基于SAM-ED光谱匹配的绝缘子污秽类型检测方法研究

污闪是威胁电网安全可靠运行的重要原因之一, 污秽类型差异将直接影响闪络电压大小。因此, 及时掌握绝缘子污秽类型信息对预防污闪有重要作用。为此提出了一种基于SAM-ED光谱匹配的绝缘子污秽类型检测方法。采集不同污秽类型样本高光谱数据, 经黑白校正及多元散射校正(MSC)去除噪声等干扰因素;利用竞争自适应重加权采样法(CARS)对光谱数据进行特征选取, 分别在特征波段和全波段范围内通过SAM-ED光谱匹配法将测试组样本光谱与参考光谱进行匹配, 根据匹配结果对样本进行分类;实验结果表明: 相比于光谱角匹配法和最小距离法, SAM-ED光谱匹配法检测效果更好;基于全波长数据进行SAM-ED光谱匹配准确率可达95%, 基于特征波长数据进行SAM-ED光谱匹配准确率可达98.33%。

Abstract

Fouling flash is one of the important reasons that threaten the safe and stable operation of power system, and the difference of fouling type will directly affect the size of flashover voltage. Therefore, timely information on insulator fouling type plays an important role in preventing fouling. To this end, a SAM-ED spectral matching based insulator fouling type detection method is proposed. The hyperspectral data of different fouling type samples are collected, and the noise and other interference factors are removed by black and white correction and multiple scattering correction (MSC); the spectral data are selected by competitive adaptive reweighted sampling (CARS), and the samples are matched with the reference spectra by SAM-ED spectral matching method in the characteristic band and full band range, respectively, and the samples are classified according to the matching results. The experimental results show that the SAM-ED spectral matching method is more effective than the spectral angle matching method and the minimum distance method, and the accuracy of SAM-ED spectral matching based on the full wavelength data can reach 95%, and the accuracy of SAM-ED spectral matching based on the characteristic wavelength data can reach 98.33%.<通讯作者>刘益岑(1986-), 男, 硕士, 高级工程师, 研究方向为电网防灾减灾及在线监测等

参考文献

[1] 关志成, 王绍武, 梁曦东, 等. 我国电力系统绝缘子污闪事故及其对策［J］. 高电压技术, 2000, 26(6): 37-39.(Guan Zhicheng, Wang Shaowu, Liang Xidong, et al. Application and Prospect of Polymeric Outdoor Insulation in China［J］. High Voltage Engineering, 2000, 26(6): 37-39.

[2] 宿志一, 李庆峰. 我国电网防污闪措施的回顾和总结［J］. 电网技术, 2010, 34(12): 124-130.(Su Zhiyi, Li Qingfeng. Historical Review and Summary on Measures Against Pollution Flashover Occurred in Power Grids in China［J］. Power System Technology, 2010, 34(12): 124-130.

[3] R. Matsuoka, K. Kondo. Influence of non-soluble contaminants on the flashover voltages of artificially contaminated insulators［J］. IEEE Transactions on Power Delivery, 1996, 11(1): 420-430.

[4] R. Sundararajan, R. S. Gorur. Role of non-soluble contaminants on the flashover voltage of porcelain insulators［J］. IEEE Transactions on Dielectrics and Electrical Insulation, 1996, 3(1): 113-118.

[5] 蒋兴良, 李鑫, 张东东, 等. 可溶性污秽成分对绝缘子交流闪络特性的影响［J］. 高电压技术, 2015, 41(6): 1915-1920.(Jiang Xingliang, Li Xin, Zhang Dongdong, et al. Effect of Soluble Contamination on the AC Flashover Performance of Insulator［J］. High Voltage Engineering, 2015, 41(6): 1915-1920.

[6] 刘桂英. 原子吸收分光光度法测定水中重金属的探讨［J］. 河北水利, 2021(09): 23+48.(Liu Guiying. Exploration of atomic absorption spectrophotometry for the determination of heavy metals in water［J］.Hebei Water Resources, 2021(09): 23+48.

[7] 李馨馨. 电感耦合等离子体原子发射光谱法测定石煤矿中钒镁锌铁铜锰［J］. 化学工程与装备, 2021(01): 227-228.(Li Xinxin. Determination of vanadium, magnesium, zinc, iron, copper and manganese in stone coal mines by inductively coupled plasma atomic emission spectrometry［J］. Chemical Engineering & Equipment, 2021(01): 227-228.

[8] 肖章. 基于图谱特征的绝缘子自然污秽检测方法研究［D］. 成都: 西南交通大学, 2020.(Xiao Zhang. Research on natural fouling detection method for insulators based on mapping features ［D］.Chengdu: Southwest Jiaotong University, 2020.

[9] W. Cai, H. Deng, G. Zhou, et al. Online measurement of equivalent salt deposit density by using optical technology［J］. IEEE Transactions on Dielectrics and Electrical Insulation, 2013, 20(2): 409-413.

[10] 陈宏达. 高光谱遥感图像的降维与分类研究［D］. 上海: 复旦大学, 2013.(Chen Hongda. Study on dimension reduction and classification of hyperspectral remote sensing images［D］. Shanghai:Fudan University, 2013.

[11] 张帅堂, 王紫烟, 邹修国, 等.基于高光谱图像和遗传优化神经网络的茶叶病斑识别［J］. 农业工程学报, 2017, 33(22): 200-207.(Zhang Shuaitang, Wang Ziyan, Zou Xuguo, et al. Tea spot recognition based on hyperspectral image and genetic optimization neural network ［J］. Journal of agricultural engineering, 2017, 33 (22): 200-207.

[12] 王晓珂, 刘婷婷, 许桂玲, 等. 基于冠层高光谱遥感的杂交水稻植被指数氮素营养诊断模型［J/OL］. 中国稻米, 2021(03).(Wang Xiaoke, Liu Tingting, Xu Guiling, et al. Nitrogen nutrition diagnosis model of hybrid rice vegetation index based on Canopy Hyperspectral Remote Sensing ［J/OL］.China rice, 2021 (03).

[13] 段瑞鲁, 刘廷玺, 张圣微, 等. 科尔沁沙地典型沙丘植被光谱特征数据的匹配［J］. 干旱区研究, 2014, 31(4): 750-755.(Duan Ruilu, Liu Tingxi, Zhang Shenwei, et al. Matching of Spectral Data of Typical Vegetation on Dune in the Horqin Sandy Land［J］. Arid Zone Research, 2014, 31(4): 750-755.

[14] 赵冬娥, 吴瑞, 赵宝国, 等. 高光谱成像的垃圾分类识别研究［J］. 光谱学与光谱分析, 2019, 39(3): 921-926.(Zhao Dong-e, Wu Rui, Zhao Baoguo, et al. Research on Garbage Classification and Recognition Based on Hyperspectral Imaging Technology［J］. Spectroscopy and Spectral Analysis, 2019, 39(3): 921-926.

[15] 徐隆鑫, 孙永华, 何仕俊, 等. 基于不同光谱匹配算法的无人机高光谱遥感影像建筑垃圾分类研究［J］.首都师范大学学报, 2021, 42(06): 50-56.(Xu Longxin, Sun Yonghua, He Shijun, et al. Study on construction waste classification of unmanned aerialvehicle hyperspectral remote sensing images based on different spectral matching algorithms［J］. Journal of Capital Normal University, 2021, 42(06): 50-56.

[16] 孔祥兵, 舒宁, 陶建斌, 等. 一种基于多特征融合的新型光谱相似性测度［J］. 光谱学与光谱分析, 2011(8): 2166-2170.(Kong Xiangbing, Shu Ning, Tao Jianbin, et al. A new spectral similarity measure based on multiple features integration［J］. Spectroscopy and Spectral Analysis, 2011(8): 2166-2170.

[17] IEC TS 60815: 2008. Selection and dimensioning of high-voltage insulators intended for use in polluted conditions-Part 2: Ceramic and glass insulators for a.c. systems［S］. IEC, 2008.

[18] 中国国家标准化管理委员会. GB/T 22707-2008直流系统用高压绝缘子的人工污秽试验［S］. 北京: 中国标准出版社, 2008.(Standardization Administration of the People’s Republic of China. Artificial pollution tests on high—voltage insulators to be used on d. c. systems: GB/T 22707—2008［S］. Beijing, China: Standard Press of China, 2008.

[19] Kruse F A, Lefkoff A B, Boardman J W, et al. The spectral image processing system (SIPS)-Interactive visualization andanalysis of imaging spectrometer data［J］. Remote Sensing Environment, 1993, 44(2): 145-163.

[20] Fenstermaker L K, Miller J R. Identification of fluvially redistribu-ted mill tailings using high spectral resolution aircraft data［J］. Photogram-metric Engineering and Remote Sensing, 1994, 60 (8): 989-995.

刘益岑, 刘曦, 杨琳, 林柯心, 郭裕钧, 张血琴. 基于SAM-ED光谱匹配的绝缘子污秽类型检测方法研究[J]. 光散射学报, 2023, 35(3): 296. LIU Yicen, LIU Xi, YANG Lin, LIN Kexin, GUO Yujun, ZHANG Xueqin. Study of insulator pollution type detection method based on SAM-ED spectral matching[J]. The Journal of Light Scattering, 2023, 35(3): 296.

基于SAM-ED光谱匹配的绝缘子污秽类型检测方法研究

关于本站 Cookie 的使用提示

全站搜索

基于SAM-ED光谱匹配的绝缘子污秽类型检测方法研究

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索