Journal of Rail Transport Planning & Management最新文献_第3页

Train rescheduling for a metro corridor under unidirectional disruptions considering the trade-off between confirm phase and interrupt phase 考虑确认阶段与中断阶段权衡的单向中断条件下地铁走廊列车重新调度

IF 2.7 Q3 TRANSPORTATION

Journal of Rail Transport Planning & Management

Pub Date : 2025-09-01 Epub Date: 2025-07-31 DOI: 10.1016/j.jrtpm.2025.100534

Fangsheng Wang , Xiaoyu Hao , Ruihua Xu

Metro systems serve as vital transportation arteries in large cities, playing a crucial role in public transit networks. However, failures such as track blockages, signal malfunctions, or train breakdowns frequently disrupt metro services. Given the substantial impact of different rescheduling strategies on transport capacity, this study incorporates the time required for dispatchers to confirm disruptions. The problem of large-scale rescheduling is reformulated into a two-stage process, the confirm phase and the interrupt phase, to analyze the trade-offs between various rescheduling strategies more effectively. Five rescheduling models are developed, each designed for specific turn-around scenarios, aiming to minimize total delay time and enhance train utilization efficiency. These models account for distinct operational conditions, train scheduling dynamics, and constraints associated with each turn-around type. The proposed rescheduling approach is applied to Shanghai Metro's Line 2, with experimental results confirming its effectiveness. The feasibility of the optimization outcomes is further validated using TPM commercial software. Additionally, the study evaluates the influence of confirmation time and turn-around type on rescheduling outcomes and overall efficiency.

地铁系统是大城市的交通要道，在公共交通网络中起着至关重要的作用。然而，轨道堵塞、信号故障或列车故障等故障经常扰乱地铁服务。考虑到不同的重新调度策略对运输能力的重大影响，本研究纳入了调度员确认中断所需的时间。为了更有效地分析各种重调度策略之间的权衡，将大规模重调度问题重新表述为确认阶段和中断阶段两个阶段的过程。开发了五种重新调度模型，每种模型都针对特定的转机场景设计，旨在最大限度地减少总延误时间，提高列车利用效率。这些模型考虑了不同的操作条件、列车调度动态以及与每种周转类型相关的约束。将该方法应用于上海地铁2号线，实验结果验证了该方法的有效性。利用TPM商业软件进一步验证了优化结果的可行性。此外，研究还评估了确认时间和周转类型对重调度结果和整体效率的影响。

{"title":"Train rescheduling for a metro corridor under unidirectional disruptions considering the trade-off between confirm phase and interrupt phase","authors":"Fangsheng Wang , Xiaoyu Hao , Ruihua Xu","doi":"10.1016/j.jrtpm.2025.100534","DOIUrl":"10.1016/j.jrtpm.2025.100534","url":null,"abstract":"<div><div>Metro systems serve as vital transportation arteries in large cities, playing a crucial role in public transit networks. However, failures such as track blockages, signal malfunctions, or train breakdowns frequently disrupt metro services. Given the substantial impact of different rescheduling strategies on transport capacity, this study incorporates the time required for dispatchers to confirm disruptions. The problem of large-scale rescheduling is reformulated into a two-stage process, the confirm phase and the interrupt phase, to analyze the trade-offs between various rescheduling strategies more effectively. Five rescheduling models are developed, each designed for specific turn-around scenarios, aiming to minimize total delay time and enhance train utilization efficiency. These models account for distinct operational conditions, train scheduling dynamics, and constraints associated with each turn-around type. The proposed rescheduling approach is applied to Shanghai Metro's Line 2, with experimental results confirming its effectiveness. The feasibility of the optimization outcomes is further validated using TPM commercial software. Additionally, the study evaluates the influence of confirmation time and turn-around type on rescheduling outcomes and overall efficiency.</div></div>","PeriodicalId":51821,"journal":{"name":"Journal of Rail Transport Planning & Management","volume":"35 ","pages":"Article 100534"},"PeriodicalIF":2.7,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144738500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Impact of track discretisation on conflict detection and resolution under ETCS with onboard train integrity monitoring 轨道离散化对列车完整性监测下ETCS冲突检测与解决的影响

IF 2.6 Q3 TRANSPORTATION

Journal of Rail Transport Planning & Management

Pub Date : 2025-09-01 Epub Date: 2025-07-08 DOI: 10.1016/j.jrtpm.2025.100533

Nina D. Versluis , Paola Pellegrini , Egidio Quaglietta , Rob M.P. Goverde , Joaquin Rodriguez

To further improve the capacity on the European railway network, next-generation distance-to-go signalling systems are being developed in the context of the European Train Control System (ETCS). This paper investigates the impact of track discretisation granularity on conflict detection and resolution for ETCS with onboard train integrity monitoring. The study enhances a previously developed model for fixed-block distance-to-go signalling by introducing a track discretisation procedure and reformulating safe train separation constraints at switches. The assessment is performed on a junction and a corridor case study, using track discretisations with maximum section lengths from 50 to 800 m. Though finer discretisations potentially improve the model objective, computation times quickly increase. While the results show minimum effects of the track discretisation on the conflict detection and resolution, they suggest that maximum section lengths of 200 or 400 m may offer a good balance between solution quality and computational complexity, depending on the track layout and traffic density. Generally, reliable rescheduling decisions can already be obtained with a 800-m discretisation.

为了进一步提高欧洲铁路网的能力，下一代远程信号系统正在欧洲列车控制系统（ETCS）的背景下开发。研究了轨道离散化粒度对列车完整性监测ETCS冲突检测与解决的影响。该研究通过引入轨道离散化程序和重新制定安全列车分离约束，增强了先前开发的固定街区距离至行信号模型。评估是在一个路口和一个走廊的案例研究中进行的，使用最大截面长度为50到800米的轨道离散。虽然更精细的离散可能会改善模型目标，但计算时间会迅速增加。虽然结果显示轨道离散化对冲突检测和解决的影响最小，但他们建议，根据轨道布局和交通密度，200或400米的最大路段长度可能在解决方案质量和计算复杂性之间提供良好的平衡。一般来说，通过800米的离散化已经可以获得可靠的重新调度决策。

{"title":"Impact of track discretisation on conflict detection and resolution under ETCS with onboard train integrity monitoring","authors":"Nina D. Versluis , Paola Pellegrini , Egidio Quaglietta , Rob M.P. Goverde , Joaquin Rodriguez","doi":"10.1016/j.jrtpm.2025.100533","DOIUrl":"10.1016/j.jrtpm.2025.100533","url":null,"abstract":"<div><div>To further improve the capacity on the European railway network, next-generation distance-to-go signalling systems are being developed in the context of the European Train Control System (ETCS). This paper investigates the impact of track discretisation granularity on conflict detection and resolution for ETCS with onboard train integrity monitoring. The study enhances a previously developed model for fixed-block distance-to-go signalling by introducing a track discretisation procedure and reformulating safe train separation constraints at switches. The assessment is performed on a junction and a corridor case study, using track discretisations with maximum section lengths from 50 to 800 m. Though finer discretisations potentially improve the model objective, computation times quickly increase. While the results show minimum effects of the track discretisation on the conflict detection and resolution, they suggest that maximum section lengths of 200 or 400 m may offer a good balance between solution quality and computational complexity, depending on the track layout and traffic density. Generally, reliable rescheduling decisions can already be obtained with a 800-m discretisation.</div></div>","PeriodicalId":51821,"journal":{"name":"Journal of Rail Transport Planning & Management","volume":"35 ","pages":"Article 100533"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144580963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analysis of freight train passing a stop signal using machine learning: Application of XGBoost and SHAP 货运列车通过停车信号的机器学习分析：XGBoost和SHAP的应用

IF 2.6 Q3 TRANSPORTATION

Journal of Rail Transport Planning & Management

Pub Date : 2025-09-01 Epub Date: 2025-06-24 DOI: 10.1016/j.jrtpm.2025.100532

Mona Ahmadi Rad , Lianne M. Lefsrud , Michael T. Hendry , Asdrubal Cheng Cen , Sara Soltaninejad

Passing a Stop Signal (PASS) is a critical safety concern in railway operations, with the potential to cause serious accidents. This study investigates non-human contributing factors to PASS events in Canadian mainline freight operations using machine learning. We analyze incident narratives from the Rail Occurrence Database System (RODS) through text mining and enrich them with geospatial and weather data. We develop a binary classification model using XGBoost and interpret feature importance and interactions with SHAP (SHapley Additive exPlanations). To address class imbalance and improve model performance, we apply a custom sampling method, combined with hyperparameter tuning and data standardization. Key contributors to PASS events include sharp track curvature near signals, downhill grades, low atmospheric pressure, high relative humidity, non-clear weather, and heavy traffic—placing Rocky Mountain subdivisions among the highest-risk areas. The model also reveals that combinations of environmental conditions, such as low temperature, low pressure, and high humidity, increase the likelihood of PASS events by reducing visibility and braking effectiveness. This study offers methodological and empirical contributions by modelling complex operational contexts, incorporating underexplored environmental factors, and producing region-specific insights. The proposed framework informs proactive safety strategies and supports risk analysis in other linear infrastructure systems.

通过停车信号（PASS）是铁路运营中一个关键的安全问题，有可能导致严重事故。本研究使用机器学习调查了加拿大干线货运业务中PASS事件的非人为影响因素。我们通过文本挖掘分析铁路事故数据库系统（RODS）中的事件叙述，并用地理空间和天气数据丰富它们。我们使用XGBoost开发了一个二元分类模型，并解释了特征重要性和与SHapley Additive explanation （SHapley Additive exPlanations）的相互作用。为了解决类失衡和提高模型性能，我们采用自定义采样方法，结合超参数调优和数据标准化。PASS事件的主要因素包括信号附近的急剧轨道曲率，下坡坡度，低气压，高相对湿度，不晴朗的天气和繁忙的交通，使落基山细分地区成为风险最高的地区。该模型还显示，低温、低压和高湿等环境条件的组合会降低能见度和制动效果，从而增加发生超车事件的可能性。本研究通过模拟复杂的操作背景、纳入未充分开发的环境因素和产生特定区域的见解，提供了方法和经验贡献。拟议的框架为主动安全策略提供信息，并支持其他线性基础设施系统的风险分析。

{"title":"Analysis of freight train passing a stop signal using machine learning: Application of XGBoost and SHAP","authors":"Mona Ahmadi Rad , Lianne M. Lefsrud , Michael T. Hendry , Asdrubal Cheng Cen , Sara Soltaninejad","doi":"10.1016/j.jrtpm.2025.100532","DOIUrl":"10.1016/j.jrtpm.2025.100532","url":null,"abstract":"<div><div>Passing a Stop Signal (PASS) is a critical safety concern in railway operations, with the potential to cause serious accidents. This study investigates non-human contributing factors to PASS events in Canadian mainline freight operations using machine learning. We analyze incident narratives from the Rail Occurrence Database System (RODS) through text mining and enrich them with geospatial and weather data. We develop a binary classification model using XGBoost and interpret feature importance and interactions with SHAP (SHapley Additive exPlanations). To address class imbalance and improve model performance, we apply a custom sampling method, combined with hyperparameter tuning and data standardization. Key contributors to PASS events include sharp track curvature near signals, downhill grades, low atmospheric pressure, high relative humidity, non-clear weather, and heavy traffic—placing Rocky Mountain subdivisions among the highest-risk areas. The model also reveals that combinations of environmental conditions, such as low temperature, low pressure, and high humidity, increase the likelihood of PASS events by reducing visibility and braking effectiveness. This study offers methodological and empirical contributions by modelling complex operational contexts, incorporating underexplored environmental factors, and producing region-specific insights. The proposed framework informs proactive safety strategies and supports risk analysis in other linear infrastructure systems.</div></div>","PeriodicalId":51821,"journal":{"name":"Journal of Rail Transport Planning & Management","volume":"35 ","pages":"Article 100532"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144364715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

System analysis of train operations to improve freight flow on high gradient rail bottleneck section with mixed traffic 混合交通高梯度轨道瓶颈段列车运行改善货流的系统分析

IF 2.6 Q3 TRANSPORTATION

Journal of Rail Transport Planning & Management

Pub Date : 2025-09-01 Epub Date: 2025-06-04 DOI: 10.1016/j.jrtpm.2025.100522

Kritika Karwasra , Narayan Rangaraj , Karuna Nidhi Singh

This paper analyzes the operations of freight trains on high-gradient rail sections, which are common on India’s western and eastern coasts (known as a ghat section). Operations in these sections differ from regular rail operations. Resource usage differs for passenger trains and freight trains and depends on whether the train is ascending or descending the graded section. This creates an imbalance in resource usage and adds complexity to these operations. Priority for passenger trains adds to this complication, making freight train scheduling challenging. This study analyzes different techniques to improve the freight throughput of the graded sections, considering the case study of the Lonavala-Karjat section. Freight trains on this section experience extended delays, leading to a network capacity bottleneck. Identifying the root cause of these delays is not straightforward, as operations are interrelated. Therefore, the study employs a systems thinking approach, beginning with identifying bottleneck resources. A discrete event simulation model is employed due to its ability to replicate complex real-world scenarios and assess the impact of different variables on system performance. Based on the findings, policies are proposed to optimize freight flow on the graded rail section.

本文分析了货运列车在高坡度铁路路段的运行情况，这在印度西部和东部海岸（被称为ghat段）很常见。这些路段的运营不同于普通铁路运营。旅客列车和货运列车的资源使用情况不同，这取决于列车是上升还是下降。这造成了资源使用的不平衡，并增加了这些操作的复杂性。客运列车的优先级增加了这种复杂性，使货运列车调度具有挑战性。本研究以Lonavala-Karjat路段为例，分析不同的改善分级路段货物吞吐量的方法。这一路段的货运列车延误时间延长，导致网络容量瓶颈。确定这些延迟的根本原因并不简单，因为操作是相互关联的。因此，本研究采用系统思维方法，从识别瓶颈资源入手。采用离散事件仿真模型是因为它能够复制复杂的现实世界场景并评估不同变量对系统性能的影响。在此基础上，提出了分级段货流优化政策。

{"title":"System analysis of train operations to improve freight flow on high gradient rail bottleneck section with mixed traffic","authors":"Kritika Karwasra , Narayan Rangaraj , Karuna Nidhi Singh","doi":"10.1016/j.jrtpm.2025.100522","DOIUrl":"10.1016/j.jrtpm.2025.100522","url":null,"abstract":"<div><div>This paper analyzes the operations of freight trains on high-gradient rail sections, which are common on India’s western and eastern coasts (known as a ghat section). Operations in these sections differ from regular rail operations. Resource usage differs for passenger trains and freight trains and depends on whether the train is ascending or descending the graded section. This creates an imbalance in resource usage and adds complexity to these operations. Priority for passenger trains adds to this complication, making freight train scheduling challenging. This study analyzes different techniques to improve the freight throughput of the graded sections, considering the case study of the Lonavala-Karjat section. Freight trains on this section experience extended delays, leading to a network capacity bottleneck. Identifying the root cause of these delays is not straightforward, as operations are interrelated. Therefore, the study employs a systems thinking approach, beginning with identifying bottleneck resources. A discrete event simulation model is employed due to its ability to replicate complex real-world scenarios and assess the impact of different variables on system performance. Based on the findings, policies are proposed to optimize freight flow on the graded rail section.</div></div>","PeriodicalId":51821,"journal":{"name":"Journal of Rail Transport Planning & Management","volume":"35 ","pages":"Article 100522"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-period railway timetabling to serve time-dependent demand 多时段铁路时刻表，以满足时效性需求

IF 2.7 Q3 TRANSPORTATION

Journal of Rail Transport Planning & Management

Pub Date : 2025-09-01 Epub Date: 2025-08-19 DOI: 10.1016/j.jrtpm.2025.100536

Renate J.H. van der Knaap, Niels van Oort, Rob M.P. Goverde

Passenger railway demand fluctuates daily, peaking at the start and end of the workday due to commuting to school and work. During the off-peak the volumes drop and most people travel for other purposes, like leisure and social visits, which results in different travel destinations. Despite this, many European Railways use fixed line plans and cyclic timetables that remain constant throughout the day. While this approach makes schedules easy to remember and provides ample off-peak travel options, it is primarily designed for peak-hour demand, making it less efficient for the off-peak. Furthermore, due to the different mix of travel purposes, a schedule based on peak-hour demand is not necessarily optimal for off-peak demand. This paper aims to combine the benefits of a cyclic timetable with the flexibility of an acyclic timetable in order to follow the time-dependent demand more closely. We propose a mixed-integer linear programming model that finds a timetable for a day consisting of several periods which each have its own line plan. The resulting timetable is required to be cyclic within each period and provide a good transition between the periods. The model is successfully tested on a case study with changing stopping patterns using data from the Dutch railway network, for which an optimal timetable is found. In this timetable, the transition between cyclic schedules can be done without cancelling trains or shifting trains from the new cyclic times.

铁路客运需求每天都在波动，在工作日开始和结束时，由于通勤上学和工作，需求达到峰值。在非高峰期间，游客数量下降，大多数人出于其他目的旅行，如休闲和社交，这导致了不同的旅游目的地。尽管如此，许多欧洲铁路使用固定线路计划和循环时间表，全天保持不变。虽然这种方法使时间表易于记忆，并提供了充足的非高峰旅行选择，但它主要是为高峰时段的需求而设计的，因此在非高峰时段效率较低。此外，由于出行目的的不同组合，基于高峰时段需求的时间表不一定是非高峰时段需求的最佳选择。本文旨在将循环时间表的优点与非循环时间表的灵活性结合起来，以便更紧密地遵循时间依赖性需求。我们提出了一个混合整数线性规划模型，它找到一个由几个时间段组成的一天的时间表，每个时间段都有自己的线路计划。生成的时间表需要在每个周期内循环，并在周期之间提供良好的过渡。利用荷兰铁路网的数据，通过改变停车模式的案例研究，成功地对该模型进行了测试，并找到了最优的时间表。在这个时间表中，循环时间表之间的转换可以在不取消列车或从新的循环时间转移列车的情况下完成。

{"title":"Multi-period railway timetabling to serve time-dependent demand","authors":"Renate J.H. van der Knaap, Niels van Oort, Rob M.P. Goverde","doi":"10.1016/j.jrtpm.2025.100536","DOIUrl":"10.1016/j.jrtpm.2025.100536","url":null,"abstract":"<div><div>Passenger railway demand fluctuates daily, peaking at the start and end of the workday due to commuting to school and work. During the off-peak the volumes drop and most people travel for other purposes, like leisure and social visits, which results in different travel destinations. Despite this, many European Railways use fixed line plans and cyclic timetables that remain constant throughout the day. While this approach makes schedules easy to remember and provides ample off-peak travel options, it is primarily designed for peak-hour demand, making it less efficient for the off-peak. Furthermore, due to the different mix of travel purposes, a schedule based on peak-hour demand is not necessarily optimal for off-peak demand. This paper aims to combine the benefits of a cyclic timetable with the flexibility of an acyclic timetable in order to follow the time-dependent demand more closely. We propose a mixed-integer linear programming model that finds a timetable for a day consisting of several periods which each have its own line plan. The resulting timetable is required to be cyclic within each period and provide a good transition between the periods. The model is successfully tested on a case study with changing stopping patterns using data from the Dutch railway network, for which an optimal timetable is found. In this timetable, the transition between cyclic schedules can be done without cancelling trains or shifting trains from the new cyclic times.</div></div>","PeriodicalId":51821,"journal":{"name":"Journal of Rail Transport Planning & Management","volume":"35 ","pages":"Article 100536"},"PeriodicalIF":2.7,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144865415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Train dwell time models for crowded metro stations using a bivariate distribution function 基于二元分布函数的拥挤地铁站列车停留时间模型

IF 2.7 Q3 TRANSPORTATION

Journal of Rail Transport Planning & Management

Pub Date : 2025-09-01 Epub Date: 2025-08-16 DOI: 10.1016/j.jrtpm.2025.100538

Natchaya Tortainchai , Taku Fujiyama

Train dwell times at high-passenger-volume stations are complex and inconsistent due to variations in passenger behaviour and interactions. While several studies have examined factors affecting dwell time and developed models to predict it, these models often struggle to accurately predict dwell times under high passenger volume conditions. This poses significant challenges to planning effective timetables in crowded environments. Given this variability, using probability-based approaches to predict dwell time delay could provide better planning. Although some studies have identified dwell time probability distribution functions, they generally do not include passenger volume level as a variable, limiting their applicability in high-density stations.

This paper investigates actual operational data to present the limitations of predicting dwell times at high-passenger-volume stations. To address the gap, this paper proposes a bivariate probability function that incorporates passenger volume as a key variable. This gives us a more reliable framework for predicting dwell time delays in crowded environments. The Kolmogorov-Smirnov (K-S) test is used to validate the bivariate dwell time function. This shows the function's capability to predict the probability of achieving target dwell times, which is essential for planning dwell times. Furthermore, this model can be applied alongside delay impact assessments, facilitating a further risk evaluation framework that can be used to make more informed decisions when setting dwell times in timetables.

在客流量大的车站，由于乘客行为和相互作用的变化，列车停留时间复杂且不一致。虽然有几项研究调查了影响停留时间的因素，并开发了预测模型，但这些模型往往难以准确预测高客运量条件下的停留时间。这对在拥挤的环境中规划有效的时间表提出了重大挑战。考虑到这种可变性，使用基于概率的方法来预测停留时间延迟可以提供更好的规划。虽然一些研究已经确定了停留时间概率分布函数，但它们通常不包括客运量水平作为变量，限制了它们在高密度车站的适用性。本文通过对实际运行数据的研究，揭示了高客流量车站停留时间预测的局限性。为了解决这一差距，本文提出了一个包含客运量作为关键变量的二元概率函数。这给了我们一个更可靠的框架来预测拥挤环境中的停留时间延迟。使用Kolmogorov-Smirnov （K-S）检验来验证二元停留时间函数。这显示了该函数预测实现目标停留时间概率的能力，这对于规划停留时间至关重要。此外，该模型可以与延误影响评估一起应用，促进进一步的风险评估框架，可用于在时间表中设置停留时间时做出更明智的决策。

{"title":"Train dwell time models for crowded metro stations using a bivariate distribution function","authors":"Natchaya Tortainchai , Taku Fujiyama","doi":"10.1016/j.jrtpm.2025.100538","DOIUrl":"10.1016/j.jrtpm.2025.100538","url":null,"abstract":"<div><div>Train dwell times at high-passenger-volume stations are complex and inconsistent due to variations in passenger behaviour and interactions. While several studies have examined factors affecting dwell time and developed models to predict it, these models often struggle to accurately predict dwell times under high passenger volume conditions. This poses significant challenges to planning effective timetables in crowded environments. Given this variability, using probability-based approaches to predict dwell time delay could provide better planning. Although some studies have identified dwell time probability distribution functions, they generally do not include passenger volume level as a variable, limiting their applicability in high-density stations.</div><div>This paper investigates actual operational data to present the limitations of predicting dwell times at high-passenger-volume stations. To address the gap, this paper proposes a bivariate probability function that incorporates passenger volume as a key variable. This gives us a more reliable framework for predicting dwell time delays in crowded environments. The Kolmogorov-Smirnov (K-S) test is used to validate the bivariate dwell time function. This shows the function's capability to predict the probability of achieving target dwell times, which is essential for planning dwell times. Furthermore, this model can be applied alongside delay impact assessments, facilitating a further risk evaluation framework that can be used to make more informed decisions when setting dwell times in timetables.</div></div>","PeriodicalId":51821,"journal":{"name":"Journal of Rail Transport Planning & Management","volume":"35 ","pages":"Article 100538"},"PeriodicalIF":2.7,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144858021","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Designing an optimized fueling infrastructure for a hydrogen railway system 为氢能铁路系统设计优化的加氢基础设施

IF 2.6 Q3 TRANSPORTATION

Journal of Rail Transport Planning & Management

Pub Date : 2025-06-02 DOI: 10.1016/j.jrtpm.2025.100524

Alessio Trivella, Amina Balha, Daniela Guericke

Hydrogen use is increasing in transportation, including within the railway sector. In collaboration with a governmental institution in the Netherlands, we study how to design an efficient hydrogen fueling infrastructure for a railway system. The problem involves selecting yards in a network for hydrogen fueling, assigning trains to these yards, locating hydrogen storage and fueling stations, and connecting them via pipelines. This key planning phase must avoid oversizing costly fueling infrastructure while accounting for track availability at yards and costs due to fueling operations. We formulate this novel problem, which has the structure of a nested facility location problem, as a mixed-integer linear program to minimize total annualized investment and operational costs. Due to the complexity of real-sized instances, we propose a matheuristic that estimates the infrastructural costs for each yard and train assignment by combining a constructive algorithm with a set covering model. It then solves a single-stage facility location problem to select yards and assign trains, followed by a yard-level improvement phase. Numerical experiments on a real Dutch case show that our approach delivers high-quality solutions quickly and offer insights into the optimal infrastructure design depending on the discretization of yard areas, number of trains, and other parameters.

氢在交通运输中的使用正在增加，包括在铁路部门。我们与荷兰的一家政府机构合作，研究如何为铁路系统设计高效的氢燃料基础设施。这个问题涉及到在一个网络中选择加氢站，为这些加氢站分配火车，定位储氢站和加氢站，并通过管道将它们连接起来。这一关键规划阶段必须避免成本高昂的加氢基础设施规模过大，同时考虑到堆场的轨道可用性和加氢操作的成本。我们将这个具有嵌套设施选址问题结构的新问题表述为一个混合整数线性规划，以最小化总年化投资和运营成本。由于实际规模实例的复杂性，我们提出了一种数学方法，通过将构造算法与集合覆盖模型相结合来估计每个场站和列车分配的基础设施成本。然后，它解决了一个单阶段的设施选址问题，即选择车场和分配列车，随后是车场水平的改进阶段。在一个真实的荷兰案例中进行的数值实验表明，我们的方法可以快速提供高质量的解决方案，并根据场站面积、列车数量和其他参数的离散化，为优化基础设施设计提供见解。

{"title":"Designing an optimized fueling infrastructure for a hydrogen railway system","authors":"Alessio Trivella, Amina Balha, Daniela Guericke","doi":"10.1016/j.jrtpm.2025.100524","DOIUrl":"10.1016/j.jrtpm.2025.100524","url":null,"abstract":"<div><div>Hydrogen use is increasing in transportation, including within the railway sector. In collaboration with a governmental institution in the Netherlands, we study how to design an efficient hydrogen fueling infrastructure for a railway system. The problem involves selecting yards in a network for hydrogen fueling, assigning trains to these yards, locating hydrogen storage and fueling stations, and connecting them via pipelines. This key planning phase must avoid oversizing costly fueling infrastructure while accounting for track availability at yards and costs due to fueling operations. We formulate this novel problem, which has the structure of a nested facility location problem, as a mixed-integer linear program to minimize total annualized investment and operational costs. Due to the complexity of real-sized instances, we propose a matheuristic that estimates the infrastructural costs for each yard and train assignment by combining a constructive algorithm with a set covering model. It then solves a single-stage facility location problem to select yards and assign trains, followed by a yard-level improvement phase. Numerical experiments on a real Dutch case show that our approach delivers high-quality solutions quickly and offer insights into the optimal infrastructure design depending on the discretization of yard areas, number of trains, and other parameters.</div></div>","PeriodicalId":51821,"journal":{"name":"Journal of Rail Transport Planning & Management","volume":"35 ","pages":"Article 100524"},"PeriodicalIF":2.6,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144189800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Identifying subway commuters travel patterns using traffic smart card data: A topic model 利用交通智能卡数据识别地铁通勤者的出行模式：一个主题模型

IF 2.6 Q3 TRANSPORTATION

Journal of Rail Transport Planning & Management

Pub Date : 2025-06-01 Epub Date: 2025-03-10 DOI: 10.1016/j.jrtpm.2024.100497

Peng He , Danyong Feng , Yang Yang , Zijia Wang

The paper presents a novel approach using Hierarchical Dirichlet Processes (HDP) integrated with K-means clustering to analyze public transit commuting behaviors using smartcard and POI data. The HDP, an unsupervised model, is designed to discern travel activities, however, little is done for this purpose. Our study proposed representing each trip using four features (duration, date, arrival time, and station type classified using POI-data) as inputs to the HDP model, which outputs the identification of specific activities such as home, work, and leisure. A comparison to other methods including trip frequency, activity duration, and Hidden Markov models demonstrates that our approach offers superior fit, as evidenced by lower perplexity and higher similarity metrics. To further refine the classification of commuting behaviors, we applied a two-step clustering algorithm that considers features such as regularity, temporality, and spatiality, resulting in the identification of strong and weak commuting behavior patterns. This classification provides urban planners with insights into the spatiotemporal characteristics of travelers in urban rail transit systems, thereby supporting more effective urban planning.

基于智能卡和POI数据，提出了一种基于分层狄利克雷过程（HDP）和K-means聚类的公共交通通勤行为分析方法。HDP是一种无监督模型，旨在识别旅行活动，然而，在这方面做得很少。我们的研究建议使用四个特征（持续时间、日期、到达时间和使用poi数据分类的站点类型）来表示每次旅行，作为HDP模型的输入，该模型输出特定活动（如家庭、工作和休闲）的识别。与其他方法（包括行程频率、活动持续时间和隐马尔可夫模型）的比较表明，我们的方法具有更好的拟合性，这一点可以通过更低的困惑度和更高的相似性指标得到证明。为了进一步完善通勤行为的分类，我们采用了一种考虑规律性、时代性和空间性等特征的两步聚类算法，从而识别出强弱通勤行为模式。这种分类为城市规划者提供了对城市轨道交通系统中旅客时空特征的洞察，从而支持更有效的城市规划。

{"title":"Identifying subway commuters travel patterns using traffic smart card data: A topic model","authors":"Peng He , Danyong Feng , Yang Yang , Zijia Wang","doi":"10.1016/j.jrtpm.2024.100497","DOIUrl":"10.1016/j.jrtpm.2024.100497","url":null,"abstract":"<div><div>The paper presents a novel approach using Hierarchical Dirichlet Processes (HDP) integrated with K-means clustering to analyze public transit commuting behaviors using smartcard and POI data. The HDP, an unsupervised model, is designed to discern travel activities, however, little is done for this purpose. Our study proposed representing each trip using four features (duration, date, arrival time, and station type classified using POI-data) as inputs to the HDP model, which outputs the identification of specific activities such as home, work, and leisure. A comparison to other methods including trip frequency, activity duration, and Hidden Markov models demonstrates that our approach offers superior fit, as evidenced by lower perplexity and higher similarity metrics. To further refine the classification of commuting behaviors, we applied a two-step clustering algorithm that considers features such as regularity, temporality, and spatiality, resulting in the identification of strong and weak commuting behavior patterns. This classification provides urban planners with insights into the spatiotemporal characteristics of travelers in urban rail transit systems, thereby supporting more effective urban planning.</div></div>","PeriodicalId":51821,"journal":{"name":"Journal of Rail Transport Planning & Management","volume":"34 ","pages":"Article 100497"},"PeriodicalIF":2.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A new look at the shape characteristics of optimal speed profile for energy-efficient train control considering multi-train power flow 考虑多列功率流的节能列车控制最优速度剖面形状特征的新研究

IF 2.6 Q3 TRANSPORTATION

Journal of Rail Transport Planning & Management

Pub Date : 2025-06-01 Epub Date: 2025-02-26 DOI: 10.1016/j.jrtpm.2025.100515

Yu Rao , Qiangqiang Liu , Qingyuan Wang , Tianxiang Li , Mingyu Zhang

The key point for the energy-efficient train control (EETC) in a multi-train system is effectively utilizing the output power of other trains. However, obtaining the optimal solution of the EETC problem considering multi-train power flow requires high-precision calculation of the adjoint variables, which is time-consuming. In this paper, we revisit the problem and introduce a speed volatility functional to analyze the shape of the optimal speed profile and the corresponding optimal control modes for the train under different external power and track gradients. Based on this analysis, a fast-solving algorithm is devised. Case studies are conducted to validate our theoretical results, and demonstrate that the proposed algorithm achieves a significant improvement in computational speed (over 99%) compared to the global optimal algorithm (Rao et al., 2023a) while ensuring the energy saving effectiveness.

多列系统节能列车控制的关键是有效利用其他列车的输出功率。然而，考虑多列潮流的EETC问题的最优解需要高精度的伴随变量计算，耗时长。在本文中，我们重新审视了这个问题，并引入了一个速度波动函数来分析在不同外部功率和轨道梯度下列车的最优速度轮廓形状和相应的最优控制模式。在此基础上，设计了一种快速求解算法。通过实例研究验证了我们的理论结果，并证明了所提出的算法在保证节能效果的同时，与全局最优算法（Rao et al., 2023a）相比，计算速度显著提高（超过99%）。

引用次数: 0

Weekly crew scheduling for freight rail engineers: A network approach 货运铁路工程师每周班组调度：网络方法

IF 2.6 Q3 TRANSPORTATION

Journal of Rail Transport Planning & Management

Pub Date : 2025-06-01 Epub Date: 2025-04-02 DOI: 10.1016/j.jrtpm.2025.100519

Jinhua Lyu, Jonathan F. Bard

Freight rail engineers and conductors have long faced unpredictable and inflexible work schedules, leading to on-the-job fatigue, compromised safety, and poor work-life balance. This paper aims to construct robust weekly schedules for these crew members to alleviate the pressures associated with irregular and unpredictable work hours. The scheduling problem is formulated as a multi-commodity network flow problem on a directed time-space graph. Both two-city and three-city districts are addressed. To account for the variability in travel times, a set of scenarios is defined in which demand is increased by up to 20% to build slack into the schedules. The results are validated using Monte Carlo simulation where 100 random weekly instances are generated for each city pair and key performance metrics assessed. Major findings show that (i) optimal weekly schedules can be constructed in minutes for engineers in crew districts with two cities, and in several hours for engineers in crew districts with three cities, (ii) different percentages of demand increase significantly affect the degree of robustness, and (iii) forming crew districts with three cities rather than two gives better results in terms of required number of engineers and trip coverage rates.

长期以来，货运铁路工程师和售票员一直面临着不可预测和不灵活的工作时间表，导致工作疲劳、安全性受损以及工作与生活的不平衡。本文旨在为这些船员构建健全的每周时间表，以减轻与不规律和不可预测的工作时间相关的压力。将调度问题表述为有向时空图上的多商品网络流问题。两个城市和三个城市的地区都有地址。为了考虑出行时间的可变性，我们定义了一组场景，在这些场景中，需求最多增加20%，从而在时间表中建立空闲。使用蒙特卡罗模拟对结果进行验证，其中为每个城市对生成100个随机的每周实例，并评估关键性能指标。主要研究结果表明：(1)两个城市的船员区工程师可以以分钟为单位构建最优周计划，三个城市的船员区工程师可以以几个小时为单位构建最优周计划；(2)不同的需求增长百分比显著影响鲁棒性程度；(3)三个城市的船员区比两个城市的船员区在所需工程师数量和行程覆盖率方面效果更好。

{"title":"Weekly crew scheduling for freight rail engineers: A network approach","authors":"Jinhua Lyu, Jonathan F. Bard","doi":"10.1016/j.jrtpm.2025.100519","DOIUrl":"10.1016/j.jrtpm.2025.100519","url":null,"abstract":"<div><div>Freight rail engineers and conductors have long faced unpredictable and inflexible work schedules, leading to on-the-job fatigue, compromised safety, and poor work-life balance. This paper aims to construct robust weekly schedules for these crew members to alleviate the pressures associated with irregular and unpredictable work hours. The scheduling problem is formulated as a multi-commodity network flow problem on a directed time-space graph. Both two-city and three-city districts are addressed. To account for the variability in travel times, a set of scenarios is defined in which demand is increased by up to 20% to build slack into the schedules. The results are validated using Monte Carlo simulation where 100 random weekly instances are generated for each city pair and key performance metrics assessed. Major findings show that (i) optimal weekly schedules can be constructed in minutes for engineers in crew districts with two cities, and in several hours for engineers in crew districts with three cities, (ii) different percentages of demand increase significantly affect the degree of robustness, and (iii) forming crew districts with three cities rather than two gives better results in terms of required number of engineers and trip coverage rates.</div></div>","PeriodicalId":51821,"journal":{"name":"Journal of Rail Transport Planning & Management","volume":"34 ","pages":"Article 100519"},"PeriodicalIF":2.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143759000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0