Detection Algorithm for Insulators and Foreign Objects on Transmission Lines Based on Unmanned Aerial Vehicle Inspection

doi:10.12096/j.2096-4528.pgt.24230

Abstract

Abstract:

Objectives Traditional power grid inspection methods suffer from high labor intensity and low efficiency. Taking Shandong Golden Power Grid as the research object, this study proposes an inspection algorithm using unmanned aerial vehicle (UAV) based on lightweight deep learning network YOLOv5-Mv3 for detecting grid insulators and foreign objects. Methods Firstly, a dataset is constructed using images captured by UAVs during power grid inspection and is trained. Then, for the grid insulators and foreign objects, Mobilenetv3 is used to replace CSPDarknet53 as the feature extraction network in order to lighten the YOLOv5-Mv3 model, reducing parameters and computational cost while maintaining accuracy and enabling real-time detection. Results The proposed detection algorithm achieves a mean Average Precision of 84.7% and 56.6 frames per second. Compared to Faster RCNN, SSD, and YOLOv4 models, the improved YOLOv5-Mv3 demonstrates higher detection accuracy and faster performance. Conclusions The proposed algorithm improves the efficiency of UAV-based power grid inspection and achieves lightweight and high-efficiency effect, fully meeting the requirements for intelligent power grid inspection.

Key words: power system, artifical intelligence (AI), power grid, unmanned aerial vehicle, target detection, transmission line, power inspection, machine vision, image processing

CLC Number:

TM 216

Zihan YU, Heming WANG, Jiankai WANG, Shengqiang ZHU, Xiangzhong MENG. Detection Algorithm for Insulators and Foreign Objects on Transmission Lines Based on Unmanned Aerial Vehicle Inspection[J]. Power Generation Technology, 2025, 46(3): 532-540.

Figures/Tables 9

Fig. 1 Flowchart of power grid inspection using UAV

Fig. 2 Diagram of MobileNetv3 architecture

Tab. 1 Comparison of detection performance before and after improvement

网络模型	参数量/个	模型内存占用量/MB
CSPDarknet53	782 772	98.54
MobileNetv3	249 446	5.41

Fig. 3 Network architecture of YOLOv5-Mv3 algorithm

Fig. 4 Detection indicators of YOLOv5-Mv

Tab. 2 Comparison of transmission line detection performance before and after improvement

模型	平均精度/%			检测速度/FPS	均值平均精度/%
模型	绝缘子	缺陷绝缘子	鸟巢	检测速度/FPS	均值平均精度/%
YOLOv5s	80.5	82.9	84.8	25.5	82.7
YOLOv5m	82.4	83.4	84.5	15.5	83.4
YOLOv5l	83.3	85.4	86.9	8.4	85.2
YOLOv5-Mv3	83.9	84.8	85.4	56.6	84.7

Fig. 5 Comparative experimental curves of YOLOv5 series

Tab. 3 Comparison with other traditional algorithms

算法	绝缘子AP	缺陷绝缘子AP	鸟巢AP	mAP	F₁
Faster R-CNN	72.3	73.6	84.2	67.1	67.5
SSD	82.4	83.8	86.7	72.6	74.6
YOLOv4	81.5	79.9	80.8	82.7	79.1
YOLOv5	82.4	83.4	84.5	83.4	80.2
YOLOv5-Mv3	83.9	84.8	85.4	84.7	81.5

