The invention relates to the technical field of urban rail control, and discloses a rail transit short-time OD flow urban rail control system and method based on heterogeneous graph convolution, and the method comprises the steps: obtaining the historical passenger flow data of an urban rail transit system, and constructing a recent OD matrix, a daily OD matrix, and a weekly OD matrix based on the historical passenger flow data. And constructing a space-time fusion network, respectively inputting the recent OD matrix, the daily OD matrix and the weekly OD matrix into the space-time fusion network, and obtaining a passenger flow score in a future time period. And establishing a staying score according to the passenger flow score and the number of the passing trains, and determining the staying level of each station in the urban rail transit system according to the relationship between the staying score and a preset staying score. And according to the relationship between the staying grade of the station and a preset staying grade, corresponding train staying time is selected for staying. According to the invention, the individual regulation and control of the stations are realized through the differentiated staying levels and duration setting, and the ability of the urban rail transit system to cope with complex demands is effectively improved.
本发明涉及城轨控制技术领域,公开了基于异构图卷积轨道交通短时OD流量城轨控制系统及方法,该方法包括:获取城市轨道交通系统的历史客流量数据,基于历史客流量数据分别构建近期OD矩阵、每日OD矩阵、每周OD矩阵。构建时空融合网络,分别将近期OD矩阵、每日OD矩阵、每周OD矩阵输入时空融合网络,获取未来时段的客流量评分。根据客流量评分与途经列车数量建立停留评分,根据停留评分与预设的停留评分之间的关系,确定城市轨道交通系统中各站点的停留等级。根据站点的停留等级与预设的停留等级之间的关系,选定相应的列车停留时间进行停留。本发明差异化的停留等级与时长设定实现对站点个性化调控,有效的提高城轨交通系统应对复杂需求的能力。
Urban rail control system and method for short-time OD flow of rail transit based on heterogeneous graph convolution
基于异构图卷积轨道交通短时OD流量城轨控制系统及方法
2024-04-12
Patent
Elektronische Ressource
Chinesisch
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES |
Urban rail transit rail deformation monitoring equipment
Europäisches Patentamt | 2021
|Multi-graph convolutional network for short-term passenger flow forecasting in urban rail transit
IET | 2020
|Multi‐graph convolutional network for short‐term passenger flow forecasting in urban rail transit
Wiley | 2020
|