Insulator defect detection under extreme weather based on synthetic weather algorithm and improved YOLOv7

Abstract Efficient and accurate insulator defect detection is essential for maintaining the safe and stable operation of transmission lines. However, the detection effectiveness is adversely impacted by complex and changeable environmental backgrounds, particularly under extreme weather that elevate...

Full description

Saved in:
Bibliographic Details
Main Authors: Yong Yang, Shuai Yang, Chuan Li, Yunxuan Wang, Xiaoqian Pi, Yuxin Lu, Ruohan Wu
Format: Article
Language:English
Published: Wiley 2025-02-01
Series:High Voltage
Online Access:https://doi.org/10.1049/hve2.12513
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850027497679224832
author Yong Yang
Shuai Yang
Chuan Li
Yunxuan Wang
Xiaoqian Pi
Yuxin Lu
Ruohan Wu
author_facet Yong Yang
Shuai Yang
Chuan Li
Yunxuan Wang
Xiaoqian Pi
Yuxin Lu
Ruohan Wu
author_sort Yong Yang
collection DOAJ
description Abstract Efficient and accurate insulator defect detection is essential for maintaining the safe and stable operation of transmission lines. However, the detection effectiveness is adversely impacted by complex and changeable environmental backgrounds, particularly under extreme weather that elevates accident risks. Therefore, this research proposes a high‐precision intelligent strategy based on the synthetic weather algorithm and improved YOLOv7 for detecting insulator defects under extreme weather. The proposed methodology involves augmenting the dataset with synthetic rain, snow, and fog algorithm processing. Additionally, the original dataset undergoes augmentation through affine and colour transformations to improve model's generalisation performance under complex power inspection backgrounds. To achieve higher recognition accuracy in severe weather, an improved YOLOv7 algorithm for insulator defect detection is proposed, integrating focal loss with SIoU loss function and incorporating an optimised decoupled head structure. Experimental results indicate that the synthetic weather algorithm processing significantly improves the insulator defect detection accuracy under extreme weather, increasing the mean average precision by 2.4%. Furthermore, the authors’ improved YOLOv7 model achieves 91.8% for the mean average precision, outperforming the benchmark model by 2.3%. With a detection speed of 46.5 frames per second, the model meets the requirement of real‐time detection of insulators and their defects during power inspection.
format Article
id doaj-art-6d0fda8c99f34929b2cb23c3c2bd8fcd
institution DOAJ
issn 2397-7264
language English
publishDate 2025-02-01
publisher Wiley
record_format Article
series High Voltage
spelling doaj-art-6d0fda8c99f34929b2cb23c3c2bd8fcd2025-08-20T03:00:09ZengWileyHigh Voltage2397-72642025-02-01101697710.1049/hve2.12513Insulator defect detection under extreme weather based on synthetic weather algorithm and improved YOLOv7Yong Yang0Shuai Yang1Chuan Li2Yunxuan Wang3Xiaoqian Pi4Yuxin Lu5Ruohan Wu6State Key Laboratory of Advanced Electromagnetic Engineering and Technology School of Electrical Engineering and Electronics Huazhong University of Science and Technology Wuhan ChinaState Key Laboratory of Advanced Electromagnetic Engineering and Technology School of Electrical Engineering and Electronics Huazhong University of Science and Technology Wuhan ChinaState Key Laboratory of Advanced Electromagnetic Engineering and Technology School of Electrical Engineering and Electronics Huazhong University of Science and Technology Wuhan ChinaState Key Laboratory of Advanced Electromagnetic Engineering and Technology School of Electrical Engineering and Electronics Huazhong University of Science and Technology Wuhan ChinaState Grid Hunan Electric Power Company Changsha ChinaState Key Laboratory of Advanced Electromagnetic Engineering and Technology School of Electrical Engineering and Electronics Huazhong University of Science and Technology Wuhan ChinaState Key Laboratory of Advanced Electromagnetic Engineering and Technology School of Electrical Engineering and Electronics Huazhong University of Science and Technology Wuhan ChinaAbstract Efficient and accurate insulator defect detection is essential for maintaining the safe and stable operation of transmission lines. However, the detection effectiveness is adversely impacted by complex and changeable environmental backgrounds, particularly under extreme weather that elevates accident risks. Therefore, this research proposes a high‐precision intelligent strategy based on the synthetic weather algorithm and improved YOLOv7 for detecting insulator defects under extreme weather. The proposed methodology involves augmenting the dataset with synthetic rain, snow, and fog algorithm processing. Additionally, the original dataset undergoes augmentation through affine and colour transformations to improve model's generalisation performance under complex power inspection backgrounds. To achieve higher recognition accuracy in severe weather, an improved YOLOv7 algorithm for insulator defect detection is proposed, integrating focal loss with SIoU loss function and incorporating an optimised decoupled head structure. Experimental results indicate that the synthetic weather algorithm processing significantly improves the insulator defect detection accuracy under extreme weather, increasing the mean average precision by 2.4%. Furthermore, the authors’ improved YOLOv7 model achieves 91.8% for the mean average precision, outperforming the benchmark model by 2.3%. With a detection speed of 46.5 frames per second, the model meets the requirement of real‐time detection of insulators and their defects during power inspection.https://doi.org/10.1049/hve2.12513
spellingShingle Yong Yang
Shuai Yang
Chuan Li
Yunxuan Wang
Xiaoqian Pi
Yuxin Lu
Ruohan Wu
Insulator defect detection under extreme weather based on synthetic weather algorithm and improved YOLOv7
High Voltage
title Insulator defect detection under extreme weather based on synthetic weather algorithm and improved YOLOv7
title_full Insulator defect detection under extreme weather based on synthetic weather algorithm and improved YOLOv7
title_fullStr Insulator defect detection under extreme weather based on synthetic weather algorithm and improved YOLOv7
title_full_unstemmed Insulator defect detection under extreme weather based on synthetic weather algorithm and improved YOLOv7
title_short Insulator defect detection under extreme weather based on synthetic weather algorithm and improved YOLOv7
title_sort insulator defect detection under extreme weather based on synthetic weather algorithm and improved yolov7
url https://doi.org/10.1049/hve2.12513
work_keys_str_mv AT yongyang insulatordefectdetectionunderextremeweatherbasedonsyntheticweatheralgorithmandimprovedyolov7
AT shuaiyang insulatordefectdetectionunderextremeweatherbasedonsyntheticweatheralgorithmandimprovedyolov7
AT chuanli insulatordefectdetectionunderextremeweatherbasedonsyntheticweatheralgorithmandimprovedyolov7
AT yunxuanwang insulatordefectdetectionunderextremeweatherbasedonsyntheticweatheralgorithmandimprovedyolov7
AT xiaoqianpi insulatordefectdetectionunderextremeweatherbasedonsyntheticweatheralgorithmandimprovedyolov7
AT yuxinlu insulatordefectdetectionunderextremeweatherbasedonsyntheticweatheralgorithmandimprovedyolov7
AT ruohanwu insulatordefectdetectionunderextremeweatherbasedonsyntheticweatheralgorithmandimprovedyolov7