Detection of pollution components on the surface of transmission line insulators based on hyperspectral technology
编号:454 访问权限:仅限参会人 更新:2022-09-21 10:28:57 浏览:153次 张贴报告

报告开始:暂无开始时间(Asia/Shanghai)

报告时间:暂无持续时间

所在会场:[暂无会议] [暂无会议段]

演示文件

提示:该报告下的文件权限为仅限参会人,您尚未登录,暂时无法查看。

摘要
Insulators of transmission lines are easy to accumulate pollution on their surfaces due to long-term exposure to the atmospheric environment, and the pollution flashover accidents it causes seriously endanger the safety of power system. And the flashover voltage is closely related to the pollution components on insulators’ surface. This paper proposes to use hyperspectral imaging technology to establish the identification model of pollution components, which makes up for the shortage of traditional insulator detection methods. Firstly, contaminated insulator samples with different pollution components were prepared in the laboratory, their hyperspectral spectral lines were obtained for comparison, then the differences between the spectral lines of the samples with different pollution components were analyzed. At last, a random forest model was built to realize the identification and classification of the samples with different pollution components, and the accuracy of the model was more than 95%. The results show that the method for detection of insulator surface pollution component based on hyperspectral imaging technology is feasible and provides a new idea for the online detection of insulators of transmission lines.
关键词
Insulator pollution flashover,Pollution components,Hyperspectral imaging techonology,Random forest
报告人
GUO Yujun
Southwest Jiaotong University

稿件作者
XIAO Rong State Grid Shanghai Electric Power Research Institute
MAO Weiyun State Grid Shanghai Electric Power Research Institute
LU Bingbing State Grid Shanghai Electric Power Research Institute
ZHA Hongyuan Southwest Jiaotong University
GUO Yujun Southwest Jiaotong University
发表评论
验证码 看不清楚,更换一张
全部评论
重要日期
  • 会议日期

    09月25日

    2022

    09月29日

    2022

  • 08月15日 2022

    提前注册日期

  • 09月10日 2022

    报告提交截止日期

  • 11月10日 2022

    注册截止日期

  • 11月30日 2022

    初稿截稿日期

  • 11月30日 2022

    终稿截稿日期

主办单位
IEEE DEIS
承办单位
Chongqing University
移动端
在手机上打开
小程序
打开微信小程序
客服
扫码或点此咨询