基于动态多源数据采集的铁路车辆装载状况检测和智能分析系统
Railway Vehicle Load Condition Detection and Intelligent Analysis System Based on Dynamic Multi-Source Data Collection
张志国 1傅健 1辛向党 1李建国2
作者信息
- 1. 中国铁路兰州局集团有限公司 货运部,甘肃 兰州 730000
- 2. 中国铁路兰州局集团有限公司 货运部,甘肃 兰州 730000;兰州交通大学 高原铁路运输智慧管控铁路行业重点实验室,甘肃 兰州 730070
- 折叠
摘要
通过分析目前铁路车辆装载人工检测方式与相关现有系统的不足,设计了一套具有动态多源数据采集的铁路车辆装载状况检测和智能分析系统.该系统通过构建多模态传感器和RS485传输及NB-IOT传输技术,对车辆装载状况进行多源数据采集、分析和处理,选用多模态传感器与边缘计算机融合,设计实现手动、自动、远程和自动故障恢复等控制方式,涵盖基础信息管理模块、检测门系统模块、警报系统模块、应用维护模块共4个功能模块.根据国内外铁路货物运输实际情况,对比分析现有的铁路货运安全检测监控技术设备等,该系统具备技术优势与应用效果,可有效指导装载优化和效率提升,在铁路货物运输领域中具有重要应用价值.
Abstract
By analyzing the shortcomings of current manual detection methods for railway vehicle loading and related existing systems,a railway vehicle load condition detection and intelligent analysis system with dynamic multi-source data collection was designed.This system collects,analyzes,and processes multi-source data on vehicle load conditions by utilizing a combination of multimodal sensors,RS485 transmission,and narrow band Internet of Things(NB-IoT)transmission technologies.Multimodal sensors are integrated with edge computing to achieve manual,automatic,remote,and automatic fault recovery control modes,as well as four functional modules,including basic information management module,detection door system module,alarm system module,and application maintenance module.According to the current status of domestic and international railway freight transportation,this study compared and analyzed the technology and equipment available for railway freight safety detection and monitoring.It demonstrated technical advantages and application effects that can effectively guide loading optimization and enhance efficiency.This system holds significant application value in the railway freight transportation sector.
关键词
铁路货运/多源数据/智能分析/决策支持/人工智能Key words
Railway Freight Transportation/Multi-Source Data/Intelligent Analysis/Decision Support/Artificial Intelligence引用本文复制引用
基金项目
中国铁路兰州局集团有限公司科技研发计划(LZJKY2023009-1)
国家铁路局高原铁路运输智慧管控铁路行业重点实验室开放基金(GYYSHZ2306)
出版年
2024
国家科技期刊平台
NSTL
维普
万方数据