Chain Insulator Detection Method Integrating Multi-directional Attention Information Aggregation and Network Pruning

TANG Yongheng; SUN Shuifa; LI Xuchen

doi:10.13296/j.1001-1609.hva.2025.10.018

您当前的位置：

首页 >

文章列表页 >

Chain Insulator Detection Method Integrating Multi-directional Attention Information Aggregation and Network Pruning

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

- Chain Insulator Detection Method Integrating Multi-directional Attention Information Aggregation and Network Pruning
- High Voltage Apparatus Vol. 61, Issue 10, Pages: 168-178(2025)
- 作者机构：
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(61871258)
- DOI：10.13296/j.1001-1609.hva.2025.10.018
  CLC：
- Received：21 March 2025，
  
  Revised：2025-06-20，
  
  Published：16 October 2025
- 稿件说明：
移动端阅览
TANG Yongheng, SUN Shuifa, LI Xuchen. Chain Insulator Detection Method Integrating Multi-directional Attention Information Aggregation and Network Pruning[J]. High voltage apparatus, 2025, 61(10): 168-178.
DOI：

TANG Yongheng, SUN Shuifa, LI Xuchen. Chain Insulator Detection Method Integrating Multi-directional Attention Information Aggregation and Network Pruning[J]. High voltage apparatus, 2025, 61(10): 168-178. DOI： 10.13296/j.1001-1609.hva.2025.10.018.

摘要

电力无人机巡检图像中复杂的背景、异物的遮挡以及多种天气下的光照影响使得绝缘子的准确识别仍是一个具有挑战性的任务。同时，现有的绝缘子检测算法不能有效表征多姿态和大长宽比的绝缘子串目标且算法参数量过大。因此，文中提出一种融合多方位注意力信息聚合与网络剪枝的链式绝缘子检测方法来检测复杂背景下的绝缘子目标。首先，该方法采用点—链式结构有效表征了多姿态的绝缘子串目标；其次，网络模型使用Drn-c42骨干网络从无人机巡检图像中提取绝缘子串图像特征；然后，通过多方位注意力聚合网络对图像进行特征细化并使网络模型以局部—全局—局部的方式更加关注于绝缘子目标的特征信息；此外，在兼顾模型性能的前提下为降低模型的复杂度，选定了合适的位置进行网络剪枝使得网络模型更加轻量化。在构建的绝缘子检测数据集上的实验结果表明，文中所提方法能有效检测绝缘子的位置和排列方向，也可以很容易扩展到其他工业领域链状目标检测任务中。

Abstract

The complex backgrounds in power drone inspection images

occlusion by foreign objects

and varying lighting variations under different diverse circumstances make accurate identification of insulators a challenging task. Meanwhile

the existing insulator detection algorithms can not effectively characterize multi-pose and largesapect-ratio insulator string targets while suffering from excessive parameter volumes. Therefore

in this paper a chain insulator detection method integrating multi-directional attention information aggregation and network pruning is proposed to identify the insulator target under complex backgrounds. First

the method employs a point-chain structure to effectively characterize the multi-pose insulator string targets；Then

the network model uses the Drnc42 backbone network to extract image features of insulator strings from drone inspection images. After that

a multidirectional attention aggregation network refines image features and enables the model to focus more on the insulator target information in a local-global-local manner. Moreover

for reducing model complexity while maintaining the modle’s performance

network pruning is applied at carefully selected positions to make the network model more lightweight. Experimental results on a constructed insulator detection dataset demonstrate that the pmethod proposed in this paper can effectively detect both position and orientation of insulators. Furthermore

the proposed algorithm framework can be readily extended to chain target detection tasks in other industrial domains.

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 .

游越 , 伊力哈木·亚尔买买提 . 基于改进YOLOv5在电力巡检中的目标检测算法研究 [J ] . 高压电器 , 2023 , 59 ( 2 ): 89 - 96 .

YOU Yue , YILIHAMU Yaermaimaiti . Research on target detection algorithm based on improved YOLOv5 in power patrol inspection [J ] . High Voltage Apparatus , 2023 , 59 ( 2 ): 89 - 96 .

李永福 , 陈立斌 , 惠君伟 , 等 . 基于EPSA-YOLOv5电力高空作业安全带佩戴检测 [J ] . 西安工程大学学报 , 2024 , 38 ( 2 ): 18 - 25 .

LI Yongfu , CHEN Libin , HUI Junwei , et al . Safety belt wearing detection for electric aloft work based on EPSA - YOLOv5 [J ] . Journal of Xi'an Polytechnic University , 2024 , 38 ( 2 ): 18 - 25 .

徐鹏雷 , 杨文刚 . 基于YOLO的输电线路鸟巢检测网络结构改进研究 [J ] . 智慧电力 , 2024 , 52 ( 4 ): 54 - 61 .

XU Penglei , YANG Wengang . Improvement of bird's nest detection network structure of transmission lines based on YOLO [J ] . Smart Power , 2024 , 52 ( 4 ): 54 - 61 .

王璞 , 谢晓娜 . 基于改进FCM算法的电力数据异常检测方法 [J ] . 电子设计工程 , 2023 , 31 ( 24 ): 33 - 37 .

WANG Pu , XIE Xiaona . Power abnormal data detection method based on improved FCM algorithm [J ] . Electronic Design Engineering , 2023 , 31 ( 24 ): 33 - 37 .

杨霞 , 苟亮 , 马倩 , 等 . 基于离群点检测算法的电力大数据异常值检测 [J ] . 电子设计工程 , 2023 , 31 ( 24 ): 61 - 64 .

YANG Xia , GOU Liang , MA Qian , et al . Outlier detection of electric power big data based on outlier detection algorithm [J ] . Electronic Design Engineering , 2023 , 31 ( 24 ): 61 - 64 .

高谭芮 , 刘忆宁 . 基于改进YOLOX的交通标志检测方法 [J ] . 电子设计工程 , 2023 , 31 ( 23 ): 189 - 195 .

GAO Tanrui , LIU Yining . Traffic sign detection method based on improved YOLOX [J ] . Electronic Design Engineering , 2023 , 31 ( 23 ): 189 - 195 .

王韵琳 , 冯天波 , 孙宁 , 等 . 融合注意力与多尺度特征的电力绝缘子缺陷检测方法 [J ] . 高电压技术 , 2024 , 50 ( 5 ): 1933 - 1942 .

WANG Yunlin , FENG Tianbo , SUN Ning , et al . Defect detection method for power insulators based on attention and multi-scale context information [J ] . High Voltage Engineering , 2024 , 50 ( 5 ): 1933 - 1942 .

王景焕 . 一类基于人工神经网络的三相异步电机断相检测方法 [J ] . 电子设计工程 , 2023 , 31 ( 5 ): 80 - 83 .

WANG Jinghuan . One method based on artificial neural networks for phase failure detection in three phase asynchronous motor [J ] . Electronic Design Engineering , 2023 , 31 ( 5 ): 80 - 83 .

胡一鸣 , 史鸿飞 , 张玉龙 , 等 . 基于行波全景故障特征自辨识的高阻接地故障检测方法 [J ] . 供用电 , 2023 , 40 ( 4 ): 39 - 46 .

HU Yiming , SHI Hongfei , ZHANG Yulong , et al . High impedance fault detection method based on traveling wave full waveform fault characteristics self-identification [J ] . Distribution & Utilization , 2023 , 40 ( 4 ): 39 - 46 .

毛王清 , 葛萱 , 王秀茹 , 等 . 基于等效阻抗降落的微电网故障检测方法研究 [J ] . 供用电 , 2023 , 40 ( 6 ): 48 - 55 .

MAO Wangqing , GE Xuan , WANG Xiuru , et al . Research on microgrid fault detection method based on equivalent impedance drop [J ] . Distribution&Utilization , 2023 , 40 ( 6 ): 48 - 55 .

庞清乐 , 韩松易 , 周泰 , 等 . 基于ASRUKF和IMC算法的电力信息物理系统虚假数据注入攻击检测 [J ] . 智慧电力 , 2024 , 52 ( 7 ): 111 - 118 .

PANG Qingle , HAN Songyi , ZHOU Tai , et al . False data injection attack detection of cyber-physical power system based on ASRUKF and IMC algorithms [J ] . Smart Power , 2024 , 52 ( 7 ): 111 - 118 .

张佳伟 , 张江南 , 吴坡 , 等 . 基于融合容积卡尔曼滤波的直流微电网虚假数据检测 [J ] . 智慧电力 , 2024 , 52 ( 3 ): 87 - 93 .

ZHANG Jiawei , ZHANG Jiangnan , WU Po , et al . False data detection in dcmicrogrids based on fusion of cubature kalman filters [J ] . Smart Power , 2024 , 52 ( 3 ): 87 - 93 .

王强 , 冯云涛 , 周超 . 基于GE-YOLO算法的输电线路绝缘子多类型缺陷检测研究 [J ] . 高压电器 , 2025 , 61 ( 6 ): 92 - 101 .

WANG Qiang , FENG Yuntao , ZHOU Chao , et al . Research on multi type defect detection of transmission line insulators based on GE-YOLO algorithm [J ] . High Voltage Apparatus , 2025 , 61 ( 6 ): 92 - 101 .

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 .

ZHAO Wenqing , XU Minfu , CHENG Xingfu , et al . An insulator in transmission lines recognition and fault detection model based on improved faster RCNN [J ] . IEEE Transactions on Instrumentation and Measurement , 2021 ( 70 ): 1 - 8 .

TAO Xian , ZHANG Dapeng , WANG Zihao , et al . Detection of power line insulator defects using aerial images analyzed with convolutional neural networks [J ] . IEEE Transactions on Systems, Man, and Cybernetics:Systems , 2020 , 50 ( 4 ): 1486 - 1498 .

LING Zenan , ZHANG Dongxia , QIU R C , et al . An accurate and real-time method of self-blast glass insulator location based on faster R-CNN and U-net with aerial images [J ] . CSEE Journal of Power and Energy Systems , 2019 , 5 ( 4 ): 474 - 482 .

SADYKOVA D , PERNEBAYEVA D , BAGHERI M , et al . IN-YOLO:Real-time detection of outdoor high voltage insulators using UAV imaging [J ] . IEEE Transactions on Power Delivery , 2020 , 35 ( 3 ): 1599 - 1601 .

WALEED D , MUKHOPADHYAY S , TARIQ U , et al . Drone-based ceramic insulators condition monitoring [J ] . IEEE Transactions on Instrumentation and Measurement , 2021 ( 70 ): 1 - 12 .

LIU Chuanyang , WU Yiquan , LIU Jingjing , et al . Insulator faults detection in aerial images from high-voltage transmission lines based on deep learning model [J ] . Applied Sciences , 2021 , 11 ( 10 ): 4647 .

BAO Wenxia , DU Xiang , WANG Nian , et al . A defect detection method based on BC-YOLO for transmission line components in UAV remote sensing images [J ] . Remote Sensing , 2022 , 14 ( 20 ): 5176 .

HAN Gujing , YUAN Qiwei , ZHAO Feng , et al . An improved algorithm for insulator and defect detection based on YOLOv4 [J ] . Electronics , 2023 , 12 ( 4 ): 933 .

HUANG Shiyi , DONG Xiaojie , WANG Yifan , et al . Detection of insulator burst position of lightweight YOLOv5 [C ] // Proceedings of the 8th International Conference on Computing and Artificial Intelligence . USA : ACM , 2022 : 573 - 578 .

LAN Ying , XU Wenxiang . Insulator defect detection algorithm based on a lightweight network [J ] . Journal of Physics:Conference Series , 2022 , 2181 ( 1 ): 012007 .

CHENG Bowen , XIAO Bin , WANG Jingdong , et al . HigherHRNet:Scale-aware representation learning for bottom-up human pose estimation [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR) . USA : IEEE , 2020 : 5385 - 5394 .

CAO Congqi , LU Yue , ZHANG Yanning . Context recovery and knowledge retrieval:A novel two-stream framework for video anomaly detection [J ] . IEEE Transactions on Image Processing:A Publication of the IEEE Signal Processing Society , 2024 ( 33 ): 1810 - 1825 .

CAO Zhe , SIMON T , WEI S E , et al . Realtime multi-person 2D pose estimation using part affinity fields [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR) . USA : IEEE , 2017 : 1302 - 1310 .

HOU Qibin , ZHOU Daquan , FENG Jiashi . Coordinate attention for efficient mobile network design [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR) . USA : IEEE , 2021 : 13708 - 13717 .

LU Xiaotong , DONG Weisheng , LI Xin , et al . Adaptive search-andtraining for robust and efficient network pruning [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2023 , 45 ( 8 ): 9325 - 9338 .

YU F , KOLTUN V , FUNKHOUSER T . Dilated residual networks [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR) . USA : IEEE , 2017 : 636 - 644 .

SANDLER M , HOWARD A , ZHU Menglong , et al . MobileNetV2:Inverted residuals and linear bottlenecks [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . USA : IEEE , 2018 : 4510 - 4520 .

GAO Shanghua , CHENG Mingming , ZHAO Kai , et al . Res2net:A new multi-scale backbone architecture [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2021 , 43 ( 2 ): 652 - 662 .

REN Shaoqing , HE Kaiming , GIRSHICK R , et al . Faster R-CNN:Towards real-time object detection with region proposal networks [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 , 39 ( 6 ): 1137 - 1149 .

LIU Wei , ANGUELOV D , ERHAN D , et al . SSD:Single shot MultiBox detector [C ] // Computer Vision-ECCV 2016 . Cham : Springer International Publishing , 2016 : 21 - 37 .

BOCHKOVSKIY A , WANG C Y , LIAO H Y M . Yolov4:Optimal speed and accuracy of object detection [EB/OL ] .[ 2025-03-21 ] . https://arxiv.org/abs/2004.10934 .

LIN T Y , GOYAL P , GIRSHICK R , et al . Focal loss for dense object detection [C ] // 2017 IEEE International Conference on Computer Vision(ICCV) . USA : IEEE , 2017 : 2999 - 3007 .

DONG Zhiwei , LI Guoxuan , LIAO Yue , et al . CentripetalNet:Pursuing high-quality keypoint pairs for object detection [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR) . USA : IEEE , 2020 : 10516 - 10525 .

WANG C Y , YEH I H , MARK LIAO H Y . YOLOv9:Learning what you want to learn using programmable gradient information [C ] // Computer Vision(ECCV 2024) . Cham : Springer Nature Switzerland , 2025 : 1 - 21 .

刘江 , 关向雨 , 温跃泉 , 等 . 基于改进YOLOv4的GIS红外特征识别与温度提取方法 [J ] . 电力工程技术 , 2023 , 42 ( 1 ): 162 - 168 .

LIU Jiang , GUAN Xiangyu , WEN Yuequan , et al . Infrared feature recognition and temperature extraction method of GIS components based on improved YOLOv4 [J ] . Electric Power Engineering Technology , 2023 , 42 ( 1 ): 162 - 168 .

赵伟达 , 陈海文 , 郭陆阳 , 等 . 基于YOLO-E与改进OCRNet图像分割的变电站仪表读数自适应识别方法 [J ] . 电力建设 , 2023 , 44 ( 11 ): 75 - 85 .

ZHAO Weida , CHEN Haiwen , GUO Luyang , et al . Substation meter readings and dial information identification method based on YOLO-E and enhanced OCRNet image segmentation [J ] . Electric Power Construction , 2023 , 44 ( 11 ): 75 - 85 .

黄悦华 , 陈照源 , 陈庆 , 等 . 基于边缘计算和改进YOLOv5s算法的输电线路故障实时检测方法 [J ] . 电力建设 , 2023 , 44 ( 1 ): 91 - 99 .

HUANG Yuehua , CHEN Zhaoyuan , CHEN Qing , et al . Real-time detection method for transmission line faults applying edge computing and improved YOLOv5s algorithm [J ] . Electric Power Construction , 2023 , 44 ( 1 ): 91 - 99 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