GIS Room Autonomous Inspection System Based on Multi-rotor UAV

Qi Li, Yan Dai, R. Han, Donglian Qi, Yunfeng Yan
{"title":"GIS Room Autonomous Inspection System Based on Multi-rotor UAV","authors":"Qi Li, Yan Dai, R. Han, Donglian Qi, Yunfeng Yan","doi":"10.1109/ICEMPE51623.2021.9509093","DOIUrl":null,"url":null,"abstract":"Gas-insulated switchgear (GIS), as an important high-voltage equipment in a substation, is extremely important to the normal operation of the substation. There are many SF6 pointer meters in the GIS room to monitor the insulating medium, SF6 gas, in the closed metal pipeline. However, since many meters are located at a height of 4-5 meters, it is not conducive to manual or robot inspection. Therefore, in order to solve the problem of inspection of SF6 meters at high places, the article proposes to use a multi-rotor Unmanned Aerial Vehicle(UAV) with strong maneuverability and high flexibility for inspection. The inspection system designed in this paper is based on the secondary development of the DJI Mavic2 UAV platform, and uses Apriltag to achieve accurate indoor positioning of the UAV. At the same time, it combines the meter recognition algorithm based on key point detection to automatically read the meters. Finally, the autonomous inspection of SF6 meters in the GIS room based on the multi-rotor UAV is realized. Through testing in the substation, the practicability of the inspection system is verified.","PeriodicalId":7083,"journal":{"name":"2021 International Conference on Electrical Materials and Power Equipment (ICEMPE)","volume":"34 1","pages":"1-4"},"PeriodicalIF":0.0000,"publicationDate":"2021-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Electrical Materials and Power Equipment (ICEMPE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICEMPE51623.2021.9509093","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Gas-insulated switchgear (GIS), as an important high-voltage equipment in a substation, is extremely important to the normal operation of the substation. There are many SF6 pointer meters in the GIS room to monitor the insulating medium, SF6 gas, in the closed metal pipeline. However, since many meters are located at a height of 4-5 meters, it is not conducive to manual or robot inspection. Therefore, in order to solve the problem of inspection of SF6 meters at high places, the article proposes to use a multi-rotor Unmanned Aerial Vehicle(UAV) with strong maneuverability and high flexibility for inspection. The inspection system designed in this paper is based on the secondary development of the DJI Mavic2 UAV platform, and uses Apriltag to achieve accurate indoor positioning of the UAV. At the same time, it combines the meter recognition algorithm based on key point detection to automatically read the meters. Finally, the autonomous inspection of SF6 meters in the GIS room based on the multi-rotor UAV is realized. Through testing in the substation, the practicability of the inspection system is verified.
基于多旋翼无人机的GIS房间自主巡检系统
气体绝缘开关柜作为变电站中重要的高压设备,对变电站的正常运行至关重要。GIS室内有许多SF6指针仪表,用于监测封闭金属管道中的绝缘介质SF6气体。但由于很多米位于4-5米的高度,不利于人工或机器人巡检。因此,为了解决高空SF6米的巡检问题,本文提出采用机动性强、灵活性高的多旋翼无人机(UAV)进行巡检。本文设计的巡检系统是基于大疆Mavic2无人机平台的二次开发,采用Apriltag实现无人机的精确室内定位。同时结合基于关键点检测的电表识别算法,实现电表自动读取。最后,实现了基于多旋翼无人机的GIS机房SF6米自主巡检。通过变电站的实际测试,验证了该检测系统的实用性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信