基于改进YOLOX的输电线路典型部件及缺陷轻量检测方法

王凌云; 万旭东; 刘兰兰; 黄力

doi:10.15938/j.emc.2025.09.010

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于改进YOLOX的输电线路典型部件及缺陷轻量检测方法

更新时间：2026-09-29

- 基于改进YOLOX的输电线路典型部件及缺陷轻量检测方法
- Light weight detection method for typical components and defects of transmission lines based on improved YOLOX
- 电机与控制学报 2025年29卷第9期页码：106-115
- 作者机构：
  
  三峡大学电气与新能源学院，湖北宜昌 443002
  三峡大学湖北省输电线路工程技术研究中心，湖北宜昌 443002
  带电巡检与智能作业技术国网公司实验室，湖南长沙 421000
- 作者简介：
  
  作者简介：王凌云（1981—），男，博士，教授，博士生导师，研究方向为输电线路智能检测；
  通信作者：万旭东
  刘兰兰（1987—），女，博士，高级工程师，研究方向为智能输电运检；
  黄力（1980—），男，博士，副教授，研究方向为输电线路智能检测。
- 基金信息：
  
  国家自然科学基金(51907104);湖北省输电线路工程技术研究中心开放课题(2019KXL05)
- DOI：10.15938/j.emc.2025.09.010
  中图分类号： TM75;TP391
- 收稿：2025-04-26，
  
  纸质出版：2025-09
- 稿件说明：
移动端阅览
王凌云, 万旭东, 刘兰兰, 等. 基于改进YOLOX的输电线路典型部件及缺陷轻量检测方法[J]. 电机与控制学报, 2025,29(9):106-115.

WANG Lingyun, WAN Xudong, LIU Lanlan, et al. Light weight detection method for typical components and defects of transmission lines based on improved YOLOX[J]. Electric Machines and Control, 2025, 29(9): 106-115.
王凌云, 万旭东, 刘兰兰, 等. 基于改进YOLOX的输电线路典型部件及缺陷轻量检测方法[J]. 电机与控制学报, 2025,29(9):106-115. DOI： 10.15938/j.emc.2025.09.010.

WANG Lingyun, WAN Xudong, LIU Lanlan, et al. Light weight detection method for typical components and defects of transmission lines based on improved YOLOX[J]. Electric Machines and Control, 2025, 29(9): 106-115. DOI： 10.15938/j.emc.2025.09.010.

摘要

针对输电线路部件及缺陷检测中模型体积大、实时性差的问题，以及因背景复杂、样本不平衡导致易误检、漏检的问题，提出一种基于改进YOLOX的输电线路典型部件及缺陷轻量检测方法。首先引入Ghostnet替换原有主干网络，实现模型轻量化。其次为解决输电线路图像背景复杂导致易漏检、误检的问题，将坐标注意力模块嵌入特征融合网络和CSPLayer结构，加强对复杂背景中目标区域的关注。最后针对输电线路部件及缺陷样本不平衡以及不同目标检测难度差异大的问题，引入变焦损失函数，降低正负样本不平衡带来的影响，提升对难分类目标的训练强度以减少误检和漏检。实验结果表明，所提方法在输电线路部件及缺陷检测中的平均精度均值提高2.67%，模型尺寸减少33.01%，推理速度为19.61 ms/张，能够满足无人机轻量化、高精度的电力实时巡检要求。

Abstract

Aiming at the problems of large model size and poor real-time performance in the detection of transmission line components and defects

as well as the problems of frequent false detection and missed detection due to complex background and imbalanced samples

a light weight detection method for typical transmission line components and defects based on improved YOLOX was proposed. Firstly

Ghostnet was introduced to replace the original backbone network to achieve model lightweighting. Secondly

in order to solve the problem of frequent missed detection and false detection caused by the complex background of the transmission line image

the coordinate attention module was embedded into both of the feature fusion network and CSPLayer structure to enhance the focus on the target area in complex background. Finally

to address the problems of the imbalance samples of transmission line components and defects and the great differences in detection difficulty of different targets

the Varifocal loss function was introduced to reduce the impact caused by the imbalance of positive and negative samples

and improve the training intensity of difficult-to-classify targets to reduce false detection and missed detection. The experimental result shows that the average accuracy of the proposed method in the detection of transmission line components and defects is increased by 2. 67%

the model size is reduced by 33. 01%

and the reasoning speed is 19.61 ms/piece

which can satisfy the requirements of UAV lightweight and high-precision power real-time inspection.

关键词

Keywords

references

NGUYEN V N, 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 & Energy Systems, 2018, 99: 107.

刘志颖,缪希仁,陈静,等.电力架空线路巡检可见光图像智能处理研究综述[J].电网技术, 2020, 44(3): 1057.

LIU Zhiying, MIAO Xiren, CHEN Jing, et al. Review of visible image intelligent processing for transmission line inspection[J]. Power System Technology, 2020, 44(3): 1057.

姜云土,韩军,丁建,等.基于多特征融合的玻璃绝缘子识别及自爆缺陷的诊断[J].中国电力, 2017, 50(5): 52.

JIANG Yuntu, HAN Jun, DING Jian, et al. The identification and diagnosis of self-blast defects of glass insulators based on multi-feature fusion[J]. Electric Power, 2017, 50(5): 52.

宋伟,左丹,邓邦飞,等.高压输电线防震锤锈蚀缺陷检测[J].仪器仪表学报, 2016, 37(S1): 113.

SONG Wei, ZUO Dan, DENG Bangfei, et al. Corrosion defect detection of earthquake hammer for high voltage transmission line[J]. Chinese Journal of Scientific Instrument, 2016, 37(S1): 113.

赵振兵,蒋志钢,李延旭,等.输电线路部件视觉缺陷检测综述[J].中国图象图形学报, 2021, 26(11): 2545.

ZHAO Zhenbing, JIANG Zhigang, LI Yanxu, et al. Overview of visual defect detection of transmission line components[J]. Journal of Image and Graphics, 2021, 26(11): 2545.

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.

JIANG Xiangju, WANG Ruitong, MA Yanhong. Insulator defect detection based on lightweight improved RT-DETR edge deployment algorithm[J]. Transactions of China Electrotechnical Society, 2025, 40(3): 842.

陈永,安卓奥博,周建宇.基于扩散模型检测的高铁接触网绝缘子缺陷语义描述方法[J].电工技术学报, 2025, 40 (13): 4100.

CHEN Yong, AN Zhuoaobo, ZHOU Jianyu. Semantic description method of high-speed railway contact net insulator defects based on diffusion model detection[J]. Transactions of China Electrotechnical Society, 2025, 40(13): 4100.

郑含博,胡钧浩,李金恒,等.基于改进实例分割与深度神经网络温度拟合的电力设备热故障诊断研究[J].电机与控制学报, 2025, 29(2): 116.

ZHENG Hanbo, HU Junhao, LI Jinheng, et al. Thermal fault diagnosis of power equipment through improved instance segmentation and deep neural network temperature fitting[J]. Electric Machines and Control, 2025, 29(2): 116.

GIRSHICK R, DONAHUE J, DARRELL T. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 23-28,2014, Columbus, Ohio, USA. 2014: 580-587.

GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV), December 7 -13, 2015, Santiago, Chile. 2015: 1440-1448.

REN Shaoqing, HE Kaiming, GIRSHICK R. 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.

CAI Z W, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 18-22, 2018, Salt Lake City, Utah, USA. 2018: 6154-6162.

侯春萍,章衡光,张巍,等.输电线路绝缘子自爆缺陷识别方法[J].电力系统及其自动化学报, 2019, 31(6): 1.

HOU Chunping, ZHANG Hengguang, ZHANG Wei, et al. Recognition method for faults of insulators on transmission lines[J]. Proceedings of the CSU-EPSA, 2019, 31(6): 1.

赵振兵,熊静,李冰,等.基于改进Cascade R-CNN的典型金具及其部分缺陷检测方法[J].高电压技术, 2022, 48 (3): 1060.

ZHAO Zhenbing, XIONG Jing, LI Bing, et al. Typical fittings and its partial defect detection method based on improved cascade R-CNN[J]. High Voltage Engineering, 2022, 48(3): 1060.

LIU Wei, ANGUELOV D, ERHAN D. SSD: Single shot multibox detector[C]//14th European Conference on Computer Vision (ECCV), October 8 - 16, 2016, Amsterdam, Netherlands.2016: 21-37.

REDMON J, DIVVALA S, GIRSHICK R. You only look once:Unified, real-time object detection[C]//2016 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30,2016, Las Vegas, Nevada, USA. 2016:779-788.

REDMON J, FARHADI A. YOLOv3: An incremental improvement[EB/OL]. (2018 -09 -30). https://arxiv. org/abs/1804.02767.

GE Z, LIU S, WANG F, et al. YOLOX: Exceeding yolo series in 2021[EB/OL]. (2021 -7 -18). https://arxiv. org/abs/2107. 08430.

石鑫,化晨冰,张凯,等.基于SSD深度神经网络的航拍图像电力目标检测[J].数据采集与处理, 2022, 37(1): 207.

SHI Xin, HUA Chenbing, ZHANG Kai, et al. Power target detection in aerial images based on SSD deep neural network[J]. Journal of Data Acquisition and Processing,2022,37(1):207.

杨剑锋,秦钟,庞小龙,等.基于深度学习网络的输电线路异物入侵监测和识别方法[J].电力系统保护与控制, 2021, 49(4): 37.

YANG Jianfeng, QIN Zhong, PANG Xiaolong, et al. Foreign body intrusion monitoring and recognition method based on denseYOLOv3 deep learning network[J]. Power System Protection and Control, 2021, 49(4): 37.

郝帅,马瑞泽,赵新生,等.基于卷积块注意模型的YOLOv3输电线路故障检测方法[J].电网技术,2021,45(8):2979.

HAO Shuai, MA Ruize, ZHAO Xinsheng, et al. Fault detection of YOLOv3 transmission line based on convolutional block attention model[J]. Power System Technology,2021,45(8):2979.

ZHANG H, CISSE M, DAUPHIN Y N, et al. mixup: Beyond empirical risk minimization[EB/OL]. (2017 -10 -25) https://arxiv. org/abs/1710. 09412

BOCHKOVSKIY A, WANG C Y, LIAO H Y M. Yolov4: Optimal speed and accuracy of object detection[J]. arXiv preprint arXiv:2004.10934, 2020.

LIN T Y, Dollár P, GIRSHICK R. Feature pyramid networks for object detection[C]//2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), July 21 -26, 2017, Honolulu, Hawaii, USA. 2017: 2117-2125.

LIU S, QI L, QIN H, et al. Path aggregation network for instance segmentation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 18 -22, 2018, Salt Lake City, Utah, USA. 2018: 8759-8768.

HAN K, WANG Y, TIAN Q. Ghostnet: more features from cheap operations[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 14 -19, 2020, Seattle, Washington, USA. 2020: 1580-1589.

HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//2018IEEE/CVFconference on computer vision and pattern rec ognition (CVPR), June 18 -22, 2018, Salt Lake City, Utah, USA. 2018: 7132-7141.

HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design[C ]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition ( CVPR), June 19 -25, 2021, Nashville, Tennessee, USA. 2021: 13713-13722.

ZHANG H, WANG Y, DAYOUB F. Varifocalnet: An iou-aware dense object detector[C ]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition ( CVPR), June 19 -25, 2021, Nashville, Tennessee, USA. 2021: 8514-8523.

BAO T, JIAO H, GAO S, et al. Back propagation optimization of convolutional neural network based on the left and the right hands Identification[C]// 2021 IEEE International Conference on Computer Science, Artificial Intelligence and Electronic Engineering (CSAIEE), March 26 -28, 2021, Kunming, China. 2021: 182-186.

LIN T Y, GOYAL P, GIRSHICK R. Focal loss for dense object detection[C]// Proceedings of the IEEE international conference on computer vision (ECCV), October 22 -29, 2017, Venice, Italy. 2017: 2980-2988.

OQUAB M, BOTTOU L, LAPTEV I, et al. Learning and transferring mid-level image representations using convolutional neural networks[C]//2014 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 23-28, 2014, Columbus, Ohio, USA. 2014: 1717-1724.

李东东,赵阳,赵耀.一种变工况下风电机组行星齿轮箱的故障诊断方法[J].电机与控制学报, 2023, 27(1): 33.

LI Dongdong, ZHAO Yang, ZHAO Yao. Fault diagnosis method for wind turbine planetary gearbox under variable working conditions[J]. Electric Machines and Control, 2023, 27(1): 33.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

考虑气隙放电、电磁传播和天线响应的局部放电联合仿真模型

无轴承电机霍尔不对称影响剖析与参数整定方法

多模态数据驱动的软测量建模与综合能源系统调度策略研究

一种改进的三相电流源型整流器非对称调制策略

高频噪声抑制与扰动前馈解耦协同的eVTOL电驱自抗扰控制方法