The Research of Urban Rail Transit Sectional Passenger Flow Prediction Method

This paper studies the short-term prediction methods of sectional passenger flow, and selects BP neural network combined with the characteristics of sectional passenger flow itself. With a case study, we design three different schemes. We use Matlab to realize the prediction of the sectional passenger flow of the Beijing subway Line 2 and make comparative analysis. The empirical research shows that combining data characteristics of sectional passenger flow with the BP neural network have good prediction accuracy.

Short-term inbound rail transit passenger flow prediction based on BILSTM model and influence factor analysis

Accurate and real-time passenger flow prediction of rail transit is an important part of intelligent transportation systems(ITS).According to previous studies,it is found that the prediction effect of a single model is not good for datasets with large changes in passenger flow characteristics and the deep learning model with added influencing factors has better prediction accuracy.In order to provide persuasive passenger flow forecast data for ITS,a deep learning model considering the influencing factors is proposed in this paper.In view of the lack of objective analysis on the selection of influencing factors by predecessors,this paper uses analytic hierarchy processes(AHP)and one-way ANOVA analysis to scientifically select the factor of time characteristics,which classifies and gives weight to the hourly passenger flow through Duncan test.Then,combining the time weight,BILSTM based model considering the hourly travel characteristics factors is proposed.The model performance is verified through the inbound passenger flow of Ningbo rail transit.The proposed model is compared with many current mainstream deep learning algorithms,the effectiveness of the BILSTM model considering influencing factors is validated.Through comparison and analysis with various evaluation indicators and other deep learning models,the results show that the R2 score of the BILSTM model considering influencing factors reaches 0.968,and the MAE value of the BILSTM model without adding influencing factors decreases by 45.61%.

Importance Analysis of Urban Rail Transit Network Station Based on Passenger

Current urban rail transit has become a major mode of transportation, and passenger is an important factor of urban rail transport, so this article is based on passenger and the degree of the road network structure, calculating the point intensity of stations of urban rail transit, and then reaching a station importance by integrating many point intensities in a survey cycle time, and getting the station importance of urban rail transit network through concrete examples.

Spatial Interaction and Network Structure Evolvement of Cities in Terms of China's Rail Passenger Flows

Cities separated in space are connected together by spatial interaction (SI) between them. But the studies focusing on the SI are relatively few in China mainly because of the scarcity of data. This paper deals with the SI in terms of rail passenger flows, which is an important aspect of the network structure of urban agglomeration. By using a data set consisting of rail O-D (origin-destination) passenger flows among nearly 200 cities, intercity rail distance O-D matrixes, and some other indices, it is found that the attenuating tendency of rail passenger is obvious. And by the analysis on dominant flows and spatial structure of flows, we find that passenger flows have a trend of polarizing to hubs while the linkages between hubs upgrade. However, the gravity model reveals an overall picture of convergence process over time which is not in our expectation of integration process in the framework of globalization and economic integration. Some driven factors for the re-organization process of the structure of urban agglomeration, such as technique advance, globalization, etc. are discussed further based on the results we obtained.

Coupling analysis of passenger and train flows for a large-scale urban rail transit system

Coupling analysis of passenger and train flows is an important approach in evaluating and optimizing the operation efficiency of large-scale urban rail transit(URT)systems.This study proposes a passenger–train interaction simulation approach to determine the coupling relationship between passenger and train flows.On the bases of time-varying origin–destination demand,train timetable,and network topology,the proposed approach can restore passenger behaviors in URT systems.Upstream priority,queuing process with first-in-first-serve principle,and capacity constraints are considered in the proposed simulation mechanism.This approach can also obtain each passenger’s complete travel chain,which can be used to analyze(including but not limited to)various indicators discussed in this research to effectively support train schedule optimization and capacity evaluation for urban rail managers.Lastly,the proposed model and its potential application are demonstrated via numerical experiments using real-world data from the Beijing URT system(i.e.,rail network with the world’s highest passenger ridership).

Last train timetable optimization for metro network to maximize the passenger accessibility over the end-of-service period

Purpose-This study aims to improve the passenger accessibility of passenger demands in the end-ofoperation period.Design/methodology/approach-A mixed integer nonlinear programming model for last train timetable optimization of the metro was proposed considering the constraints such as the maximum headway,the minimum headway and the latest end-of-operation time.The objective of the model is to maximize the number of reachable passengers in the end-of-operation period.A solution method based on a preset train service is proposed,which significantly reduces the variables of deciding train services in the original model and reformulates it into a mixed integer linear programming model.Findings-The results of the case study of Wuhan Metro show that the solution method can obtain highquality solutions in a shorter time;and the shorter the time interval of passenger flow data,the more obvious the advantage of solution speed;after optimization,the number of passengers reaching the destination among the passengers who need to take the last train during the end-of-operation period can be increased by 10%.Originality/value-Existing research results only consider the passengers who take the last train.Compared with previous research,considering the overall passenger demand during the end-of-operation period can make more passengers arrive at their destination.Appropriately delaying the end-of-operation time can increase the proportion of passengers who can reach the destination in the metro network,but due to the decrease in passenger demand,postponing the end-of-operation time has a bottleneck in increasing the proportion of passengers who can reach the destination.

National Standards for Urban Rail Transit

In this paper, we suggest the creation of passenger service standards for urban rail transit. We put forward standards suited for China's actual conditions, aimed at meeting an international level of service based on customer-oriented principles.

Optimization method of urban rail train operational plan based on O-D time-varying demand

Purpose–Under the constraints of given passenger service level and coupling travel demand with train departure time,this study optimizes the train operational plan in an urban rail corridor to minimize the numbers of train trips and rolling stocks considering the time-varying demand of urban rail passenger flow.Design/methodology/approach–The authors optimize the train operational plan in a special network layout,i.e.an urban rail corridor with dead-end terminal yard,by decomposing it into two sub-problems:train timetable optimization and rolling stock circulation optimization.As for train timetable optimization,the authors propose a schedule-based passenger flow assignment method,construct the corresponding timetabling optimization model and design the bi-directional coordinated sequential optimization algorithm.For the optimization of rolling stock circulation,the authors construct the corresponding optimization assignment model and adopt the Hungary algorithm for solving the model.Findings–The case study shows that the train operational plan developed by the study’s approach meets requirements on the passenger service quality and reduces the operational cost to the maximum by minimizing the numbers of train trips and rolling stocks.Originality/value–The example verifies the efficiency of the model and algorithm.

Real-Time Analysis and Prediction System for Rail Transit Passenger Flow Based on Deep Learning

With the rapid development of urban rail transit,rail transit plays an important role in alleviating city congestion.In recent years,with increasing pas-sengerflow,there has been huge pressure on passengerflow management.To address this problem,we propose a novel system to provide real-time statistics and predictions of passengerflow based on big data technology and deep learning technology.Moreover,the passengerflow is visualized efficiently in this system.It can provide refined passengerflow information so that people can make more rational decisions in terms of operation and planning,deploy contingency plans to avoid emergency situations,and integrate passengerflow analysis with train production,scheduling and operation to achieve cost reduction and efficiency enhancement.

2023年世界城市轨道交通运营统计与分析综述

参考国际上较为通用的统计标准,将城市轨道交通分为地铁、轻轨和有轨电车三大类,对世界城轨交通运营现状进行统计。分析表明:截至2023年底,全球有79个国家和地区的563座城市开通了城市轨道交通系统,总里程超过43400.40 km,其中地铁、轻轨、有轨电车分别占50.07%、10.69%和39.24%;中国(含港澳台)累计有66座城市开通运营轨道交通,运营里程达11900.29 km,其中中国内地运营里程11232.65 km。2022年,全球59个国家的183座城市地铁累计运送乘客586.52亿人次,平均负荷强度0.81万人次/(km·d),其中中国(含港澳台)地铁年客流量为212.51亿人次。我国城市轨道交通持续稳步发展,线网规模和客流规模继续居全球第一。统计国务院52号文件发布后的中国轨道交通的线网规模数据,预测低运量城市轨道交通系统将在中国内地有较好的发展前景,特别是中西部地区,以促进城市绿色、可持续发展。同时,根据疫情前后全球主要国家(地区)和城市的客流数据,预计中国内地客流量将在2024—2025年恢复至疫情前水平。

基于组合深度学习的轨道交通短时进站客流预测模型

针对轨道交通短时进站客流考虑不充分和特征学习不全面而导致预测精度不高的问题,选取客流特征、天气、空气质量和道路交通拥堵指数等多个因素,提出了一种基于组合深度学习的轨道交通短时进站客流预测模型(CNN-ResNet-BiLSTM)。基于卷积神经网络(CNN)对多因素客流时间序列进行自动提取,在CNN网络中插入多个残差神经网络(ResNet)来加深网络深度,利用双向长短时记忆神经网络(BiLSTM)捕捉前后两个方向的客流时间序列特征并得到预测结果;以杭州市全网80个站点工作日的进站客流为例,验证了该模型的有效性。研究结果表明:与常用的几种模型相比,多因素CNN-ResNet-BiLSTM组合模型的均方根误差(E RMS)至少降低了8.50%,平均绝对误差(E MA)至少降低了6.74%,平均绝对百分比误差(E MPA)至少降低了6.52%。

基于迁移学习的轨道交通特殊OD客流预测研究

客流预测一直是轨道交通运营公司关注的重点,由于受到运输能力的限制等因素影响,部分OD的实际客流数据与真实需求有偏差,出现异常或者样本缺失,从而造成总体样本量偏小,直接采用这些样本进行预测会明显影响预测精度,但通过还原样本值增加样本量难度太大。根据上述特点选择基于实例的迁移学习,先确定源域的对象和范围,从源域中选择合适的样本补充到总体样本中,共同组成最终的训练样本数据集,完成迁移学习。同时选择改进的Boost算法,通过误差调整样本权重,不断迭代,得到最终的预测模型。结果表明:基于实例的迁移学习结合改进Boost算法的预测精度要好于传统集成学习、ARIMA模型、多元回归模型,为轨道交通运营公司对特定OD的客流预测提供新的有益尝试。

基于数据融合的城市轨道交通大客流预警研究

为了降低因节假日或突发时间导致的客流拥堵,促进客运部门快速应对客流波动,提出了一种基于数据融合的城市轨道交通大客流预警方法。通过对客流参数预测信息进行融合,获得符合实际客流瓶颈点的参数信息,以完成轨道交通大客流预警。提出的方法利用动态贝叶斯网络,实现了历史数据与运输服务信息的融合。以城市假期期间五条线路每日客流量为例,通过对比实验验证了提出方法的有效性与准确性。

深圳市轨道交通车站与土地利用互动性研究

城市轨道交通与土地利用发展相互影响,两者协调发展有助于缓解城市交通拥堵,是城市可持续发展的关键问题之一.利用中国深圳市1999年与2015年的建筑普查、土地利用以及轨道交通车站刷卡数据,从开发强度、用地信息熵、车站类型及早晚高峰客流量等多个指标精细化分析轨道交通车站运能与周边土地利用之间的内在联系,并引入“节点-场所”模型构建指标体系评价轨道交通车站与土地利用间的发展协调程度,利用k-means聚类分析将二者协调状态划分为从属状态、平衡状态及失衡状态.结果表明,随着轨道交通车站开发建设,深圳市轨道交通车站周边土地集约利用水平提高;车站客流量与周边土地利用指标的相关性显著,全天客流量与容积率和商办建筑面积显著正相关,早高峰客流量与居住建筑面积和建筑密度显著正相关,而与容积率显著负相关,晚高峰客流量则与商办建筑面积和道路网密度显著正相关.深圳市轨道交通车站与站点周边土地利用协调发展水平偏低,站点类型以节点和场所价值低度均衡发展的从属状态为主,而协调状态则较少且集中分布在中心区圈层.未来应进一步对失衡节点地区采取针对性的开发策略,提升集聚效应与服务水平.

考虑动态随机客流的城市轨道交通列车时刻表仿真优化

为更加精准刻画动态随机客流与列车时刻表编制间的复杂匹配过程,综合考虑乘客动态随机到达过程、列车容量限制、车内拥挤度对乘客上下车速率影响、停站时间动态调整和列车运行安全防护等重要运营特征,构建城市轨道交通列车运行离散仿真模型。在此基础上,建立以最小化乘客平均候车时间为目标的随机非线性优化模型,并设计一种基于仿真的有限差分随机逼近算法,用于优化城市轨道交通发车方案。以国内某条线路的实际运营数据为例验证仿真模型及优化方法,结果表明所构建模型及算法具有较好的优化效果和计算效率,优化后的列车实绩运行时刻能更好地适应客流需求的动态随机性,且在不增加发车频次的前提下有效降低乘客平均候车时间,提升城市轨道交通运营管理水平。

基于乘客OD间路径旅行时间的城市轨道交通客流分布计算模型的适用性研究

[目的]针对目前城市轨道交通(以下简称“城轨”)线网客流分布计算模型的客流计算结果与实际客流存在偏差的现象,需基于OD间路径的实际旅行时间,对基于多路径概率分配的客流分布计算模型的适用性展开研究。[方法]基于乘客OD间路径的实际旅行时间,分析揭示了现有城轨客流分布计算模型存在的主要问题;融合AFC(自动售检票)系统和ATS(列车自动监控)系统两类数据,构建并标定了基于乘客OD间路径旅行时间的城轨客流分布计算模型;对目前国内城轨系统广泛采用的基于多路径概率分配的城轨客流分布计算模型的适用性进行了分析与评价。[结果及结论]现有城轨客流分布计算模型在路径选择集和路径选择比例上存在主要问题。通过基于多路径概率分配的城轨客流分布计算模型获取的路径分配比例,得到的旅行时间分布模拟结果均为单峰,无法重现从AFC票卡提取的实际旅行时间分布的多峰情况。当城轨线网较为简单时,基于多路径概率分配的城轨客流分布计算模型基本适用;当线网规模不断增加,线网结构进一步复杂,列车运行方式的多样性、乘客出行行为的差异性等不断加大的条件下,该模型对于路径阻抗差异小的OD可能适用,而对于路径阻抗差异大的OD不适用。

基于乘客服务水平和安全的城市轨道交通扣车方案评价

[目的]扣车是城市轨道交通发生长时间初始延误条件下经常采用的列车运行方案。为了评价该方案的合理性,需构建基于乘客服务和安全的扣车方案评价模型,并对扣车方案进行评价。[方法]考虑到乘客出行规律的复杂性和特殊性,制定了城市轨道交通扣车方案。构建了基于最大发车间隔、列车总延误时间、列车均衡性、终到延误列车数、滞留乘客数及乘客总旅行时间的扣车方案评价模型。选取上海某条轨道交通线路的4个区间,以早高峰小时的实际OD(起讫点)客流量为例进行计算。[结果及结论]计算表明,方案6下的综合评价指标最小,为最优扣车调整方案。该方案可以有效提高列车运行图的均衡性,减少滞留乘客的数量,降低车站的安全隐患。

基于加线技术的轨道交通临客开行计划优化模型

基于运行图加线技术构建适于计划性临客开行的运行线铺画方法.以运力与客流匹配度最大化、对原运行图调整最小化为优化目标,考虑行车安全、临客加线位置、开行时间域等约束,构建临客运行线铺画非线性整数规划模型,并对其线性转换以提高求解效率.以北京地铁8号线某大型活动散场大客流为场景进行案例分析,结果表明:所构建方法能够在既有运行图上有效铺画临客运行线,满足不同行车密度及停站模式下的临客开行需求.建议在较高密度行车条件下不采用“空车直达”停站模式.

土地利用与城市轨道交通客流的非线性关系

城市轨道交通站点影响范围内土地利用对客流影响具有时空分异特征且存在类型差异,为针对性探讨不同站点两者的复杂非线性关系,提出一种基于土地利用空间分布规律、对站点实际影响范围进行差异化识别的方法;并通过分时段多尺度地理加权回归,获取能够表征土地利用对客流影响时空变化特征的站点聚类指标,采用K-means++算法将研究区域内的站点划分为4类;进而基于改进的梯度提升决策树模型分类定量探讨不同类别下土地利用与轨道交通客流的复杂非线性关系。研究表明:通过捕捉不同站点土地利用与客流的时空分异特征对站点进行分类识别,可有效提升两者非线性关系模型的解释度。根据模型输出结果,发现不同类别站点影响轨道交通客流的关键土地利用要素不同,第1类中关键变量为相对重要性分别为61.35%和30.08%的公交站点数量和慢行密度;第4类的情况类似但相对数值有所变化,公交站点数量的相对重要性由61.35%下降至30.31%;建筑密度在第2类中以66.57%的相对重要度占据最大比例;但在第3类中仅占5.59%。此外,不同类别站点影响范围内土地利用与轨道交通客流的关系存在较为显著且各异的阈值效应。研究表明,对于不同类别站点的用地开发应各有侧重,且应结合实际将土地利用设计指标控制在相应的合理范围内。研究为差异化的站点周边土地利用开发策略的制定提供了理论支持和量化指导。