电工技术学报  2021, Vol. 36 Issue (2): 388-396    DOI: 10.19595/j.cnki.1000-6753.tces.191654
高电压与放电 |
基于高光谱技术的复合绝缘子表面老化程度评估
张血琴, 张玉翠, 郭裕钧, 刘凯, 吴广宁
西南交通大学电气工程学院 成都 611756
Aging Degree Evaluation of Composite Insulator Based on Hyperspectral Technology
Zhang Xueqin, Zhang Yucui, Guo Yujun, Liu Kai, Wu Guangning
School of Electrical Engineering Southwest Jiaotong University Chengdu 611756 China
全文: PDF (93269 KB)   HTML
输出: BibTeX | EndNote (RIS)      
摘要 

针对现有绝缘老化检测尚无一种便捷快速的方法,该文提出一种基于高光谱技术的复合绝缘子表面老化程度的非接触、快速无损检测评估方法。首先,通过对不同老化程度样品进行傅里叶红外测试,分析样品表面的基团变化以及对憎水性的影响;其次,利用高光谱成像仪(900~1 700nm)获取老化样本光谱信息,结合傅里叶中红外光谱,确定老化样本基团变化和光谱信息的对应关系,从而对老化程度进行定性分析;最后,基于深度极限学习机建立绝缘子老化程度评估模型,并对60组待测数据进行预测,实现对绝缘子老化程度精确分级,分类准确率达96.67%,与BP神经网络和支持向量机模型对比,表明该文所用模型可兼备快速性和准确性,为实现外绝缘表面老化程度的在线检测提供了新思路。

服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
张血琴
张玉翠
郭裕钧
刘凯
吴广宁
关键词 复合绝缘子老化程度高光谱技术傅里叶红外测试深度极限学习机    
Abstract

There is no convenient and fast method for the insulation aging degree detection. In this paper, a non-contact and fast non-destructive testing method for surface aging of composite insulators based on hyperspectral technology is proposed. Firstly, Fourier-infrared tests were carried out on samples with different aging degrees, and the group changes on the surface of the samples and the influence on hydrophobicity were analyzed. Secondly, the hyperspectral imager (900~1 700nm) was used to obtain the spectral information of the aged samples. Combined with the Fourier mid-infrared spectroscopy, the relationship between the group content and the spectral information of the aged samples was determined, so as to qualitatively analyze the degree of aging. Finally, an aging degree evaluation model based on the deep extreme learning machine was established, and 60 groups of data to be tested were predicted to achieve accurate grading of the insulator aging degree. The classification accuracy rate was 96.67%. Compared with BP neural network model and support vector machine model, it is shown that the model used in this paper has both rapidity and accuracy, which provides a new idea for on-line detection of the aging degree of external insulation surface.

Key wordsComposite insulator    aging degree    hyperspectral technology    Fourier transform infrared    deep extreme learning machine   
收稿日期: 2019-11-27     
PACS: TM216  
基金资助:

国家自然科学基金项目(51907168)、四川省杰出青年科技人才项目(2020JDJQ0039)、中央高校基本科研业务费专项资金项目(2682017CX044,2682018CX19)和国家电网有限公司科技项目(521104190007)资助

通讯作者: 刘凯 男,1990年生,博士,助理研究员,研究方向为高电压绝缘技术和输电线路防灾减灾。E-mail: liukai@swjtu.edu.cn   
作者简介: 张血琴 女,1979年生,博士,副教授,博士生导师,研究方向为高电压绝缘与防护技术。E-mail: xq_zhang@home.swjtu.edu.cn
引用本文:   
张血琴, 张玉翠, 郭裕钧, 刘凯, 吴广宁. 基于高光谱技术的复合绝缘子表面老化程度评估[J]. 电工技术学报, 2021, 36(2): 388-396. Zhang Xueqin, Zhang Yucui, Guo Yujun, Liu Kai, Wu Guangning. Aging Degree Evaluation of Composite Insulator Based on Hyperspectral Technology. Transactions of China Electrotechnical Society, 2021, 36(2): 388-396.
链接本文:  
https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.191654          https://dgjsxb.ces-transaction.com/CN/Y2021/V36/I2/388