Multi-scale Guided Filter and Decision Fusion for Thermal Fault Diagnosis of Power Equipment
-
摘要: 本文提出一种基于多尺度引导滤波和决策融合(multi-scale guided filter and decision fusion, MGDF)的电力设备热故障诊断方法,联合多尺度引导滤波和决策融合技术,充分挖掘红外图像的空间结构信息和温度信息。该方法有3个主要步骤。首先,基于热故障区域与环境背景在红外图像上的温度差异特性,逐像素计算热故障区域与环境背景的马氏距离,获取初始的热故障诊断结果。然后,采用不同参数设置的引导滤波器对初始诊断结果进行滤波处理,并将生成的若干引导滤波特征图堆叠在一起。不同参数下的滤波特征图包含着互补的空间结构信息。最后,为充分挖掘不同尺度特征图的空间结构信息和温度差异信息,利用主成分分析法对引导滤波特征图进行决策融合,提升热故障的诊断精度,生成最终的热故障诊断结果图。实验测试结果表明,本文方法在热故障诊断精度上有明显优势,满足电力设备红外巡检的应用需求。Abstract: This paper introduces a thermal fault diagnosis method called multi-scale guided filtering and decision fusion. The proposed method combines multiscale guided filtering and decision-fusion techniques for fault diagnosis. It comprises three main steps. First, the Mahalanobis distance between the fault area and background is estimated, and initial thermal fault diagnosis results are generated. The initial diagnosis result is then filtered using guided filtering with various parameters, and several filtering feature maps are generated. Different filtering feature maps contain complementary spatial-structure information. Finally, a principal component analysis algorithm fuses these filtering feature maps to capture their spatial structure information and thermal information in filtering feature maps. Experimental results show that the proposed diagnosis method has a better detection performance than the current state-of-the-art detectors.
-
Key words:
- power equipment /
- infrared image /
- thermal fault diagnosis /
- guided fusion /
- multi-scale /
- decision fusion
-
表 1 不同诊断方法的AUC指标
Table 1. AUC values of different diagnosis methods
Test
imagesRX LDP LRR MGDF 1 0.9707 0.8312 0.8974 0.9852 2 0.9901 0. 9132 0. 9326 0.9993 3 0.9893 0. 9253 0. 9486 0.9989 表 2 不同诊断方法的运行时间
Table 2. Running time of different diagnosis methods
Test images RX LDP LRR MGDF 1 0.59 0.75 0.47 2.31 2 0.53 0.61 0.34 2.27 3 0.84 0.98 0.56 2.15 表 3 单一尺度滤波参数的AUC指标
Table 3. Diagnosis methods with various parameters
Test images GF1 GF2 GF3 GF4 MGDF 1 0.9403 0.9433 0.9681 0.9562 0.9852 2 0.9787 0.9464 0.9805 0.9908 0.9993 3 0.9693 0.9712 0.9485 0.9824 0.9989 -
[1] 黄志鸿, 吴晟, 肖剑, 等. 基于引导滤波的电力设备热故障诊断方法研究[J]. 红外技术, 2021, 43(9): 910-915. http://hwjs.nvir.cn/article/id/cb2a71f1-cd7c-4e76-977b-b6f7472b905dHUANG Zhihong, WU Sheng, XIAO Jian, et al. Thermal fault diagnosis of power equipments based on guided filter[J]. Infrared Technology, 2021, 43(9): 910-915. http://hwjs.nvir.cn/article/id/cb2a71f1-cd7c-4e76-977b-b6f7472b905d [2] 刘嵘, 刘辉, 贾然, 等. 一种智能型电网设备红外诊断系统的设计[J]. 红外技术, 2020, 42(12): 198-1202. http://hwjs.nvir.cn/article/id/a00b6f68-052d-40c0-a00f-1f0ff120ce69LIU Rong, LIU Hui, JIA Ran, et al. Design of intelligent infrared diagnosis system for power grid equipment[J]. Infrared Technology, 2020, 42(12): 1198-1202. http://hwjs.nvir.cn/article/id/a00b6f68-052d-40c0-a00f-1f0ff120ce69 [3] 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. Fault Diagnosis of Substation Equipment Based on Infrared Image Processing[D]. Beijing: North China Electric Power University, 2016. [4] 胡洛娜, 彭云竹, 石林鑫. 核猫群红外图像异常检测方法在电力智能巡检中的应用[J]. 红外技术, 2018, 40(9): 323-328. http://hwjs.nvir.cn/article/id/hwjs201809013HU Luona, PENG Yunzhu, SHI Linxin. Anomaly detection method of infrared images based on kernel cat swarm optimization clustering with application in intelligent electrical power inspection[J]. Infrared Technology, 2018, 40(9): 323-328. http://hwjs.nvir.cn/article/id/hwjs201809013 [5] 魏钢, 冯中正, 唐跃林, 等. 输变电设备红外故障诊断技术与试验研究[J]. 电气技术, 2013, 14(6): 75-78. https://www.cnki.com.cn/Article/CJFDTOTAL-DQJS201306030.htmWEI Gang, FENG Zhongzheng, TANG Yuelin, et al. The infrared diagnostic technology of power transmission devices and experimental study[J]. Electrical Technology, 2013, 14(6): 75-78. https://www.cnki.com.cn/Article/CJFDTOTAL-DQJS201306030.htm [6] 李鑫, 崔昊杨, 霍思佳, 等. 基于粒子群优化法的Niblack电力设备红外图像分割[J]. 红外技术, 2018, 40(8): 780-785. http://hwjs.nvir.cn/article/id/hwjs201808010LI Xin, CUI Wuyang, HUO Sijia. Niblack's method for infrared image segmentation of electrical equipment improved by particle swarm optimization[J]. Infrared Technology, 2018, 40(8): 780-785. http://hwjs.nvir.cn/article/id/hwjs201808010 [7] 林颖, 郭志红, 陈玉峰. 基于卷积递归网络的电流互感器红外故障图像诊断[J]. 电力系统保护与控制, 2017, 45(16): 87-94. https://www.cnki.com.cn/Article/CJFDTOTAL-JDQW201516013.htmLIN Ying, GUO Zhihong, CHEN Yufeng. Convolutional-recursive network based current transformer infrared fault image diagnosis[J]. Power System Protection and Control, 2015, 45(16): 87-94. https://www.cnki.com.cn/Article/CJFDTOTAL-JDQW201516013.htm [8] 黄志鸿, 洪峰, 黄伟. 形状自适应低秩表示的电力设备热故障诊断方法研究[J]. 红外技术, 2022, 44(9): 870-874. http://hwjs.nvir.cn/article/id/8f0f8a69-4b47-46b4-bcdf-ea623287093fHUANG Zhihong, HONG Feng, HUANG Wei. Shape-adaptation low-rank representation for thermal fault diagnosis of power equipments[J]. Infrared Technology, 2022, 44(9): 870-874. http://hwjs.nvir.cn/article/id/8f0f8a69-4b47-46b4-bcdf-ea623287093f [9] 常亮, 邓小明, 周明全, 等. 图像理解中的卷积神经网[J]. 自动化学报, 2016, 42(9): 1300-1312. https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201609002.htmCHANG Liang, DENG Xiaoming, ZHOU Mingquan, et al. Convolutional neural networks in image understanding[J]. Acta Automatica Sinica, 2016, 42(9): 1300-1312. https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201609002.htm [10] 魏东, 龚庆武, 来文青, 等. 基于卷积神经网络的输电线路区内外故障判断及故障选相方法研究[J]. 中国电机工程学报, 2016, 36(5): 21-28. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDC2016S1003.htmWEI Dong, LONG Qinwu, LAI Wenqing, et al. Research on internal and external fault diagnosis and fault-selection of transmission line based on convolutional neural network[J]. Proceedings of the CSEE, 2016, 36(5): 21-28. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDC2016S1003.htm [11] 周可慧, 廖志伟, 肖异瑶, 等. 基于改进CNN的电力设备红外图像分类模型构建研究[J]. 红外技术, 2019, 41(11): 1033-1038. https://www.cnki.com.cn/Article/CJFDTOTAL-HWJS201911007.htmZHOU Kehui, LIAO Zhiwei, XIAO Yiyao, et al. Construction of infrared image classification model for power equipments based on improved CNN[J]. Infrared Technology, 2019, 41(11): 1033-1038. https://www.cnki.com.cn/Article/CJFDTOTAL-HWJS201911007.htm [12] HUANG Z, ZHOU J, LI S, et al. Superpixels segmentation and low-rank matrix recovery for thermal fault diagnosis of power equipment[C]//IEEE 5th Conference on Energy Internet and Energy System Integration, 2021: DOI: 10.1109/EI252483.2021.9713012 [13] KANG X, ZHANG X, LI S, et al. Hyperspectral anomaly detection with attribute and edge-preserving filters[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(10): 5600-5611. https://ieeexplore.ieee.org/document/7994698 [14] HE K, SUN J, TANG X. Guided image filtering[C]//Proc. of Processing IEEE Conference Computer Vision Pattern Recognition, 2010: 1-14. [15] Durand F, Dorsey J. Fast bilateral filtering for the display of high-dynamic-range images[J]. ACM Transactions on Graphics, 2002, 21(3): 257-266. https://www.bibsonomy.org/bibtex/2714918ed2c28651e4e8039e735c9393f/dblp?lang=en [16] Reed I S, YU X. Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution[J]. IEEE Transactions on Acoustic Speech Signal Processing, 1990, 38(10): 1760-1770. https://ieeexplore.ieee.org/document/60107 [17] KANG X, ZHANG X, LI S, et al. Hyperspectral anomaly detection with attribute and edge-preserving filters[J]. IEEE Trans. Geosci. Remote Sens., 2017, 55(10): 5600-5611. https://ieeexplore.ieee.org/document/7994698 [18] XU Y, WU Z, LI J, et al. Anomaly detection in hyperspectral images based on low-rank and sparse representation[J]. IEEE Trans. Geosci. Remote Sens. , 2016, 54(4): 1990-2000. https://ieeexplore.ieee.org/document/7322257 [19] 蒋昀宸, 樊绍胜, 陈骏星溆. 带电作业智能新技术及其应用现状[J]. 湖南电力, 2018, 38(5): 1-4. https://www.cnki.com.cn/Article/CJFDTOTAL-HNDL201805001.htmJIANG Yunchen, FAN Zhaosheng, CHEN Junxingxu. Smart new-technologies and applications for live work[J]. Hunan Electric Power, 2018, 38(5): 1-4. https://www.cnki.com.cn/Article/CJFDTOTAL-HNDL201805001.htm