Journal of Rail Transport Planning & Management最新文献

Due to the complex temporal dependency and various external factors, it is challenging to capture its nonlinear and unsteady trends accurately. In addition, there are several inevitable errors in the traffic sensor record, including bias and noise. However, most recent works regard the record data as exact input ignoring the effect of unknown errors. In this research, a novel framework that integrates Ensemble Empirical Mode Decomposition (EEMD) method and the Bidirectional Gate Recurrent Units (BiGRU) model was proposed to eliminate noise and enhance short-term prediction. The proposed model is mainly divided into three stages. Firstly, the EEMD algorithm adaptively decomposes the nonlinear and non-steady passenger flow signal into several sub-signals, which share more straightforward fluctuation trends and higher correlation coefficients in the preprocessing stage. Secondly, in the feature recognition and extraction stage, knowledge of the transportation field and statistical theories are applied to analyze and extract the critical decomposed components. Finally, in the prediction stage, the stacked BiGRU can learn and extract information from the input features in both directions and use a multi-step prediction to output the final prediction result. A real dataset of the Chengdu metro system is included in our experiments. The experimental results reveal that the proposed EEMD-BiGRU model's prediction performance exceeds all benchmark models. The Root Mean Square Error (RMSE) of the proposed model is reduced by up to 28.29% compared to a single GRU model without EEMD preprocessing. Also, experiments show the effectiveness and robustness of the proposed method for predicting short-term passenger flow in metro systems.

To better understand the choice behavior of train route schedulers and to predict their choices for optimizing the annual construction schedule, prospective data for 2020 on train route decisions are analyzed using discrete choice models and machine learning classifiers. The choice alternatives include (i) partial cancellation of the train schedule at the start, (ii) in the middle or (iii) at the end of the itinerary of the train service, (iv) detour and (v) delay/ahead of time, and are modeled using 39 train-, construction site-, and infrastructure variables. The top nine attributes account for about 80% of variable importance, including the travel time from the departure station to the construction site, total or line closure, travel time from the construction site to the terminus, length of the train and effective line capacity.

The models are tested for 2021 and 2022 to verify whether they can be used to forecast choices in the following years. While Random Forest performs best in terms of prediction accuracy (2021: 60.8%; 2022: 58.6%), the improvements of about 6%-points compared to the Mixed Logit model are modest. Results indicate that a substantial amount of unobserved construction site heterogeneity is present, which Random Forest cannot capture either.

Stop-skipping and timetable synchronization are two effective strategies to reduce total passengers’ travel time in a transit network for subway operation. However, the majority of studies conducted on the topic do not consider stop-skipping strategy and timetable synchronization simultaneously. Thus, this article proposes a mixed-integer programming model considering both strategies simultaneously. The model is based on passenger smart-card data concerning the trains’ capacity to minimize total passengers’ waiting time and in-vehicle time and maximize the number of passengers who successfully reach their destination in a specific study horizon. Since increasing the number of trains, stations, or the study horizon, exponentially increases the size of the problem, seeking efficient methods to solve real-sized problems is inevitable. Therefore, a heuristic algorithm based on a genetic algorithm (GA) was developed to solve the model. A hypothetical example was solved with GAMS (CPLEX) in order to evaluate the performance of both the model and the used algorithm. Then, the results were compared with the results of GA. Finally, a large-scale, real-life case study based on Tehran rail transit network was used to evaluate the proposed models in this study and the genetic algorithm approach. The results indicated that the proposed model reduced each passenger’s travel time by approximately 4.78%, on average, and it also reduced each passenger’s transfer waiting time by approximately 32.4%, on average in a peak hour. Finally, it maximized the number of passengers who reached their destination successfully in the considered study horizon.

In public transportation systems, there is a linear relationship between the passenger quantities in a station and the headway of the vehicles. An optimized headway is beneficial for both passenger satisfaction and cost reduction, since reducing the headway will increase operational costs. The headway update starts from the first station and propagates to the other stations with a time delay, τ, originating from the train's travel time between the first station and the affected station. A well-defined model of the passenger quantities in the transportation line is required for tuning the headway efficiently. In this study, the transportation system is considered as a switched time-delayed system since the change in passenger quantities is dependent on the state of a train arriving at the station and travel time is a pure delay between stations. A sample metro line has been modelled as a switched time-delayed system and simulated on MATLAB Simulink® utilizing real-world data provided by Metro Istanbul. The results of the simulations of this new model have been compared to the traditional discrete event simulations of the Arena®. Both results were consistent and the simulation based on our switched time-delayed system mathematical model was significantly faster and dynamically adjustable.

Railway operations are vulnerable to delays. Accurate predictions of train arrival and departure delays improve the passenger service quality and are essential for real-time railway traffic management to minimise their further spreading. This review provides a synoptic overview and discussion covering the breadth of diverse approaches to predict train delays. We first categorise research contributions based on their underlying modelling paradigm (data-driven and event-driven) and their mathematical model. We then distinguish between very short to long-term predictions and classify different input data sources that have been considered in the literature. We further discuss advantages and disadvantages of producing deterministic versus stochastic predictions, the applicability of different approaches during disruptions and their interpretability. By comparing the results of the included contributions, we can indicate that the prediction error generally increases when broadening the prediction horizon. We find that data-driven approaches might have the edge on event-driven approaches in terms of prediction accuracy, whereas event-driven approaches that explicitly model the dynamics and dependencies of railway traffic have their strength in providing interpretable predictions, and are more robust concerning disruption scenarios. The growing availability of railway operations data is expected to increase the appeal of big-data and machine learning methods.

Railway operations are organized according to a complex interplay of resources and according to a rigid time separation of train runs over infrastructure elements. The system dynamics are complex, and span in time and space. We use in this work the concepts of macroscopic fundamental diagrams, or more in general the analysis in a density-flow-speed diagram, to analyse and describe realized railway operations.

Specifically, we review the state of the art in aggregated models of railway performance. We illustrate a possible application by means of a test case. We consider realized railway operations, aggregated on a railway line with heterogeneous traffic, as measured in a set of stations. We use a density-flow-speed diagram to represent the recorded operations, similar to the concepts of macroscopic fundamental diagram or network fundamental diagram. In this sense, it is a first try to estimate a macroscopic relationship, from realized data based on heterogeneous railway services with different stopping patterns.

The analyses show the challenges of aggregate operations for different railway stretches, from realized data. We report what is the influence of delays, represented in those diagrams by a shift of the operating point. Future promising directions of research are concluded from the analysis.

To address the ever-growing rail transport demand, the concept of Virtual Coupling train operations is gradually gaining ground within the railway industry. Thanks to a Vehicle-to-Vehicle communication, trains could be separated by less than an absolute braking distance and even form connected platoons to increase capacity at bottlenecks. However, a major concern about this concept regards the risk of safety violations in case of operational hazards pertaining to delays in train communication and control or emergency train stops. In this paper, the notion of dynamic safety margin is introduced for Virtual Coupling to dynamically adjust train separations so to always keep required safety distances also when hazardous operational events occur. The dynamic safety margin is embedded in a multi-state train-following model to analyse Virtual Coupling operations in presence of operational risk factors. A three-step methodology is applied in a real case study to fine-tune and verify the model, perform a sensitivity analysis, and identify capacity gains in several test scenarios including nominal and degraded traffic conditions. Results show that the use of a dynamic safety margin provides substantial capacity benefits to Virtual Coupling while respecting safe train distances even in case of sudden failures of the train control or communication systems. The notion of a dynamic safety margin can hence contribute to a safer version of Virtual Coupling operations and be considered by the railway industry in defining system requirements.

In this paper, the problem of speed tracing for automatic train operation is studied. A new Intelligent-PID controller is proposed in which four optimization algorithms: Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Differential Evolution (DE), and Imperium Colony Algorithm (ICA) for the best parameter tuning with the integration of a novel switching function are used. The algorithms are analyzed and specialized for different driving modes including: acceleration, cruising, braking and speed profile shift. By the use of a switch, the PID controller is tuned according to the best algorithm. The switching action is done through a slight change from the current position to the best values by transient values determined by the other algorithm outputs. The simulation results indicate the excellence of the proposed method. The performance of the suggested structure is compared with a single-mode optimization algorithm without use of the switch. The results of the comparison show that the proposed method can track the trajectory on all driving modes with very high accuracy.

Urban rail transit, regarded as the backbone of urban public transportation, can effectively solve the problems of urban traffic congestion and automobile exhaust pollution. However, due to improper planning, unreasonable station location often appears, which seriously affects the service access and mobility of rail transit. In order to improve the station spacing and passenger transport efficiency, a calculation model of station spacing for minimizing passenger travel time was established. In order to enhance the adaptability of the model in different cities, the grid road network and radial road network are considered when establishing the model. The results show that the station spacing is related to the passenger access/egress speed, the passenger travel distance, the maximum train running speed, the train stop time and the train acceleration. The influence of these parameters on the station spacing is obtained through the control variate method, and there are indeed obvious differences under different road network conditions. The research results can provide theoretical reference for station planning of new lines. Since the station spacing of the operated lines cannot be changed, this study can provide reference for skip-stop operation.

We present an optimization model which is capable of routing and ordering trains on a microscopic level under a moving block regime. Based on a general timetabling definition (GTTP) that allows the plug in of arbitrarily detailed methods to compute running and headway times, we describe a layered graph approach using velocity expansion, and develop a mixed integer linear programming formulation. Finally, we present promising results for a German corridor scenario with mixed traffic, indicating that applying branch-and-cut to our model can solve reasonably sized instances with up to a hundred trains to optimality.