A Method of Real-Time Insulator Defect Detection Based on Improved YOLOv5s Algorithm

YAO Chunmei; XI Yanhui

doi:10.3969/j.issn.1008-0198.2025.04.017

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

A Method of Real-Time Insulator Defect Detection Based on Improved YOLOv5s Algorithm

更新时间：2025-12-08

- A Method of Real-Time Insulator Defect Detection Based on Improved YOLOv5s Algorithm
- Vol. 45, Issue 4, Pages: 119-125(2025)
- 作者机构：
  
  长沙理工大学电气与信息工程学院,湖南,长沙,410114
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1008-0198.2025.04.017
  CLC： TM854
- Published Online：05 September 2025，
  
  Published：05 September 2025
- 稿件说明：
移动端阅览
姚春梅, 席燕辉. 一种基于改进YOLOv5s算法的实时绝缘子缺陷检测方法[J]. 湖南电力, 2025, 45(4): 119-125.

YAO Chunmei, XI Yanhui. A Method of Real-Time Insulator Defect Detection Based on Improved YOLOv5s Algorithm[J]. 2025, 45(4): 119-125.
姚春梅, 席燕辉. 一种基于改进YOLOv5s算法的实时绝缘子缺陷检测方法[J]. 湖南电力, 2025, 45(4): 119-125. DOI： 10.3969/j.issn.1008-0198.2025.04.017.

YAO Chunmei, XI Yanhui. A Method of Real-Time Insulator Defect Detection Based on Improved YOLOv5s Algorithm[J]. 2025, 45(4): 119-125. DOI： 10.3969/j.issn.1008-0198.2025.04.017.

摘要

现有绝缘子缺陷检测模型存在参数量大、推理速度慢等问题

难以满足电力巡检的实时性要求

同时无人机在巡检过程中面临雾霾、低照度等复杂环境干扰。针对以上问题

提出一种基于改进的轻量化YOLOv5s的绝缘子缺陷检测方法。该方法通过三重优化策略实现模型轻量化与检测精度之间的平衡：首先

利用轻量化模块对YOLOv5s网络进行深度优化

降低模型复杂度;其次

网络使用双向加权特征金字塔网络结构增强多尺度特征融合能力

并结合SIoU损失函数提升检测精度与收敛速度;最后

采用合成雾算法提升模型在复杂环境下的泛化性能。实验结果表明

所提模型参数、浮点运算数与模型存储大小仅为1.74×10

、3.5×10

与3.9 MB

mAP@0.5达到92.8%。

Abstract

Aiming at the issues of large parameter count and slow inference speed

which is difficult to meet the demand for real-time online electric power inspection

and considering the complex environmental interferences such as the fog or low illumination during actual unmanned aerial vehicle inspection processes

an insulator defect detection method based on improved lightweight YOLOv5s is proposed. This method achieves a balance between model lightweighting and detection accuracy through a triple optimization strategy. Firstly

the YOLOv5s network is deeply optimized by using lightweight modules

which significantly reduces the model complexity. Secon

dly

the network adopts the bidirectional feature pyramid network structure to enhance the multi-scale feature fusion capability

and combines the SIoU loss function to improve detection accuracy and convergence speed. Finally

the synthetic fog algorithm is employed to effectively enhance the generalization performance of the model in complex environments. Experimental results show that the parameters

floating point operands and size of the proposed model are only 1.74×10

、3.5×10

and 3.9 MB

and the mAP@0.5 reaches 92.8%.

关键词

Keywords

references

王道累,张世恒,袁斌霞,等. 基于改进YOLOv5的轻量化玻璃绝缘子自爆缺陷检测研究[J]. 高电压技术,2023,49(10):4382-4390.

GOUDA O E,DARWISH M M F,MAHMOUD K,et al. Pollution severity monitoring of high voltage transmission line insulators using wireless device based on leakage current bursts[J]. IEEE Access,2022,10:53713-53723.

熊炜,黄玉谦,孟圣哲. 基于改进YOLOv8算法的绝缘子缺陷检测模型[J]. 电子测量技术,2024,47(12):132-139.

WANG S S,ZOU X Y,ZHU W,et al.Insulator defects detection for aerial photography of the power grid using you only look once algorithm[J]. Journal of Electrical Engineering & Technology,2023,18(4):3287-3300.

ZHAI Y J,WANG D,ZHANG M L,et al.Fault detection of insulator based on saliency and adaptive morphology[J]. Multimedia Tools and Applications,2017,76(9):12051-12064.

廖丽瑛,刘洪. 基于改进YOLOv8的绝缘子自爆缺陷检测[J]. 电子测量技术,2024,47(18):138-144.

李运堂,张坤,李恒杰,等. 基于改进YOLOv5s网络的绝缘子缺陷检测[J]. 浙江大学学报,2024,58(12):2469-2478,2499.

姜香菊,王瑞彤,马彦鸿. 基于轻量级改进RT-DETR边缘部署算法的绝缘子缺陷检测[J]. 电工技术学报,2025,40(3):842-854.

郑含博,胡思佳,梁炎燊,等. 基于YOLO-2MCS的输电线路走廊隐患目标检测方法[J]. 电工技术学报,2024,39(13):4164-4175.

MA Y P,LI Q W,CHU L L,et al.Real-time detection and spatial localization of insulators for UAV inspection based on binocular stereo vision[J]. Remote Sensing,2021,13(2):230.

WU Q G,AN J B,LIN B.A texture segmentation algorithm based on PCA and global minimization active contour model for aerial insulator images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2012,5(5):1509-1518.

ZHANG G N,LIU Z G,HAN Y.Automatic recognition for catenary insulators of high-speed railway based on contourlet transform and Chan-Vese model[J]. Optik,2016,127(1):215-221.

REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas,NV,USA. IEEE,2016:779-788.

WANG J Y,LI Y N,CHEN W X.Detection of glass insulators using deep neural networks based on optical imaging[J]. Remote Sensing,2022,14(20):5153.

JIANG H,QIU X J,CHEN J,et al.Insulator fault detection in aerial images based on ensemble learning with multi-level perception[J]. IEEE Access,2019,7:61797-61810.

ZHOU M,LI B,WANG J,et al.Fault detection method of glass insulator aerial image based on the improved YOLOv5[J]. IEEE Transactions on Instrumentation and Measurement,2023,72:3269099.

HAO K,CHEN G K,ZHAO L,et al.An insulator defect detection model in aerial images based on multiscale feature pyramid network[J]. IEEE Transactions on Instrumentation and Measurement,2022,71:3200861.

ZHANG T,ZHANG Y N,XIN M,et al.A light-weight network for small insulator and defect detection using UAV imaging based on improved YOLOv5[J]. Sensors,2023,23(11):5249.

YI W G,MA S W,LI R H.Insulator and defect detection model based on improved YOLO-S[J]. IEEE Access,2023,11:93215-93226.

CHENG Y B.Detection of power line insulator based on enhanced YOLO Model[C]//2022 IEEE Asia-Pacific Conference on Image Processing,Electronics and Computers(IPEC). Dalian,China. IEEE,2022:626-632.

TIAN X X,ZHANG M T,LU G Y.Power line insulator defect detection using CNN with dense connectivity and efficient attention mechanism[J]. Multimedia Tools and Applications,2024,83(10):28305-28322.

XIN R,CHEN X,WU J Y,et al.Insulator umbrella disc shedding detection in foggy weather[J]. Sensors,2022,22(13):4871.

GAO G L,CAO J,BAO C,et al.A novel transformer-based attention network for image dehazing[J]. Sensors,2022,22(9):3428.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Press Connection Pipe Detection Method for Transmission Line in Field Complex Background Based on Improved Convolutional Network

Related Author

ZOU Dehua

ZHANG Hongwei

QIAO Lei

ZHAO Liyuan

JIANG Wei

Related Institution

State Grid Hunan Ultra-High Voltage Transmission Company

Hunan Province Key Laboratory of Intelligent Live Working Technology and Equipment (ROBOT)

Live Inspection and Intelligent Operation Technology State Grid Corporation Laboratory

School of Mechanical Engineering and Automation, Wuhan Textile University

AI问答

⁰