A Bayesian network model to predict the effects of interruptions on train operations

Rapid online planning of train operation strategy in response to emergencies is a critical means of ensuring the safe and efficient operation for high-speed railways. However, it is difficult to achieve punctual, comfortable, and energy-saving operation under emergency scenarios due to the properties of high speeds, long inter-station distances, and the presence of long continuous gradients. This paper proposes an online planning approach of train operation curve based on dynamic programmingdeep Q network (DP-DQN). Firstly, the dynamic programming (DP) algorithm is used to optimize some train operation curves, and the state quadruples it contains are put into the memory buffer and incorporated into the reward function to guide and accelerate the network training. Then, the action mask from reinforcement learning is used to filter out the actions that cause the train speed to exceed the Automatic Train Protection speed, enabling fast and safe online planning of the speed curve under emergencies. Based on the actual data from a high-speed railway line, the proposed approach is evaluated in offline optimization. Experimental results show that, compared with mixed integer linear programming (MILP) and particle swarm optimization (PSO) algorithms, the DP-DQN approach yields small errors in train operation punctuality and stopping accuracy, better passenger comfort, and a reduction of energy consumption by 2.99% and 12.30%, respectively. Additionally, emergency scenarios involving temporary speed limit, traction/braking failure and emergency stop are simulated and analyzed. While DP-DQN results in slightly higher energy consumption than MILP in some scenarios, it significantly reduces train delays, ensures stopping accuracy, and completes online strategy planning within one second, which meets the real-time requirements of online planning.

China has recently developed a large-scale high-speed railway (HSR) network that not only revolutionizes the perception of long-haul transport but also fundamentally improves the emergency response capability of the country. This gives rise to a problem of scheduling a set of emergency trains within the predefined HSR timetable. According to different degrees of disturbance of the timetable, this paper identifies three kinds of solutions, named, ideal, quasi-ideal, and feasible solutions, to the problem. We define a “headroom” function for computing the maximum number of emergency trains that can be inserted between two adjacent regular trains without any disturbance, from which a linear algorithm for finding ideal solutions is derived. By identifying the scope of changes to each regular train, quasi-ideal and feasible solutions can be found based on the ideal solutions on a set of alternative timetables. Numerical experiments demonstrate that our method is very efficient for supporting near-immediate emergency responses. We have used the solution method to evaluate the emergency capacity of most HSR lines in China. In particular, we successfully applied the method to schedule emergency trains in the rescue operation of the 2015 Tianjin chemical explosion. The online appendix is available at https://doi.org/10.1287/trsc.2017.0794 .

Based on train operation data, Bayesian networks (BN) are used to model the cascading effects of traffic control actions and their influences (such as changes in train delays) for two and three consecutive trains. Influence factors are first determined to describe the interactions between train delays and control actions, i.e. the delay changes due to control actions over time and space. Considering the interdependence of these factors, their causal relationships are obtained, and the BN model’s connection paradigm is determined based on these causal ties. The BN structures are then proposed by combining domain knowledge and a data-driven method. The proposed models are tested on the train operation data from the Chinese high-speed railways. The results show that the proposed method exhibits a good fit for the train operation data and outperforms other conventional train operation models in terms of various evaluation metrics. Besides, the strength of train control actions’ cascading effects is investigated. It shows that section train control actions are stronger than those in stations, and both are considerably correlated with train delays and recovery times in sections and stations. Finally, a macroscopic model for control actions between several trains (more than three) is obtained based on the learned paradigm of the presented models and the cascading effects between two and three trains, demonstrating the model’s extensibility. The proposed models are intended to support traffic controllers with the estimation of future train delay change patterns, the expected control actions, and the cascading effects of control actions, and they are imperative for aiding the decision-making of controllers to manage high-speed railway traffic.

The increasing transport capacity experienced by high speed railway lines is promoting the implementation of different strategies to reduce their power consumption. Regenerative braking is a well-known approach in urban railway lines but little explored in high speed applications. The main objective of this paper is to analyze the regenerative braking potential of a conventional high speed railway line. To do so, the simulation of the Spanish high speed railway line Madrid- Valencia is performed considering rheostatic and regenerative braking strategies for two different traffic densities.

Today, about 59,000 km of specialised high-speed railway lines are in operation worldwide, about 20,000 km are under construction, and more than 50,000 km are planned to be commissioned. The maximum commercial speed of passenger trains has increased to 350 km/h. The world’s first high-speed freight trains have been designed and put into trial operation. Mastering advanced technologies in the field of high-speed railway transport, as before, is an indicator of the country’s development level. The construction of high-speed lines (HSL), along with others, solves an important problem on a global scale — it makes a significant contribution to environmental protection.We used the materials of reports and papers published on foreign information platforms; the results of the research work of Russian scientists and engineers in the field of increasing train speeds.In the BRICS countries, construction and design work on high-speed railways is underway, but given the unique conditions of each country, the pace of development is different. China is the leader of scientific progress in this sector of the railway industry, which attracts the attention of the world scientific community, including the Russian one.In Russia, according to the Transport Strategy up to 2030 with a forecast for the period up to 2035, it is envisaged to develop a network of high-speed railway lines with the unification of the largest agglomerations of the European part of the country into zones of two-hour accessibility.It is necessary to continue study and improve knowledge in the field of high-speed railway transport development.

Purpose: To increase the economic efficiency of high-speed railways (HSR). HSR infrastructure can be used not only for passenger traffic but also for high-speed freight transportation. The potential for using HSR for both passenger and freight traffic has not been sufficiently studied. This paper proposes the integration of highspeed and express passenger trains in the schedule of express container trains. Methods: Development of an integrated schedule of passenger and express container trains with specified speeds and priority parameters for each category of trains on a dedicated HSR with transition points to the general railway network; analysis of technical problems of its implementation. Results: The newly designed train schedule on the test section has illustrated that the passenger traffic capacity of the given high-speed railway line allows integrating several pairs of express container trains. In addition, it is possible to lay appropriate tracks for their non-stop passage. Thus, the fundamental possibility of implementing a mixed traffic model on a high-speed railway with high quality indicators for both passenger and freight traffic has been proven. Simultaneously, the main technical problems that require solutions for implementing the proposed mixed traffic model have been identified including the need to modify traction and non-traction rolling stock as well as improve fastenings for highspeed traffic. Practical significance: The obtained results can be used to develop models for organizing mixed traffic on the designed high-speed railways in order to increase the economic efficiency of their operation by providing high-speed transportation services for high-tariff containerized cargo.

The construction of twin cable-stayed railway bridges was undertaken near Changsha station of the Shanghai–Kunming high-speed railway (HSR) in China. Because of the inevitability of crossing the existing Wuhan–Guangzhou HSR line, the swing method was chosen so that the construction process does not interrupt the operation of the existing line. The objective of this study is to highlight the features of two cable-stayed bridges. Key structural components along with structural dimensions are discussed. Key issues associated with the structural design are analyzed, including the pylon–girder joint behavior, solar radiation temperature mode of through girder, track–bridge behavior, and the aerodynamic effects induced by high-speed trains. Finally, a brief account of the construction is given. The use of the swing method proved to be an effective solution to span existing HSR lines.

foreign matter intrusion on train operation safety is becoming increasingly serious. Based on a large amount of research data, among many factors affecting