高速铁路接触网悬挂飘浮物识别边缘物联系统研究  

Research on Edge IoT System for Identifying Floating Objects in High Speed Railway Catenary System

在线阅读下载全文

作  者:司福强 周明 王继军 荣正官 伍平 赵灵燕 SI Fuqiang;ZHOU Ming;WANG Jijun;RONG Zhengguan;WU Ping;ZHAO Lingyan(Beijing China Railway Construction Electrification Design&Research Institute Co.Ltd.,Beijing 100043,China;China Railway Construction Electrification Bureau Group Co.Ltd.,Beijing 100043,China)

机构地区:[1]北京中铁建电气化设计研究院有限公司,北京100043 [2]中国铁建电气化局集团有限公司,北京100043

出  处:《铁道建筑技术》2023年第11期21-24,共4页Railway Construction Technology

基  金:中国铁建股份有限公司科技研发计划项目(2022-C36)。

摘  要:现有高速铁路接触网的运行环境复杂多样,人工巡检压力不断增强。在面对接触网线路在线监测可视化设备、传感器等数据没有在边缘汇集,无法实现充分、灵活利用前端数据资源进行接触网线路局部状态的就地分析等问题,本文基于AI识别和数据融合分析的边缘物联技术,提供了一种边缘物联系统,减少了数据在云端和本地传送的次数,在本地实现对接触网线路状态的监测,同时将预警信息通过通信设备发送至服务器,由部署在服务器上的应用实现隐患预警,降低设备功耗的同时能够做到及时预警,极大地保障了接触网线路的安全运行。The operating environment of the existing high-speed railway catenary is complex and diverse,and the pressure of manual inspection is constantly increasing.In the face of the problem of online monitoring visualization equipment,sensors,and other data of overhead contact lines not being collected at the edge,which makes it impossible to fully and flexibly utilize front-end data resources for on-site analysis of local status of overhead contact lines,this article provides an edge IoT system based on AI recognition and data fusion analysis,reducing the number of data transfers in the cloud and local,at the same time as monitoring the status of the overhead contact line locally,the warning information is sent to the server through communication equipment.The application deployed on the server realizes hidden danger warning,reducing equipment power consumption and achieving timely warning,greatly ensuring the safe operation of the overhead contact line.

关 键 词:边缘物联融合 接触网 图像识别 预警 

分 类 号:U225[交通运输工程—道路与铁道工程] TP391.4[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象