Insulator Defect Detection Based on Complex Environment

doi:10.3969/j.issn.1006-2475.2025.09.010

Abstract

Abstract:
Abstract: Nowadays， drones have been widely used in power inspection. However， due to the complex background of insulator defect images， small defect sizes， and the occurrence of multiple damage situations such as flashover， self explosion， and breakage， the detection speed and accuracy are greatly limited. To address these issues， a complex environment insulator defect detection method based on improved YOLOv5 is proposed. Firstly， an improved feature extraction network C2FNet is adopted to obtain richer feature information while ensuring lightweight. Secondly， the Res2Net module with multi-scale information is adopted to improve gradient propagation and training performance. Finally， a dynamic object detection head 3-DyHead with adaptive fusion is designed to dynamically adjust the network structure and parameters. The experimental results show that the average accuracy of this method has reached 94.2%， which is 4.1 percentage points higher than the original model. The precision P and recall R have increased by 3.2 percentage points and 4.0 percentage points， respectively. The average accuracy of insulator flashover， hammer， and defect has increased by 11.0 percentage points， 2.0 percentage points and 6.5 percentage points.

Key words: Key words: insulator testing, C2FNet, Res2Net, adaptive fusion, 3-DyHead

CLC Number:

JI Xingyu1, HUANG Chenrong2, YAO Juncai2, WANG Kai1, GU Mingjie1. Insulator Defect Detection Based on Complex Environment[J]. Computer and Modernization, 2025, 0(09): 67-72.

References

［1］ JENSSEN R， ROVERSO D. Automatic autonomous vision-based power line inspection: A review of current status and the potential role of deep learning［J］. International Journal of Electrical Power and Energy Systems， 2018，99（2）:107-120.
［2］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.
［3］ SONG Y H， ZHOU Z Z， LI Q， et al. Intrusion detection of foreign objects in high-voltage lines based on YOLOv4［C］// 2021 IEEE 6th International Conference of Intelligent Computing and Signal Process. IEEE， 2021:1295-1300.
［4］ HE K M， ZHANG X Y， REN S Q， et al. Deep residual learning for image recognition［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2016:770-778.
［5］ WANG C Y， BOCHKOVSKIY A， LIAO H Y. Scaled-YOLOv4: Scaling cross stage partial network［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2021:13029-13038.
［6］汝承印，张仕海，张子淼，等. 基于轻量级MobileNet-SSD和MobileNetV2-DeeplabV3+的绝缘子故障识别方法［J］. 高电压技术， 2022，48（9）:3670-3679.
［7］王卓，王玉静，王庆岩，等. 基于协同深度学习的二阶段绝缘子故障检测方法［J］. 电工技术学报， 2021，36（17）:3594-3604.
［8］ HAN G， ZHAO L， LI Q， et al. A lightweight algorithm for insulator target detection and defect identification［J］. Sensors， 2023，23（3）:1216-1231.
［9］ YU J， LIU K， HE M， et al. Insulator defect detection: A detection method of target search and cascade recognition［J］. Energy Reports， 2021，7（7）:206-217.
［10］ JIA W， XU S Q， LIANG Z， et al. Real-time automatic helmet detection of motorcyclists in urban traffic using improved YOLOv5 detector［J］. IET Image Processing， 2021，15（14）:3623-3637.
［11］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.
［12］ WANG S X， ZHU J D， Ll Z T， et al. Coal gangue target detection based on improved YOLOv5s［J］. Applied sciences， 2023，13（20）:112-120.
［13］朱晓彤，张荣芬，刘宇红，等. Dim-YOLOv5n昏暗场景目标检测算法［J］. 计算机工程与应用， 2024，60（11）:173-181.
［14］裴少通，张善驰. 基于改进YOLOv5s的架空输电线路鸟类入侵检测方法［J］. 智慧电力， 2023，51（6）:100-105.
［15］ TIAN Z， SHEN C H， CHEN H， et al. Fcos: Fully convolutional one-stage object detection［C］// Proceedings of the IEEE/CVF International Conference on Computer Vision. IEEE， 2019:627-636.
［16］ QIU Z B， ZHU X， LIAO C B， et al. Detection of transmission line insulator defects based on an improved lightweight YOLOv4 model［J］. Applied Sciences， 2022，12（3）:1207-1211.
［17］ SUN Y， SONG J， LI Y， et al. lVP-YOLOv5: An intelligent vehicle-pedestrian detection method based on YOLOv5s［J］. Connection Science， 2023，35（1）:2121-2131.
［18］ TAO C Y， ZHANG J， WANG P. Smoke detection based on deep convolutional neural networks［C］// 2016 International Conference on Industrial Informatics Computing Technology. IEEE， 2016:150-153.
［19］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.
［20］ MADUAKO I， IGWE C， ABAH J， et al. Deep learning for component fault detection in electricity transmission lines［J］. Journal of Big Data， 2022，9（1）:1-34.
［21］ HUANG Z R， HU S L， ZHANG L. Fault detection of insulator in distribution network based on YOLOv5s neural network［C］// 2022 International Conference on Artificial Intelligence and Computer Information Technology（AlCIT）. IEEE， 2022: 1-5.
［22］ LIU C Y， WU Y Q， LlU J J， et al. Improved YOLOv3 network for insulator detection in aerial images with diverse background interference［J］. Electronics， 2021，10（7）:771-786.
［23］吴明杰，云利军，陈载清，等. 改进YOLOv5s的无人机视角下小目标检测算法［J］. 计算机工程与应用， 2024，60（2）:191-199.
［24］刘敏，周国亮，王红旭，等. 基于稀疏重构注意力机制的绝缘子缺陷检测方法［J］. 广东电力， 2024，37（5）:104-111.
［25］伍箴燎，吴正平，孙水发. 基于改进YOLOv5算法的绝缘子多缺陷检测［J］. 高压电器， 2022，11（2）:1-11.
［26］王年涛，王淑青，黄剑锋，等. 基于改进YOLOv5神经网络的绝缘子缺陷检测方法［J］. 激光杂志， 2022，43（8）:60-65.
［27］孙新娟，杨天宇. 融合注意力机制的改进型YOLOv5绝缘子缺陷故障检测方法［J］. 科学技术与工程， 2024，24（17）:7221-7230.

[1]	WANG Yingying, HAO Xiao. Fine-grained Image Classification Based on Res2Net and Recursive Gated Convolution [J]. Computer and Modernization, 2024, 0(10): 74-79.
[2]	XIA Qian-han, HE Sheng-huang, WU Yuan-qing, ZHAO Le-le. Few-shot Object Detection via Learnable Memory Feature Pyramid Network [J]. Computer and Modernization, 2023, 0(12): 7-13.