Fault diagnosis method of substation equipment based on You Only Look Once algorithm and infrared imaging
Aiming at the problems of local temperature increase of cable, heating of insulator porcelain disc, local heating of lightning arresters and transformers in the process of abnormal heat generation fault diagnosis of power equipment. This study proposes a target detection method that YOLOv4 (You Only...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-10-01
|
Series: | Energy Reports |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2352484722009234 |
_version_ | 1811294837663596544 |
---|---|
author | Tao Liu Guolong Li Yuan Gao |
author_facet | Tao Liu Guolong Li Yuan Gao |
author_sort | Tao Liu |
collection | DOAJ |
description | Aiming at the problems of local temperature increase of cable, heating of insulator porcelain disc, local heating of lightning arresters and transformers in the process of abnormal heat generation fault diagnosis of power equipment. This study proposes a target detection method that YOLOv4 (You Only Look Once version 4), combined with the infrared image data of power equipment to locate and diagnose the faulty heating area of power equipment. A dataset is established, and image annotation is made by detecting infrared image data of typical electrical equipment collected by the inspection department using a thermal imaging camera. Then this study established a target detection model to calculate the degree of overlap between the power equipment area and the fault area, which is used to determine whether the power equipment to be measured has abnormal heat generation. Finally, the optimal detection model was established by analyzing 6000 test samples in the four kinds of power equipment image dataset. The detection results are compared with Faster Region Convolutional Neural Network algorithms, Single-Shot multibox Detectors, and You Only Look Once version 3. The results show that YOLOv4 has an average accuracy rate of 92.2%. The YOLOv4 model established in this study can effectively detect anomalies in the infrared image of power equipment can be effectively applied to infrared detection of power equipment in substations. |
first_indexed | 2024-04-13T05:23:26Z |
format | Article |
id | doaj.art-ecfd4c84334d4d16b7b25d4a5a0ebf20 |
institution | Directory Open Access Journal |
issn | 2352-4847 |
language | English |
last_indexed | 2024-04-13T05:23:26Z |
publishDate | 2022-10-01 |
publisher | Elsevier |
record_format | Article |
series | Energy Reports |
spelling | doaj.art-ecfd4c84334d4d16b7b25d4a5a0ebf202022-12-22T03:00:40ZengElsevierEnergy Reports2352-48472022-10-018171180Fault diagnosis method of substation equipment based on You Only Look Once algorithm and infrared imagingTao Liu0Guolong Li1Yuan Gao2Corresponding author.; State Grid Tieling Electric Power Supply Company, Tieling, Liaoning 112000, ChinaState Grid Tieling Electric Power Supply Company, Tieling, Liaoning 112000, ChinaState Grid Tieling Electric Power Supply Company, Tieling, Liaoning 112000, ChinaAiming at the problems of local temperature increase of cable, heating of insulator porcelain disc, local heating of lightning arresters and transformers in the process of abnormal heat generation fault diagnosis of power equipment. This study proposes a target detection method that YOLOv4 (You Only Look Once version 4), combined with the infrared image data of power equipment to locate and diagnose the faulty heating area of power equipment. A dataset is established, and image annotation is made by detecting infrared image data of typical electrical equipment collected by the inspection department using a thermal imaging camera. Then this study established a target detection model to calculate the degree of overlap between the power equipment area and the fault area, which is used to determine whether the power equipment to be measured has abnormal heat generation. Finally, the optimal detection model was established by analyzing 6000 test samples in the four kinds of power equipment image dataset. The detection results are compared with Faster Region Convolutional Neural Network algorithms, Single-Shot multibox Detectors, and You Only Look Once version 3. The results show that YOLOv4 has an average accuracy rate of 92.2%. The YOLOv4 model established in this study can effectively detect anomalies in the infrared image of power equipment can be effectively applied to infrared detection of power equipment in substations.http://www.sciencedirect.com/science/article/pii/S2352484722009234YOLOv4Infrared imagingDeep learningFault diagnosis |
spellingShingle | Tao Liu Guolong Li Yuan Gao Fault diagnosis method of substation equipment based on You Only Look Once algorithm and infrared imaging Energy Reports YOLOv4 Infrared imaging Deep learning Fault diagnosis |
title | Fault diagnosis method of substation equipment based on You Only Look Once algorithm and infrared imaging |
title_full | Fault diagnosis method of substation equipment based on You Only Look Once algorithm and infrared imaging |
title_fullStr | Fault diagnosis method of substation equipment based on You Only Look Once algorithm and infrared imaging |
title_full_unstemmed | Fault diagnosis method of substation equipment based on You Only Look Once algorithm and infrared imaging |
title_short | Fault diagnosis method of substation equipment based on You Only Look Once algorithm and infrared imaging |
title_sort | fault diagnosis method of substation equipment based on you only look once algorithm and infrared imaging |
topic | YOLOv4 Infrared imaging Deep learning Fault diagnosis |
url | http://www.sciencedirect.com/science/article/pii/S2352484722009234 |
work_keys_str_mv | AT taoliu faultdiagnosismethodofsubstationequipmentbasedonyouonlylookoncealgorithmandinfraredimaging AT guolongli faultdiagnosismethodofsubstationequipmentbasedonyouonlylookoncealgorithmandinfraredimaging AT yuangao faultdiagnosismethodofsubstationequipmentbasedonyouonlylookoncealgorithmandinfraredimaging |