绝缘子污秽高光谱检测的特征波长筛选方法比较

doi:10.3964/j.issn.1000-0593(2025)07-1992-07

Abstract
References
Related Citation (15)

Download: PDF (6447 KB)
Export: BibTeX | EndNote (RIS)

Abstract The surface pollution will affect the insulator's insulation ability and harm the power system. The current detection method requires power outage sampling, which is tedious and time-consuming. Hyperspectral analysis can realize non-contact non-power outage detection and has good potential for application in insulator pollution detection. In order to reduce the data processing amount of insulator surface pollution hyperspectral detection and improve the accuracy of insulator hyperspectral data classification and identification, according to the current manual test sample preparation standards, Three artificial pollution samples of insulators with salt density of 0.22 milligrams per square centimeter, ash density of 0.1 milligrams per square centimeter and salt density of 0.3 milligrams per square centimeter and ash density of 0.1 milligrams per square centimeter were made.Hyperspectral sampling was carried out on insulator samples of different pollution levels. 15 regions were selected on each sample to extract regional spectral data, and a total of 90 groups of spectral data were obtained. 63 training set samples and 27 test set samples were selected. Competitive adaptive reweighted sampling (CARS) Algorithm, Successive Projections Algorithm (SPA and Uninformation Variables Elimination (UVE) were used to screen the characteristic wavelengths of insulator hyperspectral data and build a support vector machine classification model. Multivariate scattering correction (MSC), standard normal variation (SNV), first order derivative, deconvolution, moving average filtering, baseline correction, normalization, and wavelet transform were used to preprocess the spectral data. The classification experiments were carried out using the tested sample data, and the classification effects of different pretreatment methods and feature wavelength screening methods were compared. The experimental results show that the pre-treated data can improve classification recognition accuracy, and the pre-treated data's recognition accuracy can reach a low of 51.85% and a high of 96%, higher than the 40.74% in the untreated condition. Feature screening can reduce the dimensionality of the original spectral data, and SPA is the most efficient of the three methods, with an average screening rate of 3.56%. After screening, the accuracy of classification recognition can be improved, and the accuracy of classification recognition of original data can be increased from 40.74% to 74.07% after CARS screening. Pretreatment of spectral data combined with feature wavelength screening can greatly improve the classification and identification accuracy of dirty insulators. The classification and identification accuracy of MSC-CARS, SNV-CARS, MSC-UVE, and normalized UVE can reach 100% after combined processing. The average classification accuracy of CARS, SPA, and UVE combined with 8 preprocessed test sets was 87.05%, 86.25%, and 83.47%, respectively, indicating that the combination of preprocessing and feature screening plays an important role in improving data quality and model performance. These preprocessing and characteristic wavelength screening methods of spectral data can effectively reduce the original data dimension and simplify the model complexity, which can play an important role in improving the accuracy of insulator pollution classification and recognition.

Key words：Insulator pollution; Spectral detection; Pretreatment; Characteristic wavelength; Classification recognition

Received: 2024-10-01 Accepted: 2025-02-25

ZTFLH:

TH841

Corresponding Authors: CHENG Hong-bo E-mail: hbcheng@ecjtu.edu.cn

Cite this article:

LI Jia-jia,WANG Xiang-feng,HUANG Fei-lin, et al. Comparison of Wavelength Screening Methods for Insulator Pollution Hyperspectral Detection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(07): 1992-1998.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2025)07-1992-07 OR https://www.gpxygpfx.com/EN/Y2025/V45/I07/1992

[1] SU Zhi-yi, LI Qing-feng（宿志一，李庆峰）. Power System Technology （电网技术），2010，34(12)：124.
[2] JIANG Xing-liang, ZHAO Shi-hua, BI Mao-qiang，et al（蒋兴良，赵世华，毕茂强, 等）. Proceedings of the CSEE（中国电机工程学报），2013，33(31)：220.
[3] ZHAO Quan-xiang, LI Hong-yan, HAN Zhen，et al（赵全香，李红艳，韩振，等）. Electric Switchgear（电气开关），2012，50(4)：96.
[4] JIANG Xin-jian, DONG Hong-chuan, WANG Li-ming, et al（姜新建，董弘川，王黎明，等）. High Voltage Engineering（高电压技术），2017，43(12)：3869.
[5] LIU Gang, HU Qian-nan, CHEN Xi-yang（刘刚，胡倩楠，陈锡阳）. High Voltage Engineering（高电压技术），2012，38(6)：1321.
[6] HUANG Xin-bo, WEI Xu, LI Min, et al（黄新波，魏旭，李敏，等）. High Voltage Engineering（高电压技术）, 2014，40(2): 374.
[7] PENG Zi-jian, ZHANG Ye, FU Qiang, et al. （彭子健，张也，付强，等）. Power System Technology（电网技术），2017，41(11): 3705.
[8] LIU Yun-peng, JI Xin-xin, PEI Shao-tong, et al（刘云鹏，纪欣欣，裴少通，等）. High Voltage Engineering（高电压技术）, 2018，44(10): 3352.
[9] HE Hong-ying, YAO Jian-gang, JIANG Zheng-long, et al（何洪英，姚建刚，蒋正龙，等）. Proceedings of the CSEE（中国电机工程学报），2006，(8): 117.
[10] JIN Li-jun, ZHANG Da, DUAN Shao-hui, et al（金立军，张达，段绍辉，等）. Transactions of China Electrotechnical Society（电工技术学报），2014，29(8): 309.
[11] ZHANG Xue-qin, ZHANG Yu-cui, GUO Yu-jun, et al（张血琴，张玉翠，郭裕钧，等）. Transactions of China Electrotechnical Society（电工技术学报）, 2021，36(2): 388.
[12] WEN Zhi-ke, KONG Chen-hua, MIN Xuan, et al（文志科，孔晨华，闵绚，等）. High Voltage Apparatus（高压电器），2014，50(2): 75.
[13] CHEN Zhe, GAO Hong-min, SHEN Shao-hong, et al（陈哲，高红民，申邵洪，等）. Feature Extraction and Classification of Hyperspectral Remote Sensing Images(高光谱遥感图像特征提取与分类). Beijing: Posts & Telecom Press（北京：人民邮电出版社），2019, 10: 200.
[14] General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China（中华人民共和国国家质量监督检验检疫总局）. GB/T 22707—2008 Artificial Pollution Tests on High-Voltage Insulators to be Used on d.c. Systems(GB/T 22707—2008直流系统用高压绝缘子的人工污秽试验)，2008.