Fig. 6 Recognition effect of different algorithms

References 27

1	巢亚锋，万涛，张柳，等．湖南电网架空线路复合绝缘子掉线分析及建议[J]．高压电器，2021，57(8)：209-215．
	CHAO Y F， WAN T， ZHANG L，et al ．Analysis and suggestions on string breakage failure of composite insulator of overhead transmission line in Hunan power grid[J]．High Voltage Apparatus，2021，57(8)：209-215．
2	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)：7423-7446． doi:10.11834/jig.220432
	LIU C Y， WU Y Q ．Research progress of vision detection methods based on deep learning for transmission lines[J]．Proceedings of the CSEE，2023，43(19)：7423-7446． doi:10.11834/jig.220432
3	刘宏胜，李宏杰，张华君，等．混合ACA-SA算法的无人机巡检电塔路径优化方法[J]．自动化与仪器仪表，2024(1)：121-125．
	LIU H S， LI H J， ZHANG H J，et al ．A hybrid ACA-SA algorithm for UAV inspection path optimization [J]．Automation & Instrumentation，2024(1)：121-125．
4	刘春，艾克然木·艾克拜尔，蔡天池．面向建筑健康监测的无人机自主巡检与裂缝识别[J]．同济大学学报(自然科学版)，2022，50(7)：921-932．
	LIU C，EKRAM·E， CAI T C ．UAV autonomous inspection and crack detection towards building health monitoring[J]．Journal of Tongji University (Natural Science)，2022，50(7)：921-932．
5	隋宇，宁平凡，牛萍娟，等．面向架空输电线路的挂载无人机电力巡检技术研究综述[J]．电网技术，2021，45(9)：3636-3648．
	SUI Y， NING P F， NIU P J，et al ．Review on mounted UAV for transmission line inspection[J]．Power System Technology，2021，45(9)：3636-3648．
6	芦肇基，沈艳霞，谭永强．基于多结构融合WGAN的模糊绝缘子图像复原方法研究[J]．电力系统保护与控制，2024，52(22)：166-175．
	LU Z J， SHEN Y X， TAN Y Q ．A WGAN blur insulator image restoration method based on multi-structure fusion[J]．Power System Protection and Control，2024，52(22)：166-175．
7	霍红刚，周蠡，蔡杰，等．基于先验知识Faster R-CNN的输电线路无人机图像识别方法[J]．智慧电力，2024，52(6)：108-115．
	HUO H G， ZHOU L， CAI J，et al ．UAV image recognition method for transmission line based on prior knowledge faster R-CNN[J]．Smart Power，2024，52(6)：108-115．
8	任明，李乾宇，夏昌杰，等．基于稀疏光谱成像的线路复合绝缘子积污状态可视化评估[J]．中国电力，2025，58(2)：203-215．
	REN M， LI Q Y， XIA C J，et al ．Visualized estimation of composite insulator pollution status of transmission line based on reflective multispectral imaging[J]．Electric Power，2025，58(2)：203-215．
9	彭曙蓉，刘登港，何洁妮，等．基于改进YOLOv4的架空线路电力设备故障检测[J]．电力科学与技术学报，2023，38(5)：169-176．
	PENG S R， LIU D G， HE J N，et al ．Fault detection for overhead line power equipment based on improved YOLOv4[J]．Journal of Electric Power Science and Technology，2023，38(5)：169-176．
10	朱长荣，吕文超，单超，等．基于IMU-GNSS-VO的输电线无人机巡检定位和目标跟踪自适应方法[J]．电力建设，2023，44(8)：61-70．
	ZHU C R， LÜ W C， SHAN C，et al ．Adaptive method for transmission-line UAV inspection location and target tracking based on IMU-GNSS-VO[J]．Electric Power Construction，2023，44(8)：61-70．
11	杜觉晓，赵留学，莽修伟，等．基于边缘端目标识别与跟踪算法的输电线路航拍视频流诊断技术研究[J]．智慧电力，2023，51(6)：106-113．
	DU J X， ZHAO L X， MANG X W，et al ．Aerial video stream diagnosis technology for transmission lines based on edge target recognition and tracking algorithm[J]．Smart Power，2023，51(6)：106-113．
12	张焕龙，齐企业，张杰，等．基于改进YOLOv5的输电线路鸟巢检测方法研究[J]．电力系统保护与控制，2023，51(2)：151-159．
