Insulator Defect Detection Model for Transmission Lines Under Complex Weather Conditions Based on CSI-YOLO

XIANG Guodong; QI Haoyu; LI Feng; CHEN Wei; LUAN Jin; CHEN Fang; TAN Aiguo

doi:10.13296/j.1001-1609.hva.2025.10.019

您当前的位置：

首页 >

文章列表页 >

Insulator Defect Detection Model for Transmission Lines Under Complex Weather Conditions Based on CSI-YOLO

Digital Twin Technology and Applications for Multi-scenario in New Power System | 更新时间：2025-10-21

- Insulator Defect Detection Model for Transmission Lines Under Complex Weather Conditions Based on CSI-YOLO
- High Voltage Apparatus Vol. 61, Issue 10, Pages: 179-190(2025)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2025.10.019
  CLC：
- Received：07 April 2025，
  
  Revised：2025-07-21，
  
  Published：16 October 2025
- 稿件说明：
移动端阅览
XIANG Guodong, QI Haoyu, LI Feng, et al. Insulator Defect Detection Model for Transmission Lines Under Complex Weather Conditions Based on CSI-YOLO[J]. High voltage apparatus, 2025, 61(10): 179-190.
DOI：

XIANG Guodong, QI Haoyu, LI Feng, et al. Insulator Defect Detection Model for Transmission Lines Under Complex Weather Conditions Based on CSI-YOLO[J]. High voltage apparatus, 2025, 61(10): 179-190. DOI： 10.13296/j.1001-1609.hva.2025.10.019.

摘要

针对复杂场景下绝缘子缺陷检测模型精度低以及参数量大的问题，文中在YOLOv8s的基础上提出一种CSI-YOLO的轻量化绝缘子缺陷检测模型。首先结合ADown和DySample采样技术，增强模型细节特征捕获能力；其次在特征同和网络引入TFE模块和改进后的Dy-SSFF模块，提升目标特征融合度；之后使用DyHead检测头提升目标定位能力；最后使用通道剪枝技术，削减模型冗余参数。实验结果表明：所提CSI-YOLO相较于原始YOLOv8s，精准率提高了2.38%，召回率提高了1.22%，

mAP

@0.5提高了1.84%，速度提升了31.46%，参数量仅为YOLOv8s的59.64%，权重大小达到4.5 MB，验证所提方法在复杂天气条件下，能准确识别输电线路可见光图像中的绝缘子缺陷。

Abstract

In view of the problem of low accuracy and large parameters of insulator defect detection model under complex scenarios

in this paper aCSI-YOLOlightweight insulator defect detection model based on YOLOv8s is proposed. First

ADown and DySample sampling techniques are combined to enhance the capture ability of detailed feature of the model. Then

TFE module and improved Dy-SSFF module are introduced into the feature sum network to improve the fusion degree of target features. After that

the DyHead detection head is used to improve the target positioning ability. Finally

the channel pruning technique is used to reduce the redundant parameters of the model. The experimental results show that the proposedCSI-YOLO

compared with the original YOLOv8s

improves the accuracy rate by 2.38%

the recall rate by 1.22%

the

mAP

@0.5 by 1.84%

and the speed by 31.46%. The number of parameters is only 59.64%of YOLOv8s

and the weight size reaches 4.5 MB. It is verified that the proposed method can accurately identify the insulator defects in the visible light image of the transmission line under complex weather conditions.

关键词

Keywords

references

刘传洋 , 吴一全 . 基于深度学习的输电线路视觉检测方法研究进展 [J ] . 中国电机工程学报 , 2023 , 43 ( 19 ): 7423 - 7445 .

LIU Chuanyang , WU Yiquan . Research progress of vision detection methods based on deep learning for transmission lines [J ] . Proceedings of the CSEE , 2023 , 43 ( 19 ): 7423 - 7445 .

文思予 , 张上 , 张朝阳 , 等 . 基于改进YOLOv8s的多尺度检测算法 [J ] . 现代电子技术 , 2024 , 47 ( 15 ): 133 - 138 .

WEN Siyu , ZHANG Shang , ZHANG Chaoyang , et al . Multi-scale object detection algorithm based on improved YOLOv8s [J ] . Modern Electronics Technique , 2024 , 47 ( 15 ): 133 - 138 .

何锦强 , 李锐海 , 李昊 , 等 . 基于Yolov5与Grabcut的架空线路绝缘子可见光图像自动识别与分割方法 [J ] . 南方电网技术 , 2023 , 17 ( 6 ): 128 - 135 .

HE Jinqiang , LI Ruihai , LI Hao , et al . Visible light image automatic recognition and segmentation method for overhead power line insulators based on Yolov5 and Grabcut [J ] . Southern Power System Technology , 2023 , 17 ( 6 ): 128 - 135 .

汤璐 , 王淑青 , 王年涛 , 等 . 基于改进YOLOX网络的雾天绝缘子缺陷检测 [J ] . 高压电器 , 2024 , 60 ( 3 ): 223 - 228 .

TANG Lu , WANG Shuqing , WANG Niantao , et al . Insulator defect detection in foggy condition based on improved YOLOX network [J ] . High Voltage Apparatus , 2024 , 60 ( 3 ): 223 - 228 .

杨桢 , 刘易宸 , 李鑫 , 等 . 基于深度学习的输电线路绝缘子故障检测方法 [J ] . 电气工程学报 , 2024 , 19 ( 2 ): 325 - 334 .

YANG Zhen , LIU Yichen , LI Xin , et al . Insulator fault detection method for transmission line based on deep learning [J ] . Journal of Electrical Engineering , 2024 , 19 ( 2 ): 325 - 334 .

袁博雅 , 李尧 , 叶青 . 面向输电线路绝缘子的GER-YOLO缺陷检测算法 [J ] . 激光与光电子学进展 , 2024 , 61 ( 22 ): 139 - 149 .

YUAN Boya , LI Yao , YE Qing . GER-YOLO fault-detection algorithm for transmission-line insulators [J ] . Laser & Optoelectronics Progress , 2024 , 61 ( 22 ): 139 - 149 .

叶翔 , 孙嘉兴 , 甘永叶 , 等 . 改进YOLOv3模型在无人机巡检输电线路部件缺陷检测中的应用研究 [J ] . 电测与仪表 , 2023 , 60 ( 5 ): 85 - 91 .

YE Xiang , SUN Jiaxing , GAN Yongye , et al . Application of improved YOLOv3 model in defect detection of transmission line components in UAV patrol inspection [J ] . Electrical Measurement&Instrumentation , 2023 , 60 ( 5 ): 85 - 91 .

LIU Jingjing , LIU Chuanyang , WU Yiquan , et al . Insulators'identification and missing defect detection in aerial images based on cascaded YOLO models [J ] . Computational Intelligence and Neuroscience , 2022 ( 8 ): 7113765 .

YANG Lei , SONG Shouan , NIU Yong , et al . A lightweight defect detection algorithm of insulators for power inspection [C ] // 2021 IEEE International Conference on Mechatronics and Automation (ICMA) . Japan : IEEE , 2021 : 281 - 286 .

ZHANG Z D , ZHANG B , LAN Z C , et al . FINet:An insulator dataset and detection benchmark based on synthetic fog and improved YOLOv5 [J ] . IEEE Transactions on Instrumentation and Measurement , 2022 ( 71 ): 1 - 8 .

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

杨阳 , 杨帅 , 闫敏 , 等 . 基于UDD-YOLO的边缘端绝缘子放电严重程度评估算法 [J ] . 电子测量与仪器学报 , 2024 , 38 ( 1 ): 219 - 227 .

YANG Yang , YANG Shuai , YAN Min , et al . UDD-YOLO based edge-end insulator discharge severity assessment algorithm [J ] . Journal of Electronic Measurement and Instrumentation , 2024 , 38 ( 1 ): 219 - 227 .

陈奎 , 刘晓 , 贾立娇 , 等 . 基于轻量化网络与增强多尺度特征融合的绝缘子缺陷检测 [J ] . 高电压技术 , 2024 , 50 ( 3 ): 1289 - 1300 .

CHEN Kui , LIU Xiao , JIA Lijiao , et al . Insulator defect detection based on lightweight network and enhanced multi-scale feature fusion [J ] . High Voltage Engineering , 2024 , 50 ( 3 ): 1289 - 1300 .

贾晓芬 , 吴雪茹 , 赵佰亭 . 绝缘子自爆缺陷的轻量化检测网络DE-YOLO [J ] . 电子测量与仪器学报 , 2023 , 37 ( 5 ): 28 - 35 .

JIA Xiaofen , WU Xueru , ZHAO Baiting . Lightweight detection network for insulator self-detonation defect DE-YOLO [J ] . Journal of Electronic Measurement and Instrumentation , 2023 , 37 ( 5 ): 28 - 35 .

何宁辉 , 王世杰 , 刘军福 , 等 . 基于深度学习的航拍图像绝缘子缺失检测方法研究 [J ] . 电力系统保护与控制 , 2021 , 49 ( 12 ): 132 - 140 .

HE Ninghui , WANG Shijie , LIU Junfu , et al . Research on infrared image missing insulator detection method based on deep learning [J ] . Power System Protection and Control , 2021 , 49 ( 12 ): 132 - 140 .

NINGHUI H E , WANG Shijie , LIU Junfu , et al . Research on infrared image missing insulator detection method based on deep learning [J ] . Power System Protection and Control , 2021 , 49 ( 12 ): 132 - 140 .

任爽 , 商继财 , 杨凯 , 等 . 改进YOLOv4的绝缘子图像检测模型 [J ] . 广东电力 , 2023 , 36 ( 1 ): 94 - 101 .

REN Shuang , SHANG Jicai , YANG Kai , et al . Insulator image detection model based on improved YOLOv4 [J ] . Guangdong Electric Power , 2023 , 36 ( 1 ): 94 - 101 .

胡依伦 , 杨俊 , 许聪源 , 等 . PIC2f-YOLO:金属表面缺陷检测轻量化方法 [J ] . 光电工程 , 2025 , 52 ( 1 ): 86 - 100 .

HU Yilun , YANG Jun , XU Congyuan , et al . PIC2f-YOLO:A lightweight method for the detection of metal surface defects [J ] . Opto-Electronic Engineering , 2025 , 52 ( 1 ): 86 - 100 .

王慧云 , 赵俊生 , 王禹 , 等 . 面向无人边防的复杂环境遮挡小目标检测算法 [J ] . 电子测量技术 , 2024 , 47 ( 21 ): 168 - 177 .

WANG Huiyun , ZHAO Junsheng , WANG Yu , et al . Complex environment occlusion small target detection algorithm for unmanned border defense [J ] . Electronic Measurement Technology , 2024 , 47 ( 21 ): 168 - 177 .

KANG Ming , TING C M , TING F F , et al . ASF-YOLO:A novel YOLO model with attentional scale sequence fusion for cell instance segmentation [J ] . Image and Vision Computing , 2024 ( 147 ): 105057 .

DAI Xiyang , CHEN Yinpeng , XIAO Bin , et al . Dynamic head:Unifying object detection heads with attentions [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . USA : IEEE , 2021 : 7369 - 7378 .

FANG Gongfan , MA Xinyin , SONG Mingli , et al . DepGraph:Towards any structural pruning [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Canada : IEEE , 2023 : 16091 - 16101 .

HAO Yanpeng , LIANG Wei , YANG Lin , et al . Methods of image recognition of overhead power line insulators and ice types based on deep weakly - supervised and transfer learning [J ] . IET Generation Transmission&Distribution , 2022 , 16 ( 11 ): 2140 - 2153 .

孙浩 , 丁毅 , 胡岳 , 等 . 多电飞机电机绝缘研究现状和未来挑战 [J ] . 大电机技术 , 2023 ( 4 ): 1 - 10 .

SUN Hao , DING Yi , HU Yue , et al . Research status and future challenges of more electric aircraft motor insulation [J ] . Large Electric Machine and Hydraulic Turbine , 2023 ( 4 ): 1 - 10 .

张宁 , 王鹏 , 刘智捷 , 等 . 流—电耦合场中金属颗粒群的荷电计算及影响因素研究 [J ] . 电工技术学报 , 2024 , 39 ( 17 ): 5534 - 5544 .

ZHANG Ning , WANG Peng , LIU Zhijie , et al . Study on the charge calculation and influencing factors of metal particle groups in fluidelectric coupling field [J ] . Transactions of China Electrotechnical Society , 2024 , 39 ( 17 ): 5534 - 5544 .

李术林 , 夏静 , 胡道雄 , 等 . 某大型永磁直驱风力发电机低挥发份型绝缘系统开发及评估 [J ] . 大电机技术 , 2024 ( 4 ): 69 - 80 .

LI Shulin , XIA Jing , HU Daoxiong , et al . Development and evaluation of low volatile insulation system for a large permanent magnet direct - drive wind turbine generator [J ] . Large Electric Machine and Hydraulic Turbine , 2024 ( 4 ): 69 - 80 .

顾惠杰 , 陆顺豪 , 龚春彬 , 等 . 基于信号极值检测分段法和ITDPE-PCA算法的变压器绕组变形超声检测信号去噪研究 [J ] . 变压器 , 2023 , 60 ( 3 ): 36 - 42 .

GU Huijie , LU Shunhao , GONG Chunbin , et al . Research on denoising of ultrasonic detection signal of transformer winding deformation based on signal extremum detection segmentation method and ITD-PE-PCA algorithm [J ] . Transformer , 2023 , 60 ( 3 ): 36 - 42 .

李金池 , 梁超 , 张林 . 变流器接地检测电路对电机定子绕组绝缘的影响 [J ] . 大电机技术 , 2024 ( 5 ): 52 - 57 .

LI Jinchi , LIANG Chao , ZHANG Lin . Impact on stator winding insulation of traction converter grouding detection circuit [J ] . Large Electric Machine and Hydraulic Turbine , 2024 ( 5 ): 52 - 57 .

张宁 , 刘士利 , 郝建 , 等 . 变压器油中气泡杂质相局部放电特性研究综述 [J ] . 电工技术学报 , 2023 , 38 ( 10 ): 2757 - 2776 .

ZHANG Ning , LIU Shili , HAO Jian , et al . Review on partial discharge characteristics of bubble impurity phase in transformer oil [J ] . Transactions of China Electrotechnical Society , 2023 , 38 ( 10 ): 2757 - 2776 .

黄盛洁 , 姚文捷 . 数字技术用于电力变压器局部放电定位 [J ] . 变压器 , 2023 , 60 ( 1 ): 35 - 40 .

HUANG Shengjie , YAO Wenjie . Digital technology for partial discharge location of power transformer [J ] . Transformer , 2023 , 60 ( 1 ): 35 - 40 .

刘永 , 杨在葆 , 韩克俊 , 等 . 基于电容耦合传递关系的局放故障定位技术研究及工程应用 [J ] . 变压器 , 2023 , 60 ( 2 ): 54 - 58 .

LIU Yong , YANG Zaibao , HAN Kejun , et al . Research and engineering application on fault localization technology of PD test based on capacitive coupling transfer relationship [J ] . Transformer , 2023 , 60 ( 2 ): 54 - 58 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Application of Improved YOLOv11n in Detection of Main Defects of Insulators on Transmission Lines

Application of GIS Disconnector Status Monitoring Based on GIS-SegFormer

Multiple Defect Detection of Insulators Based on Improved YOLOv5 Algorithm

Research and Development of Lightweight 126 kV Gas Insulated Switchgear

Related Author

LIU Hongzhi

MA Yue

QIU Bin

WANG Kai

XIAO Zhongyang

GUO Xu

QIN Ruofeng

CHEN Zhuo

Related Institution

辽宁工程技术大学电气与控制工程学院，辽宁葫芦岛 125105Faculty of Electrical and Control Engineering, Liaoning Technical University, Liaoning Huludao 125105, China

国家电网葫芦岛供电公司，辽宁葫芦岛 125000State Grid Huludao Power Supply Company, Liaoning Huludao 125000, China

国网内蒙古东部电力有限公司通辽供电公司，内蒙古通辽 028000Tongliao Power Supply Company, State Grid Inner Mongolia Eastern Power Co., Inner Mongolia Tongliao 028000, China

国网内蒙古东部电力有限公司，呼和浩特 010010State Grid Inner Mongolia Eastern Power Co., Ltd., Hohhot 010010, China

上海思源高压开关有限公司，上海 201108Shanghai Siyuan High Voltage Switch Co., Ltd., Shanghai 201108, China

⁰