基于改进生成对抗网络的无人机电力杆塔巡检图像异常检测

doi:10.19595/j.cnki.1000-6753.tces.211849

摘要
图/表
参考文献
相关文章 (7)

全文: PDF (20235 KB) HTML
输出: BibTeX | EndNote (RIS)

摘要无人机电力线路巡检拍摄的杆塔图像背景复杂且正负样本极不均衡,严重影响了电力杆塔异常检测的准确性。该文提出一种基于压缩激活改进的快速异常检测生成对抗网络（SE-f-AnoGAN）,可提高复杂背景下无人机电力杆塔巡检图像异常检测的精度。首先,在f-AnoGAN编码器中引入压缩激活网络（SENet）,提取图像中的显著性信息。然后,将生成对抗网络的无监督学习和二分类器的有监督学习有机结合,实现前者特征提取优势和后者判别优势的互补。在此基础上,借助基于迁移学习的优化训练策略进一步有效提升模型在大规模数据集上的泛化性能。实验结果显示,总体样本的检测准确率为95.74%,正负样本的召回率分别达到96.05%和95.36%,证明了SE-f-AnoGAN在异常检测中的有效性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	仲林林
	胡霞
	刘柯妤

关键词 ：电力杆塔, 无人机巡检, 异常检测, 生成对抗网络, 迁移学习, 不平衡样本

Abstract：Power tower inspection images captured by unmanned aerial vehicles(UAVs)have complex background, and the normal and abnormal samples are extremely unbalanced, which significantly affect the accuracy of anomaly detection for power towers. In order to improve the anomaly detection accuracy in the complex environment, this paper proposes an anomaly detection method for UAV power tower inspection images based on Squeeze-and-Excitation improved fast unsupervised anomaly detection with generative adversarial network(SE-f-AnoGAN). Firstly, the Squeeze-and-Excitation Network(SENet) is added to the encoder in f-AnoGAN to extract the saliency information of images. Next, a combination of unsupervised learning by generative adversarial network and supervised learning by binary classifier is proposed, which consolidates the advantages of feature extractor and discriminator respectively. On this basis, the optimization training strategy based on transfer learning is used to further effectively improve the generalization of the model on the large datasets. The experimental results show that the accuracy rate of overall samples is 95.74% and the recall rates of positive and negative samples reach 96.05% and 95.36% respectively, which demonstrates the effectiveness of SE-f-AnoGAN in anomaly detection.

Key words： Power tower unmanned aerial vehicle (UAV) inspection anomaly detection generative adversarial network transfer learning unbalanced dataset

收稿日期: 2021-11-13

PACS:	TM75
	TP39

基金资助:江苏省科协青年科技人才托举工程（2021031）、东南大学“至善青年学者”支持计划和中央高校基本科研业务费专项资金资助项目

通讯作者: 仲林林男,1990年生,副研究员,博士生导师,研究方向为高电压技术、放电等离子体技术、人工智能技术。E-mail：linlin@seu.edu.cn

作者简介: 胡霞女,1998年生,硕士研究生,研究方向为目标检测与异常检测。E-mail：huxia@seu.edu.cn

引用本文:

仲林林, 胡霞, 刘柯妤. 基于改进生成对抗网络的无人机电力杆塔巡检图像异常检测[J]. 电工技术学报, 2022, 37(9): 2230-2240. Zhong Linlin, Hu Xia, Liu Keyu. Power Tower Anomaly Detection from Unmanned Aerial Vehicles Inspection Images Based on Improved Generative Adversarial Network. Transactions of China Electrotechnical Society, 2022, 37(9): 2230-2240.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.211849 https://dgjsxb.ces-transaction.com/CN/Y2022/V37/I9/2230

[1] 蒋兴良, 侯乐东, 韩兴波, 等. 输电线路导线覆冰扭转特性的数值模拟[J]. 电工技术学报, 2020, 35(8): 1818-1826.
Jiang Xingliang, Hou Ledong, Han Xingbo, et al.Numerical simulation of torsion characteristics of transmission line conductor[J]. Transactions of China Electrotechnical Society, 2020, 35(8): 1818-1826.
[2] Sumagayan M U, Premachandra C, Mangorsi R B, et al.Detecting power lines using point instance network for distribution line inspection[J].IEEE Access, 2021, 9: 107998-108008.
[3] Wang Renshu, Zhang Song, Chen Bin, et al.Unmanned aerial vehicle (UAV) vision-based detection and location of power towers for transmission line maintenance[C]//The 16th IET International Conference on AC and DC Power Transmission, Xi′an, China, 2020: 1937-1941.
[4] Vemula S, Frye M.Mask R-CNN powerline detector: a deep learning approach with applications to a UAV[C]//2020 AIAA/IEEE 39th Digital Avionics Systems Conference, San Antonio, America, 2020: 1-6.
[5] Wong S Y, Choe C W C, Goh H H, et al. Power transmission line fault detection and diagnosis based on artificial intelligence approach and its development in UAV: a review[J]. Arabian Journal for Science and Engineering, 2021, 46(10): 9305-9331.
[6] Bo Li, Cheng Chen, Dong Shiwen, et al.Transmission line detection in aerial images: an instance segmentation approach based on multitask neural networks[J]. Signal Processing: Image Communication, 2021, 96: 116278.
[7] Liu Ruhai, Pei Huikun, Chen Cheng, et al.Research on inclination monitoring technology of transmission tower based on UAV[J]. Journal of Physics: Conference Series, 2021, 2030(1): 012076.
[8] 律方成, 牛雷雷, 王胜辉, 等. 基于优化YOLOv4的主要电气设备智能检测及调参策略[J]. 电工技术学报, 2021, 36(22): 4837-4848.
Lü Fangcheng, Niu Leilei, Wang Shenghui, et al.Intelligent detection and parameter adjustment strategy of major electrical equipment based on optimized YOLOv4[J]. Transactions of China Electrotechnical Society, 2021, 36(22): 4837-4848.
[9] 施孟佶, 秦开宇, 李凯, 等. 高压输电线路多无人机自主协同巡线设计与测试[J]. 电力系统自动化, 2017, 41(10): 117-122.
Shi Mengji, Qin Kaiyu, Li Kai, et al.Design and testing on autonomous multi-UAV cooperation for high-voltage transmission line inspection[J]. Automation of Electric Power Systems, 2017, 41(10): 117-122.
[10] Xiong Xiaoping, Xu Shuang, Wu Wenliang, et al.Identification of electrical equipment based on faster LSTM-CNN network[C]//2020 IEEE International Conference on Networking, Sensing and Control, Nanjing, China, 2020: 1-6.
[11] 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): 1057-1069.
Liu Zhiying, Miao Xiren, Chen Jing, et al.Review ofvisible image intelligent processing for transmission line inspection[J]. Power System Technology, 2020, 44(3): 1057-1069.
[12] 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 Yu, Ning Pingfan, Niu Pingjuan, et al.Review on mounted UAV for transmission line inspection[J]. Power System Technology, 2021, 45(9): 3636-3648.
[13] Miao Xiren, Liu Xinyu, Chen Jing, et al.Insulator detection in aerial images for transmission line inspection using single shot multibox detector[J]. IEEE Access, 2019, 7: 9945-9956.
[14] 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.
Wang Zhuo, Wang Yujing, Wang Qingyan, et al.Two stage insulator fault detection method based on collaborative deep learning[J]. Transactions of China Electrotechnical Society, 2021, 36(17): 3594-3604.
[15] Zhao Wenqing, Xu Minfu, Cheng Xingfu, et al.An insulator in transmission lines recognition and fault detection model based on improved faster RCNN[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-8.
[16] Zhang Jun, Wang Jiye, Zhang Shuha.An ultra-lightweight and ultra-fast abnormal target identification network for transmission line[J]. IEEE Sensors Journal, 2021, 21(20): 23325-23334.
[17] Zu Guangxin, Wu Guoliang, Zhang Chong, et al.Detection of common foreign objects on power grid lines based on Faster R-CNN algorithm and data augmentation method[J]. Journal of Physics: Conference Series, 2021, 1746(1): 012039.
[18] 郭敬东, 陈彬, 王仁书, 等. 基于YOLO的无人机电力线路杆塔巡检图像实时检测[J]. 中国电力, 2019, 52(7): 17-23.
Guo Jingdong, Chen Bin, Wang Renshu, et al.YOLO-based real-time detection of power line poles from unmanned aerial vehicle inspection vision[J]. China Power, 2019, 52(7): 17-23.
[19] Goodfellow I, Pougetabadie J, Mirza M, et al.Generative adversarial nets[C]//Proceedings of the Advances in Neural Information Processing Systems, Montreal, Canada, 2014: 2672-2680.
[20] Arjovsky M, Chintala S, Bottou L.Wasserstein generative adversarial networks[C]//Proceedings of the 34th International Conference on Machine Learning, NSW, Australia, 2017: 214-223.
[21] Gulrajani I, Ahmed F, Arjovsky M, et al.Improved training of wassersteingans[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, USA, 2017: 5769-5779.
[22] 黄南天, 杨学航, 蔡国伟, 等. 采用非平衡小样本数据的风机主轴承故障深度对抗诊断[J]. 中国电机工程学报, 2020, 40(2): 563-574.
Huang Nantian, Yang Xuehang, Cai Guowei, et al.A deep adversarial diagnosis method for wind turbine main bearing fault with imbalanced small sample scenarios[J]. Proceedings of the CSEE, 2020, 40(2): 563-574.
[23] 李东东, 刘宇航, 赵阳, 等. 基于改进生成对抗网络的风机行星齿轮箱故障诊断方法[J]. 中国电机工程学报, 2021, 41(21): 7496-7506.
Li Dongdong, Liu Yuhang, Zhao Yang, et al.Fault diagnosis method of wind turbine planetary gearbox based on improved generative adversarial network[J]. Proceedings of the CSEE, 2021, 41(21): 7496-7506.
[24] Schlegl T, Seeböck P, Waldstein S M, et al.f-AnoGAN: fast unsupervised anomaly detection with generative adversarial networks[J]. Medical Image Analysis, 2019, 54: 30-44.
[25] Schlegl T, Seeböck P, Waldstein S M, et al.Unsupervised anomaly detection with generative adversarial networks to guide marker discovery[C]// International Conference on Information Processing in Medical Imaging, North Carolina, USA, 2017: 146-157.
[26] Wang Yingfan, Huang Haiyang, Rudin C, et al.Understanding how dimension reduction tools work:an empirical approach to deciphering t-SNE, UMAP, TriMAP, and PaCMAP for data visualization[J]. Journal of Machine Learning Research, 2021, 22(201): 1-73.
[27] Zhang Shanshan, Yang Jian, Schiele B.Occluded pedestrian detection through guided attention in cnns[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 6995-7003.
[28] Zhuang Fuzhen, Qi Zhiyuan, Duan Keyu, et al.A comprehensive survey on transfer learning[J]. Proceedings of the IEEE, 2020, 109(1): 43-76.
[29] 陈剑, 杜文娟, 王海风. 采用深度迁移学习定位含直驱风机次同步振荡源机组的方法[J]. 电工技术学报, 2021, 36(1): 179-190.
Chen Jian, Du Wenjuan, Wang Haifeng.A method of locating the power system subsynchronous oscillation source unit with grid-connected PMSG using deep transfer learning[J]. Transactions of China Electrotechnical Society, 2021, 36(1): 179-190.
[30] 周志华. 机器学习[M]. 北京: 清华大学出版社, 2016.