	ZHANG H L， QI Q Y， ZHANG J，et al ．Bird nest detection method for transmission lines based on improved YOLOv5[J]．Power System Protection and Control，2023，51(2)：151-159．
13	GIRSHICK R ．Fast R-CNN[C]//International Conference on Computer Vision．IEEE Computer Society，2015：1504.08083． doi:10.1109/iccv.2015.169
14	REN S， HE K， GIRSHICK R，et al ．Faster R-CNN：towards real-time object detection with region proposal networks[J]．IEEE Trans Pattern And Mach Intell，2017，39(6)：1137-1149． doi:10.1109/tpami.2016.2577031
15	LIU W， ANGUELOV D， ERHAN D，et al ．SSD：single shot MultiBox detector[C]//Computer Vision-ECCV2016．Cham：Springer International Publishing，2016：21-37． doi:10.1007/978-3-319-46448-0_2
16	REDMON J， DIVVALA S， GIRSHICK R，etal ．You only look once：unified，real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)．LasVegas，NV，USA：IEEE，2016：779-788． doi:10.1109/cvpr.2016.91
17	REDMON J， FARHADI A ．YOLO9000：better，faster，stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)．Honolulu，HI：IEEE，2017：7263-7271． doi:10.1109/cvpr.2017.690
18	FARHADI A， REDMON J ．Yolov3：an incremental improvement[C]//Computer Vision and Pattern Recognition.Berlin/Heidelberg，Germany：Springer，2018，1804：1-6．
19	WANG Z， GAO Q， LI D，et al ．Insulator anomaly detection method based on few-shot learning[J]．IEEE Access，2021，9：94970-94980． doi:10.1109/access.2021.3071305
20	XIA H， YANG B， LI Y，et al ．An improved CenterNet model for insulator defect detection using aerial imagery[J]．Sensors，2022，22(8)：2850． doi:10.3390/s22082850
21	HAN G， HE M， GAO M，et al ．Insulator breakage detection based on improved YOLOv5[J]．Sustainability，2022，14(10)：6066． doi:10.3390/su14106066
22	HUANG Y， JIANG L， HAN T，et al ．High-accuracy insulator defect detection for overhead transmission lines based on improved YOLOv5[J]．Applied Sciences，2022，12(24)：12682． doi:10.3390/app122412682
23	LIU L， KE C， LIN H ．Dark-center based insulator detection method in foggy environment[J]．Applied Sciences，2023，13(12)：7264． doi:10.3390/app13127264
24	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 N H， WANG S J， LIU J F，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．
25	程登峰，林世忠，尚文迪．输电线路固定翼无人机多目标巡检线路优化[J]．自动化仪表，2023，44(12)：21-25．
	CHENG D F， LIN S Z， SHANG W D ．Optimization of fixed-wingunmaunedaerialvehiclemulti-objectiveins- pectionroutesforpowertransmissionlines[J]．Process Au- tomation Instrumentation，2023，44(12)：21-25．
26	罗潇，於锋，彭勇．基于深度学习的无人机电网巡检缺陷检测研究[J]．电力系统保护与控制，2022，50(10)：132-139．
	LUO X， YU F， PENG Y ．UAV power grid inspection defect detection based on deep learning[J]．Power System Protection and Control，2022，50(10)：132-139．
27	邵瑰玮，刘壮，付晶，等．架空输电线路无人机巡检技术研究进展[J]．高电压技术，2020，46(1)：14-22．
	SHAO G W， LIU Z， FU J，et al ．Research progress in unmanned aerial vehicle inspection technology on overhead transmission lines[J]．High Voltage Engineering，2020，46(1)：14-22．

[1]	Jun ZHANG, Tianjiao PU, Wenzhong GAO, Youbo LIU, Wei PEI, Peidong XU, Tianlu GAO, Yuyang BAI. Key Technologies and Application Prospects of Intelligent Computing in Power Systems [J]. Power Generation Technology, 2025, 46(3): 421-437.
[2]	Zuhan ZHANG, Dunnan LIU, Hang FAN, Liuqing YANG, Yunjie DUAN, Yun LI, Zhenyu MA. Review of Power System Prediction Technologies Based on Large Language Models [J]. Power Generation Technology, 2025, 46(3): 438-453.
[3]	Yixuan CHEN, Jiayang WANG, Yingjun ZHUO, Siyu LU, Baorong ZHOU. Review of Artificial Intelligence Applications in Accelerating Operational Simulation of Power Systems [J]. Power Generation Technology, 2025, 46(3): 467-481.
[4]	Zhengyi YAN, Kang ZHAO, Kai WANG. Review of Application on Optimization Strategies for New-Type Power System Based on Reinforcement Learning [J]. Power Generation Technology, 2025, 46(3): 508-520.
[5]	Lei XI, Yixiao WANG, Yahui XIONG, Lu DONG. Location Detection of False Data Injection Attacks in Power Grid Based on Improved Deep Extreme Learning Machine [J]. Power Generation Technology, 2025, 46(3): 521-531.
[6]	Zhenglong SUN, Jiqiang SAN. Research on Doubly-Fed Wind Turbine Shaft System With Virtual Inertia for Torsional Vibration Analysis [J]. Power Generation Technology, 2025, 46(2): 314-325.
[7]	Yangfan ZHANG, Yilin LI, Lin YE, Xuejiao FU, Zhengyu WANG, Yaohan WANG. Short-Term Wind Power Prediction Method Considering Wind Turbine Operation Status Clustering Under Low-Temperature Conditions [J]. Power Generation Technology, 2025, 46(2): 326-335.
[8]	Yang ZHENG, Yucheng REN, Yuwei WANG, Dingji XU, Huimin YANG. Evaluation of Comprehensive Benefits of Electric Energy Substitution in Regional Power Grids Based on Improved Cloud Model [J]. Power Generation Technology, 2025, 46(2): 399-408.
[9]	Hang LI, Kunli GUO, Peng YANG, Jiajun LÜ, Beilei REN, Chenming QU, Tinghua ZHU, Yifan HAO. LCL Grid-Connected Inverters Control Strategy Based on Improved Fuzzy Linear Active Disturbance Rejection Control [J]. Power Generation Technology, 2025, 46(2): 409-420.
[10]	Guoqin LAN, Ye LU, Yansheng KAN, Jiguang ZHANG, Huanhuan WANG, Fang ZHONG, Chengcai WANG, Liming XIAO, Zhaoyang WANG. Research on the Development Trends and Countermeasures of Integrated Energy Services [J]. Power Generation Technology, 2025, 46(1): 19-30.
[11]	Wen LI, Fanpeng BU, Xiaotong ZHANG, Chuangdong YANG, Jing ZHANG. Optimal Operation Method of Electric-Hydrogen Hybrid Energy Storage Microgrid System Based on Typical Commercial Operation Mode [J]. Power Generation Technology, 2024, 45(6): 1186-1200.
[12]	Bai XIAO, Xuechun ZHAO, Guangde DONG. Summary and Prospect of Comprehensive Evaluation Methods of Power Quality [J]. Power Generation Technology, 2024, 45(4): 716-733.
[13]	Yu CHEN, Hong DING, Yong CUI, Li ZHU, Shijun CHEN, Qiuyang LING, Yongsheng XU, Jian ZHENG. Research on Temperature Situation Awareness and Auxiliary Decision-Making System Scheme of Substation Equipment [J]. Power Generation Technology, 2024, 45(4): 744-752.
[14]	Menghan JIA, Gang LIU, Shijie XU, Shuangying WU. Heterogeneous Image Fusion Algorithm and Its Application in Power Facility Detection Research [J]. Power Generation Technology, 2024, 45(3): 558-565.
[15]	Fangfang WANG, Pengwei YANG, Guangjin ZHAO, Qi LI, Xiaona LIU, Shuangchen MA. Development and Challenge of Flexible Operation Technology of Thermal Power Units Under New Power System [J]. Power Generation Technology, 2024, 45(2): 189-198.