Abstract:Aiming at the shortcomings of existing infrared images, such as low resolution and poor definition, which can easily affect the fault detection effect of electrical equipment based on infrared images, a super resolution fault identification method of infrared images of electrical equipment based on multi-scale collaboration model is proposed. Firstly, a super resolution reconstruction network for infrared images of electrical equipment is constructed based on multi-scale collaboration model. The network is based on generative adversarial network. By introducing multi-scale collaboration module and two-channel structure, the adaptability of the super resolution reconstruction network to infrared images is improved, and the effect of image feature extraction is optimized. On the basis of infrared image super-resolution reconstruction, combined with deep learning target detection method, a super-resolution fault identification model of infrared image of electrical equipment is established. Experimental verification of the proposed method is carried out. The experimental results show that the infrared image quality can be significantly improved after the proposed super resolution reconstruction network, and the PSNR and SSIM values can be increased to 27.26dB and 0.828 3 respectively. The proposed infrared image super-resolution fault identification model can significantly improve the fault identification effect, mAP, mAR, mAC and mAIOU increased by 19.34%、19.14%、11.83% and 25.03% on average.
[1] Xia Changjie, Ren Ming, Wang Bing, et al.Infrared thermography-based diagnostics on power equipment: state-of-the-art[J]. High Voltage, 2020, DOI:10.1049/ hve2.12023. [2] 李玉杰, 李洪涛, 宋思齐, 等. 基于红外的GIS内部导体温度检测技术研究[J]. 电力工程技术, 2019, 38(2): 142-146. Li Yujie, Li Hongtao, Song Siqi, et al.Temperature detection of internal conductor in GIS based on infrared thermal imaging[J]. Electric Power Engineering Technology, 2019, 38(2): 142-146. [3] 周念成, 廖建权, 王强钢, 等. 深度学习在智能电网中的应用现状分析与展望[J]. 电力系统自动化, 2019, 43(4): 180-191. Zhou Niancheng, Liao Jianquan, Wang Qianggang, et al.Analysis and prospect of the application of deep learning in smart grid[J]. Automation of Electric Power Systems, 2019, 43(4): 180-191. [4] 孙曙光, 李勤, 杜太行, 等. 基于一维卷积神经网络的低压万能式断路器附件故障诊断[J]. 电工技术学报, 2020, 35(12): 2562-2573. Sun Shuguang, Li Qin, Du Taihang, et al.Fault diagnosis of accessories for the low voltage conventional circuit breaker based on one-dimensional convolutional neural network[J]. Transactions of China Electrotechnical Society, 2020, 35(12): 2562-2573. [5] 白洁音, 赵瑞, 谷丰强, 等. 多目标检测和故障识别图像处理方法[J]. 高电压技术, 2019, 45(11): 3504-3511. Bai Jieyin, Zhao Rui, Gu Fengqiang, et al.Multi-target detection and fault recognition image processing method[J]. High Voltage Engineering, 2019, 45(11): 3504-3511. [6] Miao Xiren, Liu Xinyu, Chen Jing, et al.Insulator detection in aerial images for transmission line inspection using single shot multi-box detector[J]. IEEE Access, 2019: 9945-9956. [7] Chao Dong, Chen Change Loy, He Kaiming, et al.Image Super-resolution using deep convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307. [8] Tong Tong, Li Gen, Liu Xiejie, et al.Image super-resolution using dense skip connections[C]//IEEE 2017 International Conference on Computer Vision, Venice, Italy, 2017: 4809-4817. [9] Zhang Yulun, Tian Yapeng, Kong Yu, et al.Residual dense network for image super-resolution[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2018: 2472-2481. [10] Justin Johnson, Alexandre Alahi, Li Fei-Fei.Perceptual losses for real-time style transfer and super-resolution[C]//European Conference on Computer Vision, Amsterdam: Springer, 2016: 694-711. [11] Christian Ledig, Lucas Theis, Ferenc Huszár, et al.Photo-realistic single image super-resolution using a generative adversarial network[C]//IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, 2017: 105-114. [12] 陈智雨, 巩少岩, 俞学豪, 等. 基于自学习超分辨率的电力线路巡检可视化[J]. 电力信息与通信技术, 2019, 17(9): 11-16. Chen Zhiyu, Gong Shaoyan, Yu Xuehao, et al.Super-resolution visual patrol inspection for power line based on self-learning[J]. Electric Power Information and Communication Technology, 2019, 17(9): 11-16. [13] 白万荣, 张驯, 朱小琴, 等. 基于E-FCNN的电力巡检图像增强[J]. 中国电力, 2021(5): 179-185. Bai Wanrong, Zhang Xun, Zhu Xiaoqin, et al.Electric power inspection image enhancement based on E-FCNN[J]. Electric Power, 2021(5): 179-185. [14] 王功明, 乔俊飞, 王磊. 一种能量函数意义下的生成式对抗网络[J]. 自动化学报, 2018, 44(5): 793-803. Wang Gongming, Qiao Junfei, Wang Lei.A generative adversarial network based on energy function[J]. Acta Automatic Sinica, 2018, 44(5): 793-803. [15] Wang Xintao, Yu Ke, Wu Shixiang, et al.Enhanced super-resolution generative adversarial networks[C]// LNCS 11133: Proceedings of the 2018 European Conference on Computer Vision Workshop, 2018: 63-79. [16] Radu Timofte, Eirikur Agustsson, Luc Van Gool, et al.Ntire 2017 challenge on single image super-resolution: methods and results[C]//IEEE Conference on Computer Vision and Pattern Recognition Workshop, 2017: 1110-1121. [17] Wang Zhou, Alan Conrad Bovik, Hamid Rahim Sheikh, et al.Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Process, 2004, 13(4): 600-612. [18] Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee.Accurate image super-resolution using very deep convolutional networks[C]//IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016: 1646-1654. [19] 朱惠玲, 牛哲文, 黄克灿, 等. 基于单阶段目标检测算法的变电设备红外图像目标识别及定位[J]. 电力自动化设备, 2021, 41(8): 217-224. Zhu Huiling, Niu Zhewen, Huang Kecan, et al.Target recognition and localization in infrared image of electrical equipment based on single-stage target detection algorithm[J]. Electric Power Automation Equipment, 2021, 41(8): 217-224. [20] 徐建军, 黄立达, 闫丽梅, 等. 基于层次多任务深度学习的绝缘子自爆缺陷检测[J]. 电工技术学报, 2021, 36(7): 1407-1415. Xu Jianjun, Huang Lida, Yan Limei, et al.Insulator self-explosion defect detection based on hierar-chical multi-task deep learning[J]. Transactions of China Electrotechnical Society, 2021, 36(7): 1407-1415. [21] 王旭红, 李浩, 樊绍胜, 等. 基于改进SSD的电力设备红外图像异常自动检测方法[J]. 电工技术学报, 2020, 35(增刊1): 302-310. Wang Xuhong, Li Hao, Fan Shaosheng, et al.Infrared image anomaly automatic detection method for power equipment based on improved single shot multi box detection[J]. Transactions of China Electrotechnical Society, 2020, 35(S1): 302-310. [22] 王卓, 王玉静, 王庆岩, 等. 基于协同深度学习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. [23] Joseph Redmon, Santosh Divvala, Ross Girshick, et al.You only look once: unified real-time object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 2016: 779-788. [24] 张倩, 王建平, 李帷韬. 基于反馈机制的卷积神经网络绝缘子状态检测方法[J]. 电工技术学报, 2019, 34(16): 3311-3321. Zhang Qian, Wang Jianping, Li Weitao.Insulator state detection of convolutional neural networks based on feedback mechanism[J]. Transactions of China Electrotechnical Society, 2019, 34(16): 3311-3321. [25] 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. Zheng Hanbo, Li Jinheng, Liu Yang, et al.Object detection model for power equipment based on improved YOLOv3[J]. Transactions of China Electrotechnical Society, 2021, 36(7): 1389-1398. [26] 徐奇伟, 黄宏, 张雪锋, 等. 基于改进区域全卷积网络的高压引线接头红外图像特征分析的在线故障诊断方法[J]. 电工技术学报, 2021, 36(7): 1380-1388. Xu Qiwei, Huang Hong, Zhang Xuefeng, et al.Online fault diagnosis method for infrared image feature analysis of high-voltage lead connectors based on improved R-FCN[J]. Transactions of China Electro- technical Society, 2021, 36(7): 1380-1388.