Detection Method of Insulator Contamination Grades Based on Hyperspectral Technique

被引：0

作者：

Qiu Y. ^{[1
]}

Zhang X. ^{[1
]}

Guo Y. ^{[1
]}

Shi C. ^{[1
]}

Zhang X. ^{[1
]}

Wu G. ^{[1
]}

机构：

[1] School of Electrical Engineering, Southwest Jiaotong University, Chengdu

来源：

Gaodianya Jishu/High Voltage Engineering | 2019年 / 45卷 / 11期

基金：

中国国家自然科学基金;

关键词：

Contamination grade; Hyperspectral technique; Insulator; Multiplicative scatter correction; Support vector machine;

D O I：

10.13336/j.1003-6520.hve.20190215003

中图分类号：

学科分类号：

摘要：

The on-line detection of insulator contamination grades of transmission lines is of great importance to the prevention and control of flashover. We proposed a non-contact detection method of insulator contamination grades based on hyperspectral technique. Firstly, hyperspectral images of the samples with different contamination grades were obtained by hyper-spectrometer. Secondly, after original hyperspectral images were corrected by black-and-white correction and multiplicative scatter correction, hyperspectral curves from the region of interest(ROI) of corrected images were obtained. Finally, a multi-classification model of support vector machine was built to realize the contamination grades classification of test samples. The results show that the absorption peak, the position of reflection peak, amplitude and the change trend of the hyperspectral curve obviously change with different kinds of contamination on the surface of silicone rubber, while only the amplitude obviously changes with the same kind of contamination on the surface of silicone rubber; and the full-band data model can accurately and rapidly classify the contamination grades, with the contamination grades classification accuracy of NaCl and CaSO4 reaching 97.5%; and finally the support vector machine model based on the hyperspectral curve data of the artificial contamination samples can classify the surface of umbrellas with different contamination grades of the insulator with the classification accuracy of 80%. Therefore, this method can be applied to the non-contact detection of insulator contamination grades, which provides a new idea for the detection of insulator contamination grades. © 2019, High Voltage Engineering Editorial Department of CEPRI. All right reserved.

引用

页码：3587 / 3594

页数：7

共 25 条

[1] Gao S., Zhang B., Cui Y., Et al., AC pollution flashover performance and anti-pollution precaution of porcelain long rod insulator, High Voltage Engineering, 44, 6, pp. 1891-1897, (2018)
[2] Sui B., Sun J., Wu G., Et al., Analysis on the influence of intermittent high speed train wind on supporting insulator pollution flashover, Insulators and Surge Arresters, 2, (2012)
[3] Su Z., Li Q., Historical review and summary on measures against pollution flashover occurred in power grids in China, Power System Technology, 34, 12, pp. 124-130, (2010)
[4] Jiang X., Zhao S., Bi M., Et al., Research on flashover performance and leakage current performance of polluted insulators, Proceedings of the CSEE, 33, 31, (2013)
[5] Jiang X., Dong H., Wang L., Et al., New method to describe contamination degree of insulators by effective equivalent salt deposit density, High Voltage Engineering, 43, 12, pp. 3869-3875, (2017)
[6] Wang L., Zhong C., Insulator leakage current and its analytical method, Electric Switchgear, 49, 1, pp. 9-11, (2011)
[7] Liu G., Hu Q., Chen X., Feasibility analysis of monitoring the insulator surface contamination based on surface conductivity, High Voltage Engineering, 38, 6, pp. 1321-1326, (2012)
[8] Zhao Q., Li H., Han Z., Et al., A summary of insulator pollution detection method, Electric Switchgear, 50, 4, pp. 96-98, (2012)
[9] Jin L., Tian Z., Gao K., Et al., Discrimination of insulator contamination grades using information fusion of infrared and visible images, Proceedings of the CSEE, 36, 13, (2016)
[10] He H., Yao J., Jiang Z., Et al., Contamination grades recognition of insulators under different humidity using infrared image features and RBPNN, Proceedings of the CSEE, 26, 8, pp. 117-123, (2006)

← 1 2 3 →