电力设备IR图像特征提取及故障诊断方法研究
|
摘要
针对电力设备红外图像批量诊断中故障特征参量提取及参数配置难题,采用粒子群算法(PSO)与Niblack算法相结合的方法,将设备热像从背景中分割出来并提取出设备的最低、最高及平均温度等参量,通过计算设备各温升特征,构建支持向量机(SVM)样本特征空间。采用优化的蝙蝠算法(BA)对SVM参数进行寻优,并利用最优参数配置下的SVM实现设备故障诊断。对220组图像样本测试结果表明:该红外图像故障诊断方法在电力设备热故障缺陷检测方面的效率及准确率较高,适用于电力大数据中非结构化红外图像的批量分析与处理。
Aiming at the problem of defect test and parameter assignment in the batch diagnosis of power equipment infrared image,PSO and Niblack algorithm are used to separate the equipment thermal image from the background and extract the lowest,highest and average temperature. Then,the SVM sample feature space can be constructed by calculating the temperature rise characteristics of the equipment. The support vector machine( SVM) parameters are optimized by using the optimized bat algorithm( BA),and the equipment defects diagnosis is realized by SVM under the optimal parameter configuration. According to the 220 groups of image sample testing results,the proposed method has high efficiency and accuracy in thermal defects detection of power equipment,and is suitable for batch analysis and processing of unstructured infrared images in large power data.
Aiming at the problem of defect test and parameter assignment in the batch diagnosis of power equipment infrared image,PSO and Niblack algorithm are used to separate the equipment thermal image from the background and extract the lowest,highest and average temperature. Then,the SVM sample feature space can be constructed by calculating the temperature rise characteristics of the equipment. The support vector machine( SVM) parameters are optimized by using the optimized bat algorithm( BA),and the equipment defects diagnosis is realized by SVM under the optimal parameter configuration. According to the 220 groups of image sample testing results,the proposed method has high efficiency and accuracy in thermal defects detection of power equipment,and is suitable for batch analysis and processing of unstructured infrared images in large power data.
引文
[1]YU Ping,CUI Shaofei,GE Yongxin,et al.A new method for electrical equipment visual and infrared image registration based on alignment metric[J].Laser%Infrared,2008,38(7):737-740.(in Chinese)余萍,崔少飞,葛永新,等.基于对齐度的电力设备红外与可见光的图像配准[J].激光与红外,2008,38(7):737-740.
[2]LI Mengxing.Research and implementation of power equipment fault infrared diagnosis system[J].Electric Power IT,2013,11(2):36-39.(in Chinese)李孟兴.电力设备故障红外诊断系统的研究与实现[J].电力信息化,2013,11(2):36-39.
[3]LIN Ying,GUO Zhihong,CHEN Yufeng.Convolutionalrecursive network based current transformer infrared fault image diagnosis[J].Power System Protection and Control,2015,43(16):87-94.(in Chinese)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,2015,43(16):87-94.
[4]ZOU Hui,HUANG Fuzhen.A novel intelligent fault diagnosis method for electrical equipment using infrared thermography[J].Infrared Physics&Technology,2015,73,29-35.
[5]LANG Cheng,JIN Guangxi,XU Dan,et al.Analysis of influence factors on relative temperature difference judgement method of electrical equipments[J].Infrared and Laser Engineering,2011,40(1):28-31,40.(in Chinese)郎成,金光熙,徐丹,等.电气设备相对温差判断法的影响因素分析[J].红外与激光工程,2011,40(1):28-31,40.
[6]JIN Lijun,AI Jianyong,DUAN Wei.Health condition assessment of catenary insulation based on multisource images[J].High Voltage Engineering,2016,42(11):3515-3523.(in Chinese)金立军,艾建勇,段伟.基于多光源图像的接触网外绝缘健康状态评估[J].高电压技术,2016,42(11):3515-3523.
[7]WANG Ju,WANG Zhaohui,LIU Yin.Fast algorithm of sparse signal decomposition based on PSO and LM[J].Laser%Infrared,2012,42(2):227-230.(in Chinese)王菊,王朝晖,刘银.基于PSO和LM的信号稀疏分解快速算法[J].激光与红外,2012,42(2):227-230.
[8]Niblack W.An introduction to digital image processing[M].Denmark:Strand berg Publishing Company Birkeroed,1986,115-116.
[9]YUAN Zhiwei,HUANG Shucai,XIONG Zhigang,et al.Infrared small target detection based on SVM posterior probability[J].Laser%Infrared,2016,46(6):766-771.(in Chinese)苑智玮,黄树彩,熊志刚,等.基于SVM后验概率的红外弱小目标检测[J].激光与红外,2016,46(6):766-771.
[10]HU Yanyan,LI Dongsheng,ZHANG Shigui.Classification of hyperspectral image by convex combination kernels function SVM[J].Laser%Infrared,2016,46(5):627-633.(in Chinese)胡燕燕,李东生,张诗桂.凸组合核函数的支持向量机高光谱图像分类[J].激光与红外,2016,46(5):627-633.
[11]ZHANG Yan,WU Ling.Transformer fault diagnosis based on C-SVC and cross-validation algorithm[J].Electric Power,2012,45(11):52-55.(in Chinese)张艳,吴玲.基于支持向量机和交叉验证的变压器故障诊断[J].中国电力,2012,45(11):52-55.
[12]CHEN Yuanyuan,WANG Zhibin,WANG Zhaoba.Feature selection of Infrared spectrum based on improved bat algorithm[J].Infrared and Laser Engineering,2014,43(8):2715-2721.(in Chinese)陈媛媛,王志斌,王召巴.基于改进蝙蝠算法的红外光谱特征选择[J].红外与激光工程,2014,43(8):2715-2721.
[13]CHEN Shijie,LIAN Ke,WANG Houjun.Method for analog circuit fault diagnosis based on GA optimized SVM[J].Journal of University of Electronic Science and Technology of China,2009,38(4):553-558.(in Chinese)陈世杰,连可,王厚军.遗传算法优化的SVM模拟电路故障诊断方法[J].电子科技大学学报,2009,38(4):553-558.
[14]GUO Tiantai,HONG Bo,PAN Zengrong,et al.Application of improved SVM in quantitative analysis of mine gas concentration[J].Infrared and Laser Engineering,2016,45(6):211-218.(in Chinese)郭天太,洪博,潘增荣,等.改进的SVM在矿井气体定量分析中的应用[J].红外与激光工程,2016,45(6):211-218.
[15]UAN Chongwen,CHENG Lizhi.Sample set shrinking strategy efficiently improving parameters seeking of support vector machines[J].Computer Applications,2007,27(2):363-365.(in Chinese)段崇雯,成礼智.有效提高SVM参数搜索效率的样本集缩减策略[J].计算机应用,2007,27(2):363-365.
[2]LI Mengxing.Research and implementation of power equipment fault infrared diagnosis system[J].Electric Power IT,2013,11(2):36-39.(in Chinese)李孟兴.电力设备故障红外诊断系统的研究与实现[J].电力信息化,2013,11(2):36-39.
[3]LIN Ying,GUO Zhihong,CHEN Yufeng.Convolutionalrecursive network based current transformer infrared fault image diagnosis[J].Power System Protection and Control,2015,43(16):87-94.(in Chinese)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,2015,43(16):87-94.
[4]ZOU Hui,HUANG Fuzhen.A novel intelligent fault diagnosis method for electrical equipment using infrared thermography[J].Infrared Physics&Technology,2015,73,29-35.
[5]LANG Cheng,JIN Guangxi,XU Dan,et al.Analysis of influence factors on relative temperature difference judgement method of electrical equipments[J].Infrared and Laser Engineering,2011,40(1):28-31,40.(in Chinese)郎成,金光熙,徐丹,等.电气设备相对温差判断法的影响因素分析[J].红外与激光工程,2011,40(1):28-31,40.
[6]JIN Lijun,AI Jianyong,DUAN Wei.Health condition assessment of catenary insulation based on multisource images[J].High Voltage Engineering,2016,42(11):3515-3523.(in Chinese)金立军,艾建勇,段伟.基于多光源图像的接触网外绝缘健康状态评估[J].高电压技术,2016,42(11):3515-3523.
[7]WANG Ju,WANG Zhaohui,LIU Yin.Fast algorithm of sparse signal decomposition based on PSO and LM[J].Laser%Infrared,2012,42(2):227-230.(in Chinese)王菊,王朝晖,刘银.基于PSO和LM的信号稀疏分解快速算法[J].激光与红外,2012,42(2):227-230.
[8]Niblack W.An introduction to digital image processing[M].Denmark:Strand berg Publishing Company Birkeroed,1986,115-116.
[9]YUAN Zhiwei,HUANG Shucai,XIONG Zhigang,et al.Infrared small target detection based on SVM posterior probability[J].Laser%Infrared,2016,46(6):766-771.(in Chinese)苑智玮,黄树彩,熊志刚,等.基于SVM后验概率的红外弱小目标检测[J].激光与红外,2016,46(6):766-771.
[10]HU Yanyan,LI Dongsheng,ZHANG Shigui.Classification of hyperspectral image by convex combination kernels function SVM[J].Laser%Infrared,2016,46(5):627-633.(in Chinese)胡燕燕,李东生,张诗桂.凸组合核函数的支持向量机高光谱图像分类[J].激光与红外,2016,46(5):627-633.
[11]ZHANG Yan,WU Ling.Transformer fault diagnosis based on C-SVC and cross-validation algorithm[J].Electric Power,2012,45(11):52-55.(in Chinese)张艳,吴玲.基于支持向量机和交叉验证的变压器故障诊断[J].中国电力,2012,45(11):52-55.
[12]CHEN Yuanyuan,WANG Zhibin,WANG Zhaoba.Feature selection of Infrared spectrum based on improved bat algorithm[J].Infrared and Laser Engineering,2014,43(8):2715-2721.(in Chinese)陈媛媛,王志斌,王召巴.基于改进蝙蝠算法的红外光谱特征选择[J].红外与激光工程,2014,43(8):2715-2721.
[13]CHEN Shijie,LIAN Ke,WANG Houjun.Method for analog circuit fault diagnosis based on GA optimized SVM[J].Journal of University of Electronic Science and Technology of China,2009,38(4):553-558.(in Chinese)陈世杰,连可,王厚军.遗传算法优化的SVM模拟电路故障诊断方法[J].电子科技大学学报,2009,38(4):553-558.
[14]GUO Tiantai,HONG Bo,PAN Zengrong,et al.Application of improved SVM in quantitative analysis of mine gas concentration[J].Infrared and Laser Engineering,2016,45(6):211-218.(in Chinese)郭天太,洪博,潘增荣,等.改进的SVM在矿井气体定量分析中的应用[J].红外与激光工程,2016,45(6):211-218.
[15]UAN Chongwen,CHENG Lizhi.Sample set shrinking strategy efficiently improving parameters seeking of support vector machines[J].Computer Applications,2007,27(2):363-365.(in Chinese)段崇雯,成礼智.有效提高SVM参数搜索效率的样本集缩减策略[J].计算机应用,2007,27(2):363-365.