
浏览全部资源
扫码关注微信
1.三峡大学电气与新能源学院,湖北省宜昌市443002
2.湖北省输电线路工程技术研究中心(三峡大学),湖北省宜昌市443002
3.中国电力科学研究院有限公司电网环境保护国家重点实验室,湖北省武汉市430072
收稿日期:2024-07-29,
修回日期:2024-10-11,
录用日期:2024-10-15,
移动端阅览
吴田, 王铭心, 唐盼, 等. 基于改进YOLOv8的带电作业绝缘毯表面缺陷识别[J/OL]. 默认刊物名称, 2025.
WU Tian, WANG Mingxin, TANG Pan, et al. Live Working Insulation Blanket Surface Defect Recognition Based on Improved YOLOv8[J/OL]. Moren journal, 2025.
绝缘毯表面缺陷对其绝缘性能和使用寿命有严重影响,针对现有检测方法面对不规则缺陷以及绝缘毯表面纹理干扰造成的检测效率和准确率低的问题,本文提出一种基于改进YOLOv8的绝缘毯缺陷检测算法,引入SPD-Conv卷积神经网络,解决小目标检测特征遗漏问题;引入Deformable-LKA注意力机制自适应调整卷积核大小和形状,增强特征提取能力;针对缺陷形状不规则的问题,改进YOLOv8中的损失函数为Shape-IoU,减少标注框的影响;同时开展模拟缺陷绝缘毯的沿面放电试验,获取不同缺陷对绝缘性能的影响。实验结果表明:绝缘毯表面不同类型缺陷对沿面放电特性影响差异明显,改进模型在扩充数据集上的识别率为94.8%,相比原模型在检测速度和精度上都有一定的提升,为带电作业绝缘毯表面缺陷检测提供参考。
Surface defects of insulating blankets can severely impact their insulating performance and service life. To address the low detection efficiency and accuracy caused by irregular defects and interference from the surface texture of insulating blankets
this paper proposes an improved YOLOv8 algorithm for detecting defects in insulating blankets. The algorithm introduces an SPD-Conv convolutional neural network to address the issue of feature omission in small target detection. It incorporates the Deformable-LKA attention mechanism to adaptively adjust the size and shape of the convolutional kernel
enhancing the capability to extract features. To tackle the issue of irregular defect shapes
the loss function in YOLOv8 is improved to Shape-IoU
reducing the impact of annotation boxes. Additionally
a surface discharge test is conducted on simulated defective insulating blankets to quantify the impact of different defects on insulating performance. Experimental results indicate that different types of surface defects on insulating blankets significantly affect surface discharge characteristics. The improved model achieves a recognition rate of 94.8% on the expanded dataset
showing certain improvements in detection speed and accuracy compared to the original model
providing a reference for the detection of surface defects on insulating blankets used in live working.
胡毅 , 刘凯 , 彭勇 , 等 . 带电作业关键技术研究进展与趋势 [J ] . 高电压技术 , 2014 , 40 ( 07 ): 1921 - 1931 .
HU Yi , LIU Kai , PENG Yong , et al . Research Status and Development Trend of Live Working Key Technology [J ] . High Voltage Engineering , 2014 , 40 ( 07 ): 1921 - 1931 .
冯振波 , 郑孝干 , 陈炜 , 等 . 220kV开关触头转臂绝缘遮蔽罩试验研究 [J ] . 高压电器 , 2023 , 59 ( 01 ): 25 - 29 .
FENG Zhenbo , ZHENG Xiaogan , CHEN Wei , et al . Study on Testing of Insulation Shield of 220 kV Switch Contact Arm [J ] . High Voltage Apparatus , 2023 , 59 ( 01 ): 25 - 29 .
黎鹏 , 刘畅 , 李慧慧 , 等 . 高温对配电线路带电作业用绝缘毯沿面闪络特性的影响 [J ] . 电网技术 , 2021 , 45 ( 12 ): 4971 - 4978 .
LI Peng , LIU Chang , LI Huihui , et al . Influence of High Temperature on Surface Flashover Characteristics of Insulating Blankets Used in Live Working of Distribution Lines [J ] . Power System Technology , 2021 , 45 ( 12 ): 4971 - 4978 .
吴田 , 曹探深 , 劳国威 , 等 . 基于硬质疏水性涂层的配网遮蔽用具的沿面放电特性研究 [J ] . 高压电器 , 2021 , 57 ( 04 ): 21 - 27 .
WUTian , CAO Tanshen , LAO Guowei , et al . Study on Surface Discharge Characteristic for Distribution Network Cover Appliance Based on Toughing Hydrophobic Coating [J ] . High Voltage Apparatus , 2021 , 57 ( 04 ): 21 - 27 .
贾子建 , 吴田 , 高广德 , 等 . 基于图像识别的绝缘材料憎水表面凝露形貌表征及其对放电发展影响研究 [J ] . 国外电子测量技术 , 2024 , 43 ( 02 ): 26 - 33 .
JIA Zijian , WU Tian , GAO Guangde , et al . Research on the characterization of hydrophobic surface condensation morphology of insulating materials and its influence on discharge development based on image recognition [J ] . Foreign Electronic Measurement Technology , 2024 , 43 ( 02 ): 26 - 33 .
易辉 . 标准DL/T976—2005《带电作业工具、装置和设备预防性试验规程》编写说明 [J ] . 电力标准化与技术经济 , 2006 ( 03 ): 1 - 5 .
刘东庭 , 鲁林军 , 刘聪汉 , 等 . 配电带电作业绝缘遮蔽工具的设计和应用 [J ] . 电网与清洁能源 , 2020 , 36 ( 01 ): 36 - 40+45 .
LIU Dongting , LU Linjun , LIU Conghan , et al . Design and Application of Insulation Shielding Tools for Live Distribution Operation [J ] . Power System and Clean Energy , 2020 , 36 ( 01 ): 36 - 40+45 .
王伟 , 刘宏 , 董理科 , 等 . 基于激光超声峰值重建算法的盆式绝缘子缺陷检测研究 [J ] . 绝缘材料 , 2023 , 56 ( 01 ): 96 - 101 .
WANG Wei , LIU Hong , DONG Like , et al . Research on basin insulator defect detection based on laser ultrasonic peak reconstruction algorithm [J ] . Insulating Material , 2023 , 56 ( 01 ): 96 - 101 .
刘传洋 , 吴一全 , 刘景景 . 无人机航拍图像中绝缘子缺陷检测的深度学习方法研究进展 [J/OL ] . 电工技术学报 , 1 - 21 [ 2024-10-11 ] .
Liu Chuanyang , Wu Yiquan , Liu Jingjing . Research Progress of Deep Learning Methods for Insulator Defect Detection in UAV based Aerial Images [J ] . Transactions of China Electrotechnical Society , 1 - 21 [ 2024-10-11 ] .
LOHALA S , ALSADOON A , PRASAD P W C , et al . A novel deep learning neural network for fast⁃food image classification and prediction using modified loss function [J ] . Multimedia Tools and Applications , 2021 , 80 ( 17 ): 25453 ⁃ 25476 .
FENG X , JIANG W . Research on human fall detection based on Tiny⁃yolov3 algorithm [C ] // EITCE’21:Proceed⁃ ings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering . USA : ACM Publishing , 2021 : 1326 ⁃ 1330
吴田 , 杨威 , 陶雄俊 , 等 . 基于轻量级密集残差网络的输电线路绝缘子红外图像的超分辨率重建 [J/OL ] . 高压电器 , 1 - 12 [ 2024-10-11 ] .
WU Tian , YANG Wei , TAO Xiongjun , et al . Super-resolution Reconstruction of Infrared Image of Transmission Line Insulator Based on Lightweight Residual in Residual Dense Net [J ] . High Voltage Apparatus , 1 - 12 [ 2024-10-11 ] .
吴田 , 罗成军 , 王申华 , 等 . 基于改进局部阈值分割的绝缘毯表面微缺陷的无损智能评估方法 [J ] . 高压电器 , 2022 , 58 ( 11 ): 75 - 81 .
WU Tian , LUO Chengjun , WANG Shenhua , et al . Nondestructive Intelligent Assessment Method on Surface Micro⁃defects of Insulating Blanket Based on Modified Local Threshold Segmentation [J ] . High Voltage Apparatus , 2022 , 58 ( 11 ): 75 - 81 .
涂俊博 , 曾佳林 , 唐越新 , 等 . 基于深度学习的太阳能电池片表面缺陷检测及分类 [J/OL ] . 激光与光电子学进展 , 1 - 13 [ 2024-06-24 ] .
TU Junbo , ZENG Jialin , TANG Yuexin , et al . Detection and classification of surface defects of solar cells based on deep learning [J ] . Laser & Optoelectronics Progress , 1 - 13 [ 2024-06-24 ] .
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 ( 05 ): 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 ( 05 ): 1933 - 1942 .
Tong Liang , Fan Changlong , Peng Zhongbo , et al . WTBD-YOLOv8:An Improved Method for Wind Turbine Generator Defect Detection [J ] . Sustainability , 2024 , 16 ( 11 ): 44 - 67 .
韩睿 , 戴哲仁 , 蒋鹏 , 等 . 基于改进YOLOv8的电力场景通用缺陷检测模型 [J ] . 浙江电力 , 2024 , 43 ( 04 ): 113 - 120 .
HAN Rui , DAI Zheren , JIANG Peng , et al . A general defect detection model for power scenarios using the improved YOLOv8 [J ] . Zhejiang Electric Powe , 2024 , 43 ( 04 ): 113 - 120 .
朱泓宇 , 程换新 , 骆晓玲 . 改进YOLOv8网络在绝缘子缺陷检测中的应用 [J ] . 水电能源科学 , 2024 , 42 ( 05 ): 183 - 187 .
ZHU Hongyu , CHENG Huanxin , LUO Xiaoling . Application of Improved YOLOv8 Network in Insulator Defect Detection [J ] . Water Resource sand Power , 2024 , 42 ( 05 ): 183 - 187 .
REDMON J , DIVVALA S , GIRSHICK R , et al . You only look once:unified,realtime object detection [C ] // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . USA : IEEE , 2016 : 779 ⁃ 788 .
吴田 , 万亚旭 , 王申华 , 等 . 基于改进ST-GCN的10kV带电作业人员视频异常行为识别方法 [J/OL ] . 南方电网技术 , 1 - 9 [ 2024-06-20 ] .
WU Tian , WAN Yaxu , WANG Shenhua , et al . Video Abnormal Behavior Recognition Method for 10kV Live Workers Based on Improved ST-GCN [J ] . SOUTHERN POWER SYSTEM TECHNOLOGY , 1 - 9 [ 2024-06-20 ] .
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 ( 03 ): 223 - 228 .
TANGLu , WANGShuqing , WANG Niantao , et al . Insulator Defect Detection in Foggy Condition Based on Improved YOLOX Network [J ] . High Voltage Apparatus , 2024 , 60 ( 03 ): 223 - 228 .
DONG Jiaxiu , LI Zhaonan , WANG Zibin , et al . Pixel⁃level intelligent segmentation and measurement method for pavement multiple damages based on mobile deep learning [J ] . IEEE Access , 2021 ( 9 ): 143860 ⁃ 143876 .
高黎明 . 基于轻量化目标检测的绝缘子缺陷识别 [J ] . 高压电器 , 2023 , 59 ( 12 ): 237 - 244 .
GAO Liming . Insulator Defect Identification Based on Lightweight Object Detection [J ] . High Voltage Apparatus , 2023 , 59 ( 12 ): 237 - 244 .
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 .
José B S , Frizzo S S , Gurmail S , et al . Hybrid-YOLO for classification of insulators defects in transmission lines based on UAV [J ] . International Journal of Electrical Power and Energy Systems , 2023 , 148 .
龚冰 , 唐盼 , 沈辉 , 等 . 带电作业用绝缘遮蔽用具组合沿面放电试验研究 [J ] . 水电能源科学 , 2018 , 36 ( 12 ): 179 - 181+186 .
GONG Bing , TANG Pan , SHEN Hui , et al . Study on Surface Discharge Test of Combination of Insulating Shielding Cover for Live Working [J ] . Water Resources and Power , 2018 , 36 ( 12 ): 179 - 181+186 .
Sunkara , Raja , Tie Luo . No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objects [J ] . arXiv , 2022 .
Azad Reza , Leon Niggemeier , Michael Huttemann , et al . Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation [J ] . arXiv , 2023 .
ZHANG Hao , ZHANG Shuaijie . Shape-IoU:More Accurate Metric considering Bounding Box Shape and Scale [J ] . arXiv , 2023 .
张玮亚 , 陈中 , 宫衍平 , 等 . 不同工况下带电作业绝缘毯局部放电及击穿特性 [J ] . 电力系统及其自动化学报 , 2022 , 34 ( 09 ): 57 - 63 .
ZHANG Weiya , CHEN Zhong , GONG Yanping , et al . Partial Discharge and Breakdown Characteristics of Insulating Blankets in Live Working under Different Operation Conditions [J ] . Proceedings of the CSU-EPSA , 2022 , 34 ( 09 ): 57 - 63 .
0
浏览量
1
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
陕公网安备 61010402000197