绝缘子污秽等级的高光谱特征优化识别技术研究
作者:
中图分类号:

TM855

基金项目:

中国南方电网有限责任公司科技项目“高压设备绝缘状态关联光谱检测与诊断技术研究”(YNKJXM20180015)


Optimization and identification technology of hyperspectral spectral features of insulator pollution levels
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [25]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    为解决传统污秽检测方法对输电线路绝缘子污闪防治的局限性,通常采用非接触式、高分辨率的高光谱技术研究污秽在线检测技术。为有效提取反应污秽度的光谱特征,削弱冗余与干扰信息的影响,文中提出一种基于小波包能量谱特征优化的绝缘子污秽等级识别技术。首先,对不同污秽等级的绝缘子样品的光谱图像进行背景分割,提取均匀覆污区像素点的光谱均值曲线;其次,对不同图像的光强均匀度差异、环境噪声进行预处理,并通过对数变换提升不同污秽等级间的可区分性;再次,对预处理后的光谱曲线进行小波包能量谱特征提取;最后,基于所提特征建立基于支持向量机(SVM)的污秽等级识别模型。实验结果表明,相比于采用全波段数据或主成分分析(PCA)特征数据作为输入,基于小波包能量谱特征建立的SVM污秽等级识别模型对样品识别准确率更高,可以达到99.8%。

    Abstract:

    To solve the problem of traditional pollution detection methods on the prevention and control of pollution flashover of transmission line insulators,the non-contact and high-resolution hyperspectral technology is used to study the on-line pollution detection technology. At the same time,an insulator pollution level identification technology based on wavelet packet energy spectrum feature optimization is proposed to effectively extract the spectral features reflecting the pollution degree and weaken the influence of redundancy and interference information. Firstly,the spectral images of insulator samples with different pollution levels are segmented to extract the spectral mean curve of pixels in uniform pollution area. Secondly,the difference of light intensity uniformity and environmental noise of different images are preprocessed,and the differentiability among different pollution levels is improved by logarithmic transformation. Thirdly,the feature extraction of wavelet packet energy spectrum is performed on the preprocessed spectral lines. Finally,a pollution level recognition model based on the proposed features and support vector machines (SVM) is established. The experimental results show that the SVM pollution level recognition model based on wavelet energy spectrum features achieves 99.8%,and it has higher recognition accuracy than full band data or principal component analysis (PCA) feature data does.

    参考文献
    [1] 徐森,仵超,李少华,等.雾霾期间绝缘子的积污特性研究[J].中国电机工程学报,2017,37(7):2142-2151. XU Sen,WU Chao,LI Shaohua,et al. Research on pollution accumulation characteristics of insulators during fog-haze days[J]. Proceedings of the CSEE,2017,37(7):2142-2151.
    [2] 姚磊.北京地区输电线路绝缘子污秽监测分析与防污措施建议[J].电气技术与经济,2019(3):38-40. YAO Lei. Pollution monitoring analysis of transmission line insulators in Beijing and suggestions on anti pollution measures[J]. Electrical Equipment and Economy,2019(3):38-40.
    [3] 刘阳,徐硕,李铁军.架空输电线路运行的影响因素与运维策略[J].电气时代,2018(12):49-50. LIU Yang,XU Shuo,LI Tiejun. Influence factors and operation and maintenance strategy of overhead transmission line operation[J]. Electric Age,2018(12):49-50.
    [4] 邵仕超,毕晓甜,李明哲,等.特殊工业粉尘地区复合绝缘子自然积污特性研究[J].电力工程技术,2021,40(1):138-141,154. SHAO Shichao,BI Xiaotian,LI Mingzhe,et al. Natural fouling characteristics of composite insulators in special industrial dust areas[J]. Electric Power Engineering Technology,2021,40(1):138-141,154.
    [5] 蒋子丹,蒋兴良,蒋晏如,等.湖南地区输电线路悬式绝缘子自然积污规律[J].中南大学学报(自然科学版),2018,49(7):1683-1690. JIANG Zidan,JIANG Xingliang,JIANG Yanru,et al. Natural contamination characteristics of suspension insulator in Hunan province[J]. Journal of Central South University (Science and Technology),2018,49(7):1683-1690.
    [6] 王林,王洪光,景凤仁,等.一种悬垂绝缘子带电清扫机器人机构设计[J].机械设计与制造,2019(1):232-235. WANG Lin,WANG Hongguang,JING Fengren,et al. Mechanism design of a live-line cleaning robot for suspension insulator strings[J]. Machinery Design&Manufacture,2019(1):232-235.
    [7] 张慧莹.输电线路绝缘子识别与故障状态检测技术研究[D].西安:西安工程大学,2018. ZHANG Huiying. Research on insulator identification and fault state detection technology of transmission line[D]. Xi'an:Xi'an Polytechnic University,2018.
    [8] 芦山,王希林,刘星廷,等.基于激光诱导击穿光谱的绝缘子污秽自由定标定量分析[J].智慧电力,2021,49(10):90-96. LU Shan,WANG Xilin,LIU Xingting,et al. Calibration-free quantitative analysis of insulator pollution via laser-induced breakdown spectroscopy[J]. Smart Power,2021,49(10):90-96.
    [9] 张若兵,董广奇,刘辉,等.特殊污秽环境下±660 kV直流线路铵盐积污特性[J].高电压技术,2019,45(2):463-469. ZHANG Ruobing,DONG Guangqi,LIU Hui,et al. Ammonium contamination deposited characteristics of±660 kV DC transmission lines in special pollution environment[J]. High Voltage Engineering,2019,45(2):463-469.
    [10] 蒋兴良,刘又超,刘要峰,等.可溶物对绝缘子有效污秽度的影响[J].高电压技术,2018,44(5):1483-1489. JIANG Xingliang,LIU Youchao,LIU Yaofeng,et al. Effect of soluble contaminants on the effective pollution degree of insulators[J]. High Voltage Engineering,2018,44(5):1483-1489.
    [11] 王胜辉,牛雷雷,李浩,等.基于放电紫外成像特征的污秽线路盘形绝缘子绝缘状态评估[J].高压电器,2019,55(2):201-207. WANG Shenghui,NIU Leilei,LI Hao,et al. Insulation condition evaluation of contaminated disc insulator for transmission lines based on the characteristic of discharge UV imaging characteristics[J]. High Voltage Apparatus,2019,55(2):201-207.
    [12] 姜洪亮.红外精确测温在检测开关设备污秽中的应用[J].江西电力,2015,39(1):70-71. JIANG Hongliang. Application of infrared accurate temperature measurement in detecting contamination of switchgear[J]. Jiangxi Electric Power,2015,39(1):70-71.
    [13] 裴少通.基于红外紫外成像检测技术的绝缘子运行状态分析与评估[D].北京:华北电力大学,2019. PEI Shaotong. Analysis and evaluation of insulator operation status based on infrared and ultraviolet imaging detection technology[D]. Beijing:North China Electric Power University, 2019.
    [14] 黄习飞.红外图像在架空线路故障检测中的应用研究[D].淮南:安徽理工大学,2018. HUANG Xifei. Application of infrared image in fault detection of overhead lines[D]. Huainan:Anhui University of Science&Technology,2018.
    [15] 戈灏,张曼曼,吴广宁,等.基于紫外脉冲法的陶瓷绝缘子污秽状态检测及评估方法[J].广东电力,2018,31(8):91-97. GE Hao,ZHANG Manman,WU Guangning,et al. Detection and evaluation method for contamination of ceramic insulator based on UV pulse method[J]. Guangdong Electric Power,2018,31(8):91-97.
    [16] 余海,姜吉顺,史晓航,等.基于红外测温的复合绝缘子老化程度量化评估方法[J/OL].电测与仪表:1-6[2022-01-27]. http://kns.cnki.net/kcms/detail/23.1202.TH.20210114.1423.002.html. YU Hai,JIANG Jishun,SHI Xiaohang,et al. Quantitative evaluation method for aging of composite insulators based on infrared temperature measurement[J/OL]. Electrical Measurement&Instrumentation:1-6[2022-01-27]. http://kns.cnki.net/kcms/detail/23.1202.TH.20210114.1423.002.html.
    [17] 杨晓玉,刘贵珊,丁佳兴,等.灵武长枣VC含量的高光谱快速检测研究[J].光谱学与光谱分析,2019,39(1):230-234. YANG Xiaoyu,LIU Guishan,DING Jiaxing,et al. A rapid evaluation of VC content on Lingwu long jujube using hyperspectral technique[J]. Spectroscopy and Spectral Analysis,2019,39(1):230-234.
    [18] 邱彦,张血琴,郭裕钧,等.基于高光谱技术的绝缘子污秽等级检测方法[J].高电压技术,2019,45(11):3587-3594. QIU Yan,ZHANG Xueqin,GUO Yujun,et al. Detection method of insulator contamination grades based on hyperspectral technique[J]. High Voltage Engineering,2019,45(11):3587-3594.
    [19] 张晓青.基于高光谱技术的绝缘子表面附灰密度检测方法研究[D].成都:西南交通大学,2019. ZHANG Xiaoqing. Research on the detection method of NSDD on insulator surface based on hyperspectral technology[D]. Chengdu:Southwest Jiaotong University,2019.
    [20] 刘志刚.支撑向量机在光谱遥感影像分类中的若干问题研究[D].武汉:武汉大学,2004. LIU Zhigang. Key problems of applying support vector machines to the classification of spectral remote sensing imagery[D]. Wuhan:Wuhan University,2004.
    [21] 张汉奎,黄波,俞乐. SVM-RFE高光谱数据波段选择中核函数的研究[J].遥感技术与应用,2013,28(5):747-752. ZHANG Hankui,HUANG Bo,YU Le. Kernel function in SVM-RFE based hperspectral data band selection[J]. Remote Sensing Technology and Application,2013,28(5):747-752.
    [22] 杨哲海,李之歆,韩建峰,等.高光谱中的Hughes现象与低通滤波器的运用[J].测绘学院学报,2004,21(4):253-255,258. YANG Zhehai,LI Zhixin,HAN Jianfeng,et al. The Hughes phenomenon in hyperspectral analysis and the application of the lowpass filter[J]. Journal of Institute of Surveying and Mapping,2004,21(4):253-255,258.
    [23] 第五鹏瑶,卞希慧,王姿方,等.光谱预处理方法选择研究[J].光谱学与光谱分析,2019,39(9):2800-2806. DIWU Pengyao,BIAN Xihui,WANG Zifang,et al. Study on the selection of spectral preprocessing methods[J]. Spectroscopy and Spectral Analysis,2019,39(9):2800-2806.
    [24] 郭伟超,赵怀山,李成,等.基于小波包能量谱与主成分分析的轴承故障特征增强诊断方法[J].兵工学报,2019,40(11):2370-2377. GUO Weichao,ZHAO Huaishan,LI Cheng,et al. Fault feature enhancement method for rolling bearing fault diagnosis based on wavelet packet energy spectrum and principal component analysis[J]. Acta ArmamentarⅡ,2019,40(11):2370-2377.
    [25] 房立清,吕岩,张建伟,等.小波包能量谱和RVM在自动机故障诊断中的应用[J].机械设计与制造,2018(10):74-77. FANG Liqing,LYU Yan,ZHANG Jianwei,et al. Application of wavelet packet energy spectrum and RVM in automaton fault diagnosis[J]. Machinery Design&Manufacture,2018(10):74-77.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

沈龙,钱国超,彭兆裕,李谦慧,杨坤,马御棠.绝缘子污秽等级的高光谱特征优化识别技术研究[J].电力工程技术,2022,41(2):156-162,208

复制
分享
文章指标
  • 点击次数:1036
  • 下载次数: 1303
  • HTML阅读次数: 2147
  • 引用次数: 0
历史
  • 收稿日期:2021-11-11
  • 最后修改日期:2022-01-27
  • 录用日期:2021-06-07
  • 在线发布日期: 2022-03-24
  • 出版日期: 2022-03-28
文章二维码