|
|
|
| Application progress of deep learning in power equipment defect identification |
| ZANG Guoqiang1,2, LIU Xiaoli3, XU Yingfei1,2, CHEN Yulu4, LI Wenbo1 |
1. Hefei Institute of Physical Science, Chinese Academy of Sciences, Hefei 230031;
2. University of Science and Technology of China, Hefei 230026;
3. State Grid Genhe Power Supply Company, Genhe, Inner Mongolia 022350;
4. Institute of Physical Science and Information Technology, Anhui University, Hefei 230601 |
|
|
|
|
Abstract Deep learning can be used to identify defects in power equipment images intelligently, efficiently and accurately in power equipment defect recognition. In this paper, the substance and the background of defect recognition is described at first. Then several dominant deep learning models of defect recognition are sketched and the improvement and optimization of these models are introduced. The applications of the models in current market are summarized, and the challenges and difficulties faced in these applications are analyzed. Finally, the future trend of deep learning in power equipment defect recognition is discussed in terms of automatic machine learning, sample database construction and power knowledge mapping.
|
|
Received: 22 November 2021
|
|
|
|
| Cite this article: |
|
ZANG Guoqiang,LIU Xiaoli,XU Yingfei等. Application progress of deep learning in power equipment defect identification[J]. Electrical Engineering, 2022, 23(6): 1-7.
|
|
|
|
| URL: |
|
http://dqjs.cesmedia.cn/EN/Y2022/V23/I6/1
|
[1] 李宗. 电力系统及电力设备的可靠性[J]. 甘肃科技纵横, 2018, 47(10): 49-51, 86.
[2] 房婷. 电力系统变电运行设备的主要问题和解决方法分析[J]. 中文科技期刊数据库 (引文版) 工程技术, 2016(11): 00291.
[3] 杨明波, 杨露. 浅谈如何加强电力设备缺陷管理[J].通讯世界, 2017(21): 247-248.
[4] 黄旭骏, 蒋卫东, 邢哲鸣. 输电线路设备缺陷管理现状及对策分析[J]. 中国高新技术企业, 2015(34): 70-71.
[5] 赵寿生, 董升. 基于提升变电设备缺陷管理创新机制的实施与思考[J]. 企业管理, 2016(增刊1): 138-139.
[6] 苏超, 彭泽荣, 黄志文. 基于图像处理的绝缘子缺陷检测[J]. 工业控制计算机, 2016, 29(12): 18-20.
[7] 张云飞. 单人背包式全景技术在输电线路巡视中的应用[J]. 电气技术, 2018, 19(4): 92-95.
[8] 王子昊. 深度学习在输电铁塔关键部件缺陷检测中的应用研究[D]. 天津: 中国民航大学, 2018.
[9] 周宸, 高伟, 郭谋发. 基于YOLOv4模型的玻璃绝缘子自爆缺陷识别方法[J]. 电气技术, 2021, 22(5): 38-42, 49.
[10] 李宁, 郑仟, 谢贵文, 等. 基于无人机图像识别技术的输电线路缺陷检测[J]. 电子设计工程, 2019, 27(10): 102-106, 112.
[11] 刘建友, 李宝树, 仝卫国. 航拍绝缘子图像的提取和识别[J]. 传感器世界, 2009, 15(12): 22-24.
[12] 马帅营, 安居白, 陈舫明. 基于HSI颜色空间的绝缘子图像的分割[J]. 大连民族学院学报, 2010, 12(5): 481-484.
[13] 张浩, 王玮, 徐丽杰, 等. 图像识别技术在电力设备监测中的应用[J]. 电力系统保护与控制, 2010, 38(6): 88-91.
[14] 何春光. 基于改进SIFT算法的输电线路挂线故障隐患检测[J]. 电子设计工程, 2021, 29(2): 99-102, 107.
[15] 邹栋. 输电线路中关键部件图像识别及异常检测方法研究[D]. 保定: 华北电力大学, 2017.
[16] 熊小萍, 许爽, 蒙登越, 等. 基于Faster R-CNN的输电线路缺陷识别模型研究[J]. 自动化与仪器仪表, 2020(3): 1-6.
[17] 卢宏涛, 张秦川. 深度卷积神经网络在计算机视觉中的应用研究综述[J]. 数据采集与处理, 2016, 31(1): 1-17.
[18] 徐洪学, 汪安祺, 杜英魁, 等. 深度学习的基本模型及其应用研究[J]. 长春师范大学学报, 2020, 39(12): 47-54, 93.
[19] KRIZHEVSKY A, SUTSKEVER I, HINTON G E.Imagenet classification with deep convolutional neural networks[C]//Advances in Neural Information Pro- cessing Systems, London, 2012: 1097-1105.
[20] 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.
[21] 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.
[22] 李柯泉, 陈燕, 刘佳晨, 等. 基于深度学习的目标检测算法综述[J/OL]. 计算机工程: 1-17[2022-01-12]. DOI: 10.19678/j.issn.1000-3428.0062725.
[23] 金昊, 康宇哲, 齐希阳, 等. 基于Faster R-CNN的高压电线缺陷检测方法[J]. 计算机应用, 2019, 39(增刊2): 97-102.
[24] REDMON J, DIVVALA S, GIRSHICK R, et al.You only look once: unified, real-time object detection[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 2016: 779-788.
[25] LIU Wei, ANGUELOV D, ERHAN D, et al.SSD: single shot multibox detector[EB/OL]. arXiv, https:// arxiv.org/abs/1512.02325.
[26] 郑含博, 李金恒, 刘洋, 等. 基于改进YOLOv3的电力设备红外目标检测模型[J]. 电工技术学报, 2021, 36(7): 1389-1398.
[27] 王婉婷, 姜国龙, 褚云飞, 等. 从RCNN到YOLO系列的物体检测系统综述[J]. 齐鲁工业大学学报, 2021, 35(5): 9-16.
[28] 冯庆胜, 牛学慧. 基于SSD的受电弓拉弧在线检测方法[J]. 自动化与仪表, 2021, 36(3): 45-49.
[29] 唐聪, 凌永顺, 郑科栋, 等. 基于深度学习的多视窗SSD目标检测方法[J]. 红外与激光工程, 2018, 47(1): 302-310.
[30] 翁智, 程曦, 郑志强. 基于改进YOLOv3的高压输电线路关键部件检测方法[J]. 计算机应用, 2020, 40(增刊2): 183-187.
[31] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al.Generative adversarial networks[C]//International Conference on Neural Information Processing Systems, 2014: 2672-2680.
[32] 顾晓东, 唐丹宏, 黄晓华. 基于深度学习的电网巡检图像缺陷检测与识别[J]. 电力系统保护与控制, 2021, 49(5): 91-97.
[33] KARLINSKY L, SHTOK J, HARARY S, et al.RepMet: representative-based metric learning for classification and few-shot object detection[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 2019.
[34] PAN S J, YANG Qiang.A survey on transfer lear- ning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345-1359.
[35] 刘大鹏, 曹永锋, 张伦. 深度迁移主动学习研究综述[J]. 现代计算机, 2021(10): 88-93.
[36] XU Yong, DU Jun, DAI Lirong, et al.Cross-language transfer learning for deep neural network based speech enhancement[C]//International Symposium on Chinese Spoken Language Processing, Singapore, 2014.
[37] HUANG Shengjun, ZHAO Jiawei, LIU Zhaoyang.Cost-effective training of deep CNNs with active model adaptation[EB/OL]. arXiv, https://arxiv.org/abs/ 1802.05394.
[38] 王涵, 张倩旭, 黄银龙. 基于迁移学习的电力设备发热位置判定方法[J]. 科技经济导刊, 2020, 28(34): 14-15.
[39] CRESWELL A, WHITE T, DUMOULIN V, et al.Generative adversarial networks: an overview[J]. IEEE Signal Processing Magazine, 2018, 35(1): 53-65.
[40] TAYLOR L, NITSCHKE G.Improving deep learning with generic data augmentation[C]//2018 IEEE Symposium Series on Computational Intelligence (SSCI), Bangalore, 2018.
[41] 麦俊佳, 曾懿辉, 胡壮丽, 等. 基于深度学习的输电线路航拍照片目标检测应用[J]. 广东电力, 2020, 33(9): 174-182.
[42] PEREZ L, WANG J.The effectiveness of data aug- mentation in image classification using deep lear- ning[EB/OL]. arXiv, https://arxiv.org/abs/1712.04621v1.
[43] 淦艳, 叶茂, 曾凡玉. 生成对抗网络及其应用研究综述[J]. 小型微型计算机系统, 2020, 41(6): 1133-1139.
[44] 何佳美. 基于生成对抗网络的电力设备图像扩充模型及算法研究[D]. 成都: 电子科技大学, 2020.
[45] 任欢, 王旭光. 注意力机制综述[J]. 计算机应用, 2021, 41(增刊1): 1-6.
[46] 邬满, 文莉莉, 孙苗. 注意力机制海洋场景图像理解算法[J/OL]. 计算机工程与应用: 1-11 [2021-11-22]. http://kns.cnki.net/kcms/detail/11.2127.TP.20210317. 1008.002.html.
[47] 王燕妮, 余丽仙. 注意力与多尺度有效融合的SSD目标检测算法[J]. 计算机科学与探索, 2022, 16(2): 438-447.
[48] CHENG Yu, WANG Duo, ZHOU Pan, et al.A survey of model compression and acceleration for deep neural networks[EB/OL]. arXiv, https://arxiv.org/abs/1710. 09282.
[49] 张涛. 高压输电线路目标缺陷识别算法设计与实现[D]. 扬州: 扬州大学, 2021.
[50] 吴凯东, 缪希仁, 刘志颖, 等. 基于泛在物联的输电线路智能巡检技术综述[J]. 电器与能效管理技术, 2020(3): 1-7.
[51] 张姝, 王昊天, 董骁翀, 等. 基于深度学习的输电线路螺栓检测技术[J]. 电网技术, 2021, 45(7): 2821-2829.
[52] 李雪峰, 刘海莹, 刘高华, 等. 基于深度学习的输电线路销钉缺陷检测[J]. 电网技术, 2021, 45(8): 2988-2995.
[53] 宁柏锋. 基于深度学习的无人机巡检图像销钉故障检测[J]. 计算机测量与控制, 2019, 27(11): 25-29.
[54] 王万国, 田兵, 刘越, 等. 基于RCNN的无人机巡检图像电力小部件识别研究[J]. 地球信息科学学报, 2017, 19(2): 256-263.
[55] 杨波, 曹雪虹, 焦良葆, 等. 改进实时目标检测算法的电力巡检鸟巢检测[J]. 电气技术, 2020, 21(5): 21-27, 32.
[56] OUYANG Wanli, WANG Xiaogang, ZHANG Cong, et al.Factors in finetuning deep model for object detection with long-tail distribution[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 2016: 864-873.
[57] VACARO L, SAUSONETTI G, MICARELLI A.An empirical review of automated machine learning[J]. Computers, 2021, 10(1): 11. |
|
|
|
2022, Vol. 23 
