In response to the growing demand for rail transport, next-generation signalling systems are increasingly investigated by the railway community. In particular, the concept of Virtual Coupling (VC) is progressively gaining ground thanks to its potential ability to reduce safe train separation to less than an absolute braking distance. That enables trains to move synchronously in a vehicle-to-vehicle radio-connected convoy. One of the major concerns associated with this concept is the safe and effective control of trains in a convoy when considering varying train resistances and risk factors due to, e.g., sudden degradation in the train and communication performance. This paper develops a novel Predictive Artificial Potential Field (PAPF) approach for safe and effective real-time train control under realistic VC operations. The proposed approach uses a realistic homogeneous strip model of train motion. Moreover, it incorporates a dynamically changing safety margin to take into account risk factor occurrences, such as delays in train control and communication, or sudden emergency braking applications. A simulation-based assessment of the developed method is performed for a high-speed rail corridor in China. Results show that the proposed PAPF control algorithm effectively supervises the safe train separation, preventing activation of emergency brakes even when risk events occur. The method contributes to advancing the state of the art on VC train control.

Automatic Train Operation (ATO) aims to enhance punctuality, energy efficiency, and reliability by automating driving tasks. Specifically, for mainline railways, an ATO onboard component generates and tracks optimised train trajectories based on time targets or windows at critical network locations, known as timing points, across train routes. These timing points and their associated constraints are specified in the Train Path Envelope (TPE), computed to ensure conflict-free operations. The generation of TPEs relies on dynamic updates of the real-time traffic plan from the Traffic Management System and real-time train statuses (e.g., position and speed). Understanding how TPEs are affected by these updates is essential for effective ATO deployment. To address this, this paper proposes a sensitivity analysis using elementary effects of a TPE generation algorithm, evaluating its response to variations in real-time traffic plans and train status updates. A real-life case study on a Dutch rail corridor with heterogeneous traffic reveals that control timing points can be introduced into the TPE as headways decrease, to homogenise traffic by aligning speed profiles and thus resolving conflicts. Timing point locations remain mostly unchanged, while their associated time windows become more sensitive when placed further along the route. Operational tolerance, which defines the latest conflict-free passing time, becomes more sensitive to headway changes and the distance from the previous stop.

The dynamics of a moving train are usually described by means of a motion model based on Newton’s second law. This model uses as input track geometry data and train characteristics like mass, the parameters that model the running resistance, the maximum tractive effort and power, and the brake rates to be applied. It can reproduce and predict train dynamics accurately if the mentioned train characteristics are carefully calibrated. The model constitutes the core element of a broad variety of railway applications, from timetabling tools to Driver Advisory Systems and Automatic Train Operation. Among the existing train motion model calibration techniques, those that use operational data are of particular interest, as they benefit from on- board recorded data, capturing the train dynamics during operation. In this literature review article we provide an overview of the train motion model calibration techniques that have been published in the scientific literature between January 2000 and December 2021 and either use operational data or can be minimally adapted to use it. To this end, we present a critical overview of the existing train motion model calibration approaches, distinguishing online calibration that analyzes data on- the-go and offline calibration that analyzes historical data batchwise. We propose a research agenda and highlight some potential goals to be tackled in the near future: from devising accurate online calibrators for eco-driving applications to quantitizing the physical sources of parameter variation. Last, we discuss practical recommendations for practitioners and scholars inferred from the current state of the art.

Artificial Intelligence (AI) is becoming pervasive in most engineering domains, and railway transport is no exception. However, due to the plethora of different new terms and meanings associated with them, there is a risk that railway practitioners, as several other categories, will get lost in those ambiguities and fuzzy boundaries, and hence fail to catch the real opportunities and potential of machine learning, artificial vision, and big data analytics, just to name a few of the most promising approaches connected to AI. The scope of this paper is to introduce the basic concepts and possible applications of AI to railway academics and practitioners. To that aim, this paper presents a structured taxonomy to guide researchers and practitioners to understand AI techniques, research fields, disciplines, and applications, both in general terms and in close connection with railway applications such as autonomous driving, maintenance, and traffic management. The important aspects of ethics and explainability of AI in railways are also introduced. The connection between AI concepts and railway subdomains has been supported by relevant research addressing existing and planned applications in order to provide some pointers to promising directions.

In big cities, the metro lines usually face great pressure caused by huge passengers demand, especially during peak hours. When disruptions occur, passengers accumulate quickly at stations. It is of great importance for dispatchers to take passenger flow control into consideration for the traffic management to ensure passengers’ safety and to maintain their satisfaction. This paper proposes an integrated disruption management model, which incorporates train rescheduling and passenger flow control. In this model, the train services can be short-turned, cancelled and rerouted, while the number of passengers entering a station is managed by controlling the station gates with consideration of the capacities of platforms and trains. Moreover, the number of passengers arriving at a station is calculated according to the origin-destination matrices. The objectives are to recover the train operation to the original timetable as soon as possible and to minimize the waiting time of passengers outside the stations. With the interaction between train services, passengers and station gates, an iterative metaheuristic approach is proposed to solve the integrated disruption management problem. Based on the data of a Beijing metro line, numerical experiments are conducted to test the proposed algorithm. The results demonstrate the importance of integrated disruption management and the effectiveness of our solution method.

This paper proposes a novel train trajectory optimization approach for high-speed railways. We restrict our attention to single train operation scenarios with different scheduled/rescheduled running times aiming at generating optimal train recommended trajectories in real time, which can ensure punctuality and energy efficiency of train operation. A learning-based approach deep deterministic policy gradient (DDPG) is designed to generate optimal train trajectories based on the offline training from the interaction between the agent and the trajectory simulation environment. An allocating running time and selecting operation modes (ARTSOM) algorithm is proposed to improve train punctuality and give a series of discrete operation modes (full traction, cruising, coasting, full braking), and thus to produce a feasible training set for DDPG, which can speed up the training process. Numerical experiments show that an optimized speed profile can be generated by DDPG within seconds on a realistic railway line. In addition, the results demonstrate the generalization ability of trained DDPG in solving TTO problems with different running times and line conditions.

Employing regenerative braking in trains contributes to reducing the amount of energy used, especially when applied to commuter trains and to those used on very dense suburban networks. This paper presents a method to fine-tune the periodic timetable to improve the utilization of regenerative energy and to shave power peaks while maintaining the structure and robustness of the original timetable. First, a mixed-integer linear programming model based on the periodic event scheduling framework is proposed. A set of feasible timetables is determined and optimized with the aim of increasing synchronized acceleration and braking events at the same station, and maintaining the timetable robustness at the specified level. Next, a local search algorithm is developed to optimize the timetable such that the power peak value is minimized. The max-plus system model is adopted to estimate the delay propagation. Monte Carlo simulation is used to evaluate the utilization of regenerative energy and power peaks in random delayed circumstances. The proposed method was adopted to fine-tune the 2019 timetable for a sub-network of the Dutch railway. In the case of on- time scenarios, the optimized timetable increases the regenerative energy usage by almost 290% and decreases the 15-minute power peaks by 8.5%. In the case of delay scenarios, the optimized timetable outperforms the original timetable in terms of using regenerative energy and shaving power peaks.

Railway systems may be interrupted by unforeseen events that require quick replanning to a feasible new schedule. This paper deals with the train rescheduling problem on double-track lines. The rescheduling problem is regarded as a conflict detection and resolution procedure. Timed Colored Petri nets are adopted to model the railway system: places represent rail resources, and tokens represent trains. A conflict detection rule is established in accordance with the safety principles of railway operations to predict potential conflicts. A Petri-net-based conflict resolution algorithm adapted from the A* algorithm is designed to search for an optimal or a near-optimal feasible schedule. The algorithm takes into account the railway operational principles when generating new markings, so that the new schedule has less train delays and respects the safety principles. The approach is applied in a case study to a double-track corridor from the Dutch railway network. For small delays, the algorithm can make delayed trains recover to their scheduled timetable within seconds. For large perturbations, the solutions generated by the algorithm can effectively reduce train delays while ensuring traffic safety.

This paper presents a microscopic model for accurate prediction of train event times based on a timed event graph with dynamic arc weights. The process times in the model are dynamically obtained using processed historical track occupation data, thus reflecting all phenomena of railway traffic captured by the train describer systems and preprocessing tools. The graph structure of the model allows applying fast algorithms to compute prediction of event times even for large networks. The accuracy of predictions is increased by incorporating the effects of predicted route conflicts on train running times due to braking and reacceleration. Moreover, the train runs with process times that continuously deviate from their estimates in a certain pattern are detected, and downstream process times are adaptively adjusted to minimize the expected prediction error. The tool has been tested and validated in a real-time environment using train describer log files.