Application of Hierarchical Extreme Learning Machine in Prediction of Insulator Pollution Degree Using Hyperspectral Images

YANG Gang; LI Hengchao; TAN Bei; SHI Chaoqun; ZHANG Xueqin; GUO Yujun; WU Guangning

doi:10.3969/j.issn.0258-2724.20190093

Volume 55 Issue 3

Jun. 2020

Turn off MathJax

Article Contents

Abstract

References

Journal of Southwest Jiaotong University > 2020 > 55(3): 579-587.

YANG Gang, LI Hengchao, TAN Bei, SHI Chaoqun, ZHANG Xueqin, GUO Yujun, WU Guangning. Application of Hierarchical Extreme Learning Machine in Prediction of Insulator Pollution Degree Using Hyperspectral Images[J]. Journal of Southwest Jiaotong University, 2020, 55(3): 579-587. doi: 10.3969/j.issn.0258-2724.20190093

Citation:

YANG Gang, LI Hengchao, TAN Bei, SHI Chaoqun, ZHANG Xueqin, GUO Yujun, WU Guangning. Application of Hierarchical Extreme Learning Machine in Prediction of Insulator Pollution Degree Using Hyperspectral Images[J]. Journal of Southwest Jiaotong University, 2020, 55(3): 579-587. doi: 10.3969/j.issn.0258-2724.20190093

Citation:

YANG Gang, LI Hengchao, TAN Bei, SHI Chaoqun, ZHANG Xueqin, GUO Yujun, WU Guangning. Application of Hierarchical Extreme Learning Machine in Prediction of Insulator Pollution Degree Using Hyperspectral Images[J]. Journal of Southwest Jiaotong University, 2020, 55(3): 579-587. doi: 10.3969/j.issn.0258-2724.20190093

PDF( 1031 KB)

Application of Hierarchical Extreme Learning Machine in Prediction of Insulator Pollution Degree Using Hyperspectral Images

doi: 10.3969/j.issn.0258-2724.20190093

Received Date: 05 Mar 2019
Rev Recd Date: 25 Jun 2019

Available Online: 04 Sep 2019

Publish Date: 01 Jun 2020

Abstract

Abstract

Hyperspectral images possess merging properties of image and spectrum, wide spectral range, and high spectral resolution, which can finely reflect the material microscopic characteristics. To this end, hyperspectral imaging technology is introduced to research the insulator pollution degree in a non-contact way. Considering that extreme learning machine (ELM) has high learning efficiency and strong generalization ability, we construct a ELM with regularization constraint based insulator pollution degree prediction (ELM-IPDP) model. Besides, in order to further improve the prediction performance, hierarchical ELM (HELM) is utilized to learn the effective, abstract, and discriminative feature representations from the complex hyperspectral images, and the HELM based insulator pollution degree prediction (HELM-IPDP) model is proposed. Experiments are performed with different amounts of training data and numbers of neurons in hidden layers. Experimental results show that the prediction performance is basically improved with the increase of numbers of neurons in hidden layer and training samples. Specifically, when the proportion of training sample and test sample is 9∶1, root mean squared error (RMSE) and correlation coefficient of the ELM-IPDP model are 0.040 3 and 0.944 7, while those of the HELM-IPDP model are up to 0.022 3 and 0.972 0, respectively.
- insulator pollution degree,
- hyperspectral images,
- extreme learning machine,
- hierarchical etreme learning machine

FullText(HTML)

References(21)

References

汪万平,陈伟根,刘凡,等. 基于泄漏电流特征信息及概率神经网络的绝缘子污秽度预测模型[J]. 高压电器,2017,53(9): 198-203.

WANG Wanping, CHEN Weigen, LIU Fan, et al. Con-tamination level forecast model of insulators based on leakage current characteristics and probabilistic neural network[J]. High Voltage Apparatus, 2017, 53(9): 198-203.

王健,杨志超,葛乐,等. 基于BP神经网络和模糊逻辑的绝缘子污秽等级预测[J]. 南京工程学院学报(自科版),2013,11(4): 17-22.

WANG Jian, YANG Zhichao, GE Le, et al. Prediction of insulator pollution severity class based on BP neural network and fuzzy logic[J]. Journal of Nanjing Institute of Technology (Natural Science Edition), 2013, 11(4): 17-22.

文志科,孔晨华,闵绚,等. 高光谱遥感检测复合绝缘子运行状态技术研究[J]. 高压电器,2014,50(2): 75-79.

WEN Zhike, KONG Chenhua, MIN Xuan, et al. Working state detection of composite insulator by hyperspectral remote sensing[J]. High Voltage Apparatus, 2014, 50(2): 75-79.

黄锋华,张淑娟,杨一,等. 油桃外部缺陷的高光谱成像检测[J]. 农业机械学报,2015,46(11): 252-259. doi: 10.6041/j.issn.1000-1298.2015.11.034

HUANG Fenghua, ZHANG Shujuan, YANG Yi, et al. Application of hyperspectral imaging for detection of de-fective features in nectarine fruit[J]. Transactions of the Chinese Society of Agricultural Machine, 2015, 46(11): 252-259. doi: 10.6041/j.issn.1000-1298.2015.11.034

岳学军,全东平,洪添胜,等. 柑橘叶片叶绿素含量高光谱无损检测模型[J]. 农业工程学报,2015,31(1): 294-302. doi: 10.3969/j.issn.1002-6819.2015.01.039

YUE Xuejun, QUAN Dongping, HONG Tiansheng, et al. Non-destructive hyperspectral measurement model of chlorophyll content for citrus leaves[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(1): 294-302. doi: 10.3969/j.issn.1002-6819.2015.01.039

易秋香,黄敬峰,王秀珍. 玉米粗纤维含量高光谱估算模型研究[J]. 红外与毫米波学报,2007,26(5): 393-395. doi: 10.3321/j.issn:1001-9014.2007.05.018

YI Qiuxiang, HUANG Jingfeng, WANG Xiuzhen. Hyper-spectral estimation models for crude fibre concentration of corn[J]. Journal of Infrared and Millimeter Waves, 2007, 26(5): 393-395. doi: 10.3321/j.issn:1001-9014.2007.05.018

张初,刘飞,章海亮,等. 近地高光谱成像技术对黑豆品种无损鉴别[J]. 光谱学与光谱分析,2014,34(3): 746-750. doi: 10.3964/j.issn.1000-0593(2014)03-0746-05

ZHANG Chu, LIU Fei, ZHANG Hailiang, et al. Identifi-cation of varieties of black bean using ground based hyperspectral imaging[J]. Spectroscopy and Spectral Analysis, 2014, 34(3): 746-750. doi: 10.3964/j.issn.1000-0593(2014)03-0746-05

贾仕强,刘哲,李绍明,等. 基于高光谱图像技术的玉米杂交种纯度鉴定方法探索[J]. 光谱学与光谱分析,2013,33(10): 2847-2852. doi: 10.3964/j.issn.1000-0593(2013)10-2847-06

JIA Shiqiang, LIU Zhe, LI Shaoming, et al. Study on method of maize hybrid purity identification based on hyperspectral image technology[J]. Spectroscopy and Spectral Analysis, 2013, 33(10): 2847-2852. doi: 10.3964/j.issn.1000-0593(2013)10-2847-06

李庆利,薛永祺,王建宇,等. 高光谱成像系统在中医舌诊中的应用研究[J]. 红外与毫米波学报,2006,25(6): 465-468. doi: 10.3321/j.issn:1001-9014.2006.06.016

LI Qingli, XUE Yongqi, WANG Jianyu, et al. Application of hyperspectral imaging system in tongue analysis of tradi-tional chinese medicine[J]. Journal of Infrared and Millimeter Waves, 2006, 25(6): 465-468. doi: 10.3321/j.issn:1001-9014.2006.06.016

周霄,高峰,张爱武,等. VIS/NIR高光谱成像在中国云冈石窟砂岩风化状况分布研究中的进展[J]. 光谱学与光谱分析,2012,32(3): 790-794. doi: 10.3964/j.issn.1000-0593(2012)03-0790-05

ZHOU Xiao, GAO Feng, ZHANG Aiwu, et al. Advance in the study of the powdered weathering profile of sand-stone on china yungang grottoes based on VIS/NIR hyperspectral imaging[J]. Spectroscopy and Spectral Analysis, 2012, 32(3): 790-794. doi: 10.3964/j.issn.1000-0593(2012)03-0790-05

孙美君,柴勃隆,张冬,等. 基于近红外高光谱技术的敦煌莫高窟壁画起甲病害风险评估方法[J]. 文物保护与考古科学,2016,28(4): 1-8.

SUN Meijun, CHAI Bolong, ZHANG Dong, et al. As-sessing the degree of flaking of the murals in the Dunhuang Mogao Grottoes using near-infrared hyper-spectral imaging[J]. Sciences of Conservation and Ar-chaeology, 2016, 28(4): 1-8.

邵瑰玮,付晶,陈怡,等. 基于图谱特征的复合绝缘子老化神经网络评估方法[J]. 高电压技术,2014,40(3): 861-867.

SHAO Guiwei, FU Jing, CHEN Yi, et al. Aging assess-ment method of composite insulator using neural network based on image and spectra characteristics[J]. High Voltage Engineering, 2014, 40(3): 861-867.

向文祥,王星超,罗洋,等. 复合绝缘子粉化状态非接触检测技术研究[J]. 中国电业(技术版),2015(10): 3-5. doi: 10.3969/j.issn.1002-1140.2015.11.002

XIANG Wenxiang, WANG Xingchao, LUO Yang, et al. Research of composite insulator powder status non-contact detection technology[J]. China Electric Power (Technology Edition), 2015(10): 3-5. doi: 10.3969/j.issn.1002-1140.2015.11.002

孙志军,薛磊,许阳明,等. 深度学习研究综述[J]. 计算机应用研究,2012,29(8): 2806-2810. doi: 10.3969/j.issn.1001-3695.2012.08.002

SUN Zhijun, XUE Lei, XU Yangming, et al. Overview of deep learning[J]. Application Research of Computers, 2012, 29(8): 2806-2810. doi: 10.3969/j.issn.1001-3695.2012.08.002

王璨,武新慧,李恋卿,等. 卷积神经网络用于近红外光谱预测土壤含水率[J]. 光谱学与光谱分析,2018,38(1): 36-41.

WANG Can, WU Xinhui, LI Lianqiang, et al. Convolu-tional neural network application in prediction of soil moisture content[J]. Spectroscopy and Spectral Analysis, 2018, 38(1): 36-41.

HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine:theory and applications[J]. Neurocomputing, 2006, 70: 489-501. doi: 10.1016/j.neucom.2005.12.126

TANG J, DENG C, HUANG G B. Extreme learning machine for multilayer perceptron[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(4): 809-821. doi: 10.1109/TNNLS.2015.2424995

BECK A, TEBOULLE M A. Fast iterative shrink-age-thresholding algorithm for linear inverse problems[J]. Siam Journal on Imaging Sciences, 2009, 2(1): 183-202. doi: 10.1137/080716542

国家电网公司. 电力系统污区分级与外绝缘选择标准: Q/GDW 152—2006[S]. 北京: 中国电力出版社, 2006.

李佐胜,姚建刚,杨迎建,等. 绝缘子污秽等级红外热像检测的视角影响分析[J]. 高电压技术,2008,34(11): 2327-2331.

LI Zuosheng, YAO Jiangang, YANG Yingjian, et al. Analysis of visual angle influence on infrared thermal image detecting of insulator contamination grades[J]. High Voltage Engineering, 2008, 34(11): 2327-2331.

刘平,马美湖. 基于高光谱技术检测全蛋粉掺假的研究[J]. 光谱学与光谱分析,2018,38(1): 246-252.

LIU Ping, MA Meihu. Application of hyperspectral technology for detecting adulterated whole egg powder[J]. Spectroscopy and Spectral Analysis, 2018, 38(1): 246-252.

Relative Articles

[1]	LIU Hongen, HU Minsheng, HU Hailin. Reinforcement Learning Braking Control of Maglev Trains Based on Self-Learning of Hybrid Braking Features[J]. Journal of Southwest Jiaotong University, 2024, 59(4): 839-847. doi: 10.3969/j.issn.0258-2724.20230517
[2]	LIU Yuekai, GAO Hongli, GUO Liang, YOU Zhichao, LI Shichao. In-situ Roughness Evaluation of Milling Machined Surface Based on Lightweight Deep Convolutional Neural Network[J]. Journal of Southwest Jiaotong University, 2024, 59(1): 193-200. doi: 10.3969/j.issn.0258-2724.20210959
[3]	YAN Zhitao, MA Wenjun, ZHANG Pu, QIU Zhe. Optimization and Tensile Properties of Composite Insulator at High and Low Temperature[J]. Journal of Southwest Jiaotong University, 2021, 56(1): 56-61, 83. doi: 10.3969/j.issn.0258-2724.20181032
[4]	ZHANG Xueqin, GAO Runming, GUO Yujun, KANG Yongqiang, LI Yuansheng, WU Guangning. Hyperspectral-Based Corona Aging Evaluation for Composite Insulators[J]. Journal of Southwest Jiaotong University, 2020, 55(2): 442-449. doi: 10.3969/j.issn.0258-2724.20181062
[5]	LI Hengchao, TAN Bei, YANG Gang, SHI Chaoqun, ZHANG Xueqin, WU Guangning. Contamination Degree Prediction of Insulators Based on Hyperspectral Imaging Technology[J]. Journal of Southwest Jiaotong University, 2019, 54(4): 686-693. doi: 10.3969/j.issn.0258-2724.20180267
[6]	HUANG Zuowei, ZHANG Suifeng, ZHANG Taoxin. Optimization of Endmember Extraction in Mixed Pixel Unmixing in Hyperspectral Images[J]. Journal of Southwest Jiaotong University, 2018, 53(6): 1150-1156, 1172. doi: 10.3969/j.issn.0258-2724.2018.06.009
[7]	LIAO Yifan, HU Chuanliang, TANG Jun, YANG Fan, CHEN Zhihao, ZHOU Yu, LU Zhanhui. Analysis of Lightning Breakdown Characteristics of Contaminated Insulators in Parallel Clearance[J]. Journal of Southwest Jiaotong University, 2018, 53(6): 1117-1122. doi: 10.3969/j.issn.0258-2724.2018.06.004
[8]	MENG Guowang, ZHOU Jiamei, GAO Bo. Limit State Design Method of Railway Tunnel Portal Based on Reliability Theory[J]. Journal of Southwest Jiaotong University, 2016, 29(1): 30-35,49. doi: 10.3969/j.issn.0258-2724.2016.01.005
[9]	QIN Zhentao, YANG Wunian, YANG Ru, PAN Peifen, DENG Cong. Hyperspectral Image Classification Based on Structured Dictionary Learning[J]. Journal of Southwest Jiaotong University, 2015, 28(2): 336-341. doi: 10.3969/j.issn.0258-2724.2015.02.020
[10]	SUN Jixing, LUO Shucai, WU Guangning, GAO Guoqiang, YANG Kunsong, HU Xueyong. Pollution Distribution Characteristic of High-Speed Train Roof Insulator and Its Optimization Strategy[J]. Journal of Southwest Jiaotong University, 2014, 27(2): 343-350. doi: 10.3969/j.issn.0258-2724.2014.02.024
[11]	WANG Rui, LI Hengchao, YIN Zhongke. Hyperspectral Sparse Unmixing via Adaptive Overcomplete Dictionary Learning[J]. Journal of Southwest Jiaotong University, 2014, 27(4): 597-604. doi: 10.3969/j.issn.0258-2724.2014.04.006
[12]	SUN Jixing, WU Guangning, CHEN Weirong, GAO Guoqiang, CUI Yi, WANG Bo. Dynamic Simulation Analysis of Bar Insulator Pollution in Strong Wind[J]. Journal of Southwest Jiaotong University, 2012, 25(3): 413-419. doi: 10.3969/j.issn.0258-2724.2012.03.010
[13]	SHEN Yuanxia, WANG Guoyin. Data-Driven Q-Learning in Dynamic Environment[J]. Journal of Southwest Jiaotong University, 2009, 22(6): 877-881.
[14]	ZHANG Zeqiang, CHENG Wenming, ZHONG Bin, TANG Liansheng. Model and Simulation of Angel of Two-Degree of Freedom for Overhead[J]. Journal of Southwest Jiaotong University, 2006, 19(6): 696-699.
[15]	ZHOU Bin, LI Yu-mei, SHIGA Seiichi. Selection of the Learning Samples of Neural Networks for Internal-Combustion Engine Emission[J]. Journal of Southwest Jiaotong University, 2002, 15(6): 659-663.
[16]	YE Li-sheng, HE Feng-dao. The Learning of BP Neural Network Based on Evolutionary Programming[J]. Journal of Southwest Jiaotong University, 2001, 14(5): 545-548.
[17]	PENGXiong-zhi, LUO Shu-xue, ZHAO Shan-rui. Statistical Analysis of Pile Ultimate Bearing Capacity and Pile Reliability[J]. Journal of Southwest Jiaotong University, 2001, 14(3): 332-335.
[18]	He Zhengyou, Qian Qingquan. An Improved Wavelet Neural Network Structure and Its Learning Algorithm[J]. Journal of Southwest Jiaotong University, 1999, 12(5): 436-440.
[19]	HE Zheng-You, Jian-Qing-Quan. An Improved Wavelet Neural Network Structure and Its Learning Algorithm[J]. Journal of Southwest Jiaotong University, 1999, 12(5): 436-440.

Supplements(0)

Cited By

Cited by

Periodical cited type(2)

1.	顾黎强，钱朝军，孙明刚，张龙，施浩波. 激光诱导击穿光谱技术在绝缘子污秽快速定量检测中的应用. 绝缘材料. 2024(06): 96-101 .
2.	刘益岑，吴广宁，郭裕钧，刘毅杰，魏文赋，雷潇，李沛东. 招弧角电极直流电弧运动特性分析. 西南交通大学学报. 2023(01): 40-47 . 本站查看

Other cited types(4)

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Figures(6) / Tables(2)

Get Citation

PDF

XML

Article views(675) PDF downloads(17)