Deep Residual UNet Network-based Infrared Image Segmentation Method for Electrical Equipment
-
摘要: 红外图像处理是实现电气故障诊断的有效手段,而电气设备分割是故障检测的关键环节。针对复杂背景下红外图像电气设备分割难问题,本文采用深度残差网络与UNet网络相结合,深度残差网络替代VGG16对UNet网络进行特征提取和编码,构建深度残差系列Res-Unet网络实现对电气设备的分割。以电流互感器和断路器两种电气设备红外图像分割为例测试Res-Unet网络分割效果,并与传统的UNet网络和Deeplabv3+网络进行对比。通过对数量为876的样本进行测试,实验结果表明,Res18-UNet能够准确地分割电气设备,对电流互感器和断路器的分割准确率超93%,平均交并比大于89%,且分割准确性优于UNet及Deeplabv3+网络模型,为实现电气故障智能诊断奠定基础。Abstract: Infrared thermal image processing is an effective method for detecting defects in electrical equipment. Aiming at the problem of electrical equipment segmentation in infrared thermal images with a complex background, in this study we propose a deep residual UNet network for infrared thermal image segmentation. Using a deep residual network to replace VGG16 to perform feature extraction and coding for the UNet network, a deep residual series UNET network was constructed to segment electrical equipment. To validate the effectiveness of the Res-UNet network, infrared images, including current transformers and circuit breakers, were used to test the segmentation results and were compared with the traditional UNet and Deeplabv3+ networks. The networks were tested using 876 images. The experimental results show that RES18-UNET can accurately segment electrical equipment; the segmentation precision of current transformers and circuit breakers is greater than 93%, and the mean intersection over union (MIoU) is greater than 89%. Our method obtains more accurate segmentation results than UNet and Deeplabv3+, setting the basis for intelligent diagnosis of electrical faults.
-
Key words:
- infrared image /
- electrical fault diagnosis /
- image segmentation /
- UNet
-
表 1 不同分割方法得到的MIOU值
Table 1. The MIOU values based on different segmentation methods
表 2 测试数据集的准确率
Table 2. The accuracy of the test dataset
network Segmentation object IoU MIoU Precision Deeplabv3+ Current transformer 0.79 0.8011 0.90 Circuit breaker 0.67 0.84 Background 0.95 0.97 UNet Current transformer 0.8023 0.8272 0.9150 Circuit breaker 0.7179 0.8960 Background 0.9615 0.9805 Res18-UNet Current transformer 0.8623 0.8963 0.9470 Circuit breaker 0.8579 0.9347 Background 0.9686 0.9907 Res34-UNet Current transformer 0.6306 0.7139 0.7110 Circuit breaker 0.6064 0.7396 Background 0.9047 0.9872 Res50-UNet Current transformer 0.4747 0.5906 0.5174 Circuit breaker 0.4249 0.3700 Background 0.8722 0.9689 -
[1] 康龙. 基于红外图像处理的变电站设备故障诊断[D]. 北京: 华北电力大学, 2016.KANG Long. Substation Equipment Fault Diagnosis Based on Infrared Image[D]. Beijing: North China Electric Power University, 2016. [2] 曾亮. 基于红外图像的变电站设备故障精准定位方法的研究[D]. 重庆: 重庆理工大学, 2019.ZENG Liang. Research on Precise Fault Location Method of Substation Equipment Based on Infrared Image[D]. Chongqing: Chongqing University of Technology, 2019. [3] ZOU H, HUANG F. A novel intelligent fault diagnosis method for electrical equipment using infrared thermography[J]. Infrared Physics & Technology, 2015, 73: 29-35. [4] 周建国, 雷民, 杨褚明, 等. 带电设备红外诊断应用规范: DL/T 664-2008. [S]. 国家能源局, [2016-12-05].ZHOU Jianguo, LEI Min, YANG Chuming, et al. Application Specification for Infrared Diagnosis of Live Equipment[S]. National Energy Administration, [2016-12-05]. [5] 许志浩, 郑诗泉, 康兵, 等. 基于三相自搜寻比较法的电气设备过热故障识别方法[J]. 红外技术, 2021, 43(11): 1112-1118. http://hwjs.nvir.cn/article/id/35d8419e-d42a-4472-bc86-a4292e5976a4XU Zhihao, ZHENG Shiquan, KANG Bing, et al. Overheat fault identification method for electrical equipment based on three-phase self-searching comparison method[J]. Infrared Technology, 2021, 43(11): 1112-1118. http://hwjs.nvir.cn/article/id/35d8419e-d42a-4472-bc86-a4292e5976a4 [6] Rahmani A, Haddadnia J, SeryasatO. Intelligent fault detection of electrical equipment in ground substations using thermo vision technique[C]//2010 2nd International Conference on Mechanical and Electronics Engineering, 2010: V2-150-V2-154. [7] LIN K C, LAI C S. Fault recognition system of electrical components in scrubber using infrared images[C]//International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, 2003: 1303-1310. [8] 王晶, 姚邹静, 赵春晖. 基于红外图像时空特征的电力设备故障诊断[J]. 控制工程, 2021, 28(8): 1683-1690. https://www.cnki.com.cn/Article/CJFDTOTAL-JZDF202108025.htmWANG Jing, YAO Zoujing, ZHAO Chunhui. A fault diagnosis method for power equipment based on spatiotemporal features of infrared images[J]. Control Engineering of China, 2021, 28(8): 1683-1690. https://www.cnki.com.cn/Article/CJFDTOTAL-JZDF202108025.htm [9] 李文璞, 谢可, 廖逍, 等. 基于Faster RCNN变电设备红外图像缺陷识别方法[J]. 南方电网技术, 2019, 13(12): 79-84. https://www.cnki.com.cn/Article/CJFDTOTAL-NFDW201912012.htmLI Wenpu, XIE Ke, LIAO Xiao, et al. Intelligent diagnosis method of infrared image for transformer equipment based on improved faster RCNN[J]. Southern Power System Technology, 2019, 13(12): 79-84. https://www.cnki.com.cn/Article/CJFDTOTAL-NFDW201912012.htm [10] 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(S1): 302-310. https://www.cnki.com.cn/Article/CJFDTOTAL-DGJS2020S1034.htmWANG 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. https://www.cnki.com.cn/Article/CJFDTOTAL-DGJS2020S1034.htm [11] 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. https://www.cnki.com.cn/Article/CJFDTOTAL-DGJS202107009.htmZHENG Hanbo, LI Jinheng, LIU Yang, et al. Infrared object detection model for power equipment based on improved YOLOv3[J]. Transactions of China Electrotechnical Society, 2021, 36(7): 1389-1398. https://www.cnki.com.cn/Article/CJFDTOTAL-DGJS202107009.htm [12] 黄新宇, 张洋, 王黎明, 等. 基于Mask-RCNN算法的复合绝缘子串红外图像分割与温度读取[J]. 高压电器, 2021, 57(9): 87-94. https://www.cnki.com.cn/Article/CJFDTOTAL-GYDQ202109012.htmHUANG Xinyu, ZHANG Yang, WANG Liming, et al. Infrared image segmentation and temperature reading of composite insulator strings based on mask⁃RCNN algorithm[J]. High Voltage Apparatus, 2021, 57(9): 87-94. https://www.cnki.com.cn/Article/CJFDTOTAL-GYDQ202109012.htm [13] 李文璞, 毛颖科, 廖逍, 等. 基于旋转目标检测的变电设备红外图像电压致热型缺陷智能诊断方法[J]. 高电压技术, 2021, 47(9): 3246-3253. https://www.cnki.com.cn/Article/CJFDTOTAL-GDYJ202109022.htmLI Wenpu, MAO Yingke, LIAO Xiao, et al. Intelligent diagnosis method of infrared image for substation equipment voltage type thermal defects based on rotating target detection [J]. High Voltage Apparatus, 2021, 47(9): 3246-3253. https://www.cnki.com.cn/Article/CJFDTOTAL-GDYJ202109022.htm [14] 刘云鹏, 张喆, 裴少通, 等. 基于深度学习的红外图像中劣化绝缘子片的分割方法[J]. 电测与仪表, 2022, 59(9): 63-68. https://www.cnki.com.cn/Article/CJFDTOTAL-DCYQ202209009.htmLIU Yunpeng, ZHANG Zhe, PEI Shaotong, et al. Faulty insulator segmentation method in infrared image based on deep learning[J]. Electrical Measurement & Instrumentation, 2022, 59(9): 63-68. https://www.cnki.com.cn/Article/CJFDTOTAL-DCYQ202209009.htm [15] 袁刚, 许志浩, 康兵, 等. 基于DeepLabv3+网络的电流互感器红外图像分割方法[J]. 红外技术, 2021, 43(11): 1127-1134. http://hwjs.nvir.cn/article/id/b9df2f53-2244-471b-b0ec-42159cfaa654YUAN Gang, XU Zhihao, KANG Bing, et al. Deep Labv3+ network-based infrared image segmentation method for current transformer[J]. Infrared Technology, 2021, 43(11): 1127-1134. http://hwjs.nvir.cn/article/id/b9df2f53-2244-471b-b0ec-42159cfaa654 [16] 谷世举, 卜雄洙, 靳建伟, 等. 基于改进Unet网络的炮口火焰分割方法[J]. 国外电子测量技术, 2021, 40(4): 16-21. https://www.cnki.com.cn/Article/CJFDTOTAL-GWCL202104006.htmGU Shiju, BU Xingzhu, JIN Jianwei, et al. Muzzle flame segmentation method based on improved Unet network[J]. Foreign Electronic Measurement Technology, 2021, 40(4): 16-21. https://www.cnki.com.cn/Article/CJFDTOTAL-GWCL202104006.htm [17] CHEN Z, ZHU H. Visual quality evaluation for semantic segmentation: subjective assessment database and objective assessment measure[J]. IEEE Transactions on Image Processing, 2019, 28(12): 5785-5796.