Voltage-Induced Heating Defect Detection for Electrical Equipment in Thermal Images
Voltage-induced heating defect is a type of defect that may occur in transformation substation equipment. Although this type of defect is less common compared to current-induced heating defects, it is crucial to identify it due to its association with severe insulation degradation problems that requ...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/24/8036 |
| _version_ | 1797381269753954304 |
|---|---|
| author | Ying Lin Zhuangzhuang Li Yiwei Sun Yi Yang Wenjie Zheng |
| author_facet | Ying Lin Zhuangzhuang Li Yiwei Sun Yi Yang Wenjie Zheng |
| author_sort | Ying Lin |
| collection | DOAJ |
| description | Voltage-induced heating defect is a type of defect that may occur in transformation substation equipment. Although this type of defect is less common compared to current-induced heating defects, it is crucial to identify it due to its association with severe insulation degradation problems that require prompt intervention. However, the temperature variations caused by these defects may be relatively subtle, making it challenging to distinguish them in thermal images. In this work, considering the characteristics of voltage-induced heating defects and the scarcity of defect data, we propose a two-stage method for defect detection. In the first stage, we employ oriented R-CNN to detect oriented parts of the equipment, accurately localizing the centerline of each part. In the second stage, we extract the temperature distribution along the centerline of specific parts and discretize them as features. Subsequently, we train one-class support vector machines based on the features extracted from normal images for defect diagnosis. Experimental results demonstrate that the proposed method is capable of accurately detecting defects while maintaining a low false positive rate. |
| first_indexed | 2024-03-08T20:49:02Z |
| format | Article |
| id | doaj.art-a149a031ada54810ac5c187e7b4695af |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-08T20:49:02Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-a149a031ada54810ac5c187e7b4695af2023-12-22T14:05:53ZengMDPI AGEnergies1996-10732023-12-011624803610.3390/en16248036Voltage-Induced Heating Defect Detection for Electrical Equipment in Thermal ImagesYing Lin0Zhuangzhuang Li1Yiwei Sun2Yi Yang3Wenjie Zheng4State Grid Shandong Electric Power Research Institute, Jinan 250002, ChinaState Grid Shandong Electric Power Research Institute, Jinan 250002, ChinaState Grid Shandong Electric Power Research Institute, Jinan 250002, ChinaState Grid Shandong Electric Power Research Institute, Jinan 250002, ChinaState Grid Shandong Electric Power Research Institute, Jinan 250002, ChinaVoltage-induced heating defect is a type of defect that may occur in transformation substation equipment. Although this type of defect is less common compared to current-induced heating defects, it is crucial to identify it due to its association with severe insulation degradation problems that require prompt intervention. However, the temperature variations caused by these defects may be relatively subtle, making it challenging to distinguish them in thermal images. In this work, considering the characteristics of voltage-induced heating defects and the scarcity of defect data, we propose a two-stage method for defect detection. In the first stage, we employ oriented R-CNN to detect oriented parts of the equipment, accurately localizing the centerline of each part. In the second stage, we extract the temperature distribution along the centerline of specific parts and discretize them as features. Subsequently, we train one-class support vector machines based on the features extracted from normal images for defect diagnosis. Experimental results demonstrate that the proposed method is capable of accurately detecting defects while maintaining a low false positive rate.https://www.mdpi.com/1996-1073/16/24/8036electrical equipment defect detectionvoltage-induced heating defectthermal image analysisoriented object detection |
| spellingShingle | Ying Lin Zhuangzhuang Li Yiwei Sun Yi Yang Wenjie Zheng Voltage-Induced Heating Defect Detection for Electrical Equipment in Thermal Images Energies electrical equipment defect detection voltage-induced heating defect thermal image analysis oriented object detection |
| title | Voltage-Induced Heating Defect Detection for Electrical Equipment in Thermal Images |
| title_full | Voltage-Induced Heating Defect Detection for Electrical Equipment in Thermal Images |
| title_fullStr | Voltage-Induced Heating Defect Detection for Electrical Equipment in Thermal Images |
| title_full_unstemmed | Voltage-Induced Heating Defect Detection for Electrical Equipment in Thermal Images |
| title_short | Voltage-Induced Heating Defect Detection for Electrical Equipment in Thermal Images |
| title_sort | voltage induced heating defect detection for electrical equipment in thermal images |
| topic | electrical equipment defect detection voltage-induced heating defect thermal image analysis oriented object detection |
| url | https://www.mdpi.com/1996-1073/16/24/8036 |
| work_keys_str_mv | AT yinglin voltageinducedheatingdefectdetectionforelectricalequipmentinthermalimages AT zhuangzhuangli voltageinducedheatingdefectdetectionforelectricalequipmentinthermalimages AT yiweisun voltageinducedheatingdefectdetectionforelectricalequipmentinthermalimages AT yiyang voltageinducedheatingdefectdetectionforelectricalequipmentinthermalimages AT wenjiezheng voltageinducedheatingdefectdetectionforelectricalequipmentinthermalimages |