Insulator Defect Detection Algorithm Based on Improved YOLOv11n

Ensuring the reliability and safety of electrical power systems requires the efficient detection of defects in high-voltage transmission line insulators, which play a critical role in electrical isolation and mechanical support. Environmental factors often lead to insulator defects, highlighting the...

Full description

Saved in:
Bibliographic Details
Main Authors: Junmei Zhao, Shangxiao Miao, Rui Kang, Longkun Cao, Liping Zhang, Yifeng Ren
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/5/1327
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850052699619328000
author Junmei Zhao
Shangxiao Miao
Rui Kang
Longkun Cao
Liping Zhang
Yifeng Ren
author_facet Junmei Zhao
Shangxiao Miao
Rui Kang
Longkun Cao
Liping Zhang
Yifeng Ren
author_sort Junmei Zhao
collection DOAJ
description Ensuring the reliability and safety of electrical power systems requires the efficient detection of defects in high-voltage transmission line insulators, which play a critical role in electrical isolation and mechanical support. Environmental factors often lead to insulator defects, highlighting the need for accurate detection methods. This paper proposes an enhanced defect detection approach based on a lightweight neural network derived from the YOLOv11n architecture. Key innovations include a redesigned C3k2 module that incorporates multidimensional dynamic convolutions (ODConv) for improved feature extraction, the introduction of Slimneck to reduce model complexity and computational cost, and the application of the WIoU loss function to optimize anchor box handling and to accelerate convergence. Experimental results demonstrate that the proposed method outperforms existing models like YOLOv8 and YOLOv10 in precision, recall, and mean average precision (mAP), while maintaining low computational complexity. This approach provides a promising solution for real-time, high-accuracy insulator defect detection, enhancing the safety and reliability of power transmission systems.
format Article
id doaj-art-a82a1cbf87f64a16a3b5d47a4a01f613
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-a82a1cbf87f64a16a3b5d47a4a01f6132025-08-20T02:52:45ZengMDPI AGSensors1424-82202025-02-01255132710.3390/s25051327Insulator Defect Detection Algorithm Based on Improved YOLOv11nJunmei Zhao0Shangxiao Miao1Rui Kang2Longkun Cao3Liping Zhang4Yifeng Ren5The College of Electrical and Control Engineering, North University of China, Taiyuan 030051, ChinaThe College of Electrical and Control Engineering, North University of China, Taiyuan 030051, ChinaThe College of Electrical and Control Engineering, North University of China, Taiyuan 030051, ChinaThe College of Electrical and Control Engineering, North University of China, Taiyuan 030051, ChinaThe College of Electrical and Control Engineering, North University of China, Taiyuan 030051, ChinaThe College of Electrical and Control Engineering, North University of China, Taiyuan 030051, ChinaEnsuring the reliability and safety of electrical power systems requires the efficient detection of defects in high-voltage transmission line insulators, which play a critical role in electrical isolation and mechanical support. Environmental factors often lead to insulator defects, highlighting the need for accurate detection methods. This paper proposes an enhanced defect detection approach based on a lightweight neural network derived from the YOLOv11n architecture. Key innovations include a redesigned C3k2 module that incorporates multidimensional dynamic convolutions (ODConv) for improved feature extraction, the introduction of Slimneck to reduce model complexity and computational cost, and the application of the WIoU loss function to optimize anchor box handling and to accelerate convergence. Experimental results demonstrate that the proposed method outperforms existing models like YOLOv8 and YOLOv10 in precision, recall, and mean average precision (mAP), while maintaining low computational complexity. This approach provides a promising solution for real-time, high-accuracy insulator defect detection, enhancing the safety and reliability of power transmission systems.https://www.mdpi.com/1424-8220/25/5/1327insulator defect detectionyou only look once (YOLO)multidimensional dynamic convolutions (ODConv)
spellingShingle Junmei Zhao
Shangxiao Miao
Rui Kang
Longkun Cao
Liping Zhang
Yifeng Ren
Insulator Defect Detection Algorithm Based on Improved YOLOv11n
Sensors
insulator defect detection
you only look once (YOLO)
multidimensional dynamic convolutions (ODConv)
title Insulator Defect Detection Algorithm Based on Improved YOLOv11n
title_full Insulator Defect Detection Algorithm Based on Improved YOLOv11n
title_fullStr Insulator Defect Detection Algorithm Based on Improved YOLOv11n
title_full_unstemmed Insulator Defect Detection Algorithm Based on Improved YOLOv11n
title_short Insulator Defect Detection Algorithm Based on Improved YOLOv11n
title_sort insulator defect detection algorithm based on improved yolov11n
topic insulator defect detection
you only look once (YOLO)
multidimensional dynamic convolutions (ODConv)
url https://www.mdpi.com/1424-8220/25/5/1327
work_keys_str_mv AT junmeizhao insulatordefectdetectionalgorithmbasedonimprovedyolov11n
AT shangxiaomiao insulatordefectdetectionalgorithmbasedonimprovedyolov11n
AT ruikang insulatordefectdetectionalgorithmbasedonimprovedyolov11n
AT longkuncao insulatordefectdetectionalgorithmbasedonimprovedyolov11n
AT lipingzhang insulatordefectdetectionalgorithmbasedonimprovedyolov11n
AT yifengren insulatordefectdetectionalgorithmbasedonimprovedyolov11n