrical and Automation Engineering, East China Jiaotong University, Nanchang 330013, ChinaThis paper proposes a novel metal oxide arrester (MOA) fault detection technology based on a small sample infrared image. The research is carried out from the detection process and data enhancement. A lightweight MOA identification and location algorithm is designed at the edge, which can not only reduce the amount of data uploaded, but also reduce the search space of cloud algorithm. In order to improve the accuracy and generalization ability of the defect detection model under the condition of small samples, a multi-model fusion detection algorithm is proposed. Different features of the image are extracted by multiple convolutional neural networks, and then multiple classifiers are trained. Finally, the weighted voting strategy is used for fault diagnosis. In addition, the extended model of fault samples is constructed by transfer learning and deep convolutional generative adversarial networks (DCGAN) to solve the problem of unbalanced training data sets. The experimental results show that the proposed method can realize the accurate location of arrester under the condition of small samples, and after the data expansion, the recognition rate of arrester anomalies can be improved from 83% to 85%, showing high effectiveness and reliability.https://www.mdpi.com/2079-9292/10/15/1748metal oxide arresterdeep learningedge computingcondition monitoring |
| spellingShingle | Baoquan Wei Yong Zuo Yande Liu Wei Luo Kaiyun Wen Fangming Deng Novel MOA Fault Detection Technology Based on Small Sample Infrared Image Electronics metal oxide arrester deep learning edge computing condition monitoring |
| title | Novel MOA Fault Detection Technology Based on Small Sample Infrared Image |
| title_full | Novel MOA Fault Detection Technology Based on Small Sample Infrared Image |
| title_fullStr | Novel MOA Fault Detection Technology Based on Small Sample Infrared Image |
| title_full_unstemmed | Novel MOA Fault Detection Technology Based on Small Sample Infrared Image |
| title_short | Novel MOA Fault Detection Technology Based on Small Sample Infrared Image |
| title_sort | novel moa fault detection technology based on small sample infrared image |
| topic | metal oxide arrester deep learning edge computing condition monitoring |
| url | https://www.mdpi.com/2079-9292/10/15/1748 |
| work_keys_str_mv | AT baoquanwei novelmoafaultdetectiontechnologybasedonsmallsampleinfraredimage AT yongzuo novelmoafaultdetectiontechnologybasedonsmallsampleinfraredimage AT yandeliu novelmoafaultdetectiontechnologybasedonsmallsampleinfraredimage AT weiluo novelmoafaultdetectiontechnologybasedonsmallsampleinfraredimage AT kaiyunwen novelmoafaultdetectiontechnologybasedonsmallsampleinfraredimage AT fangmingdeng novelmoafaultdetectiontechnologybasedonsmallsampleinfraredimage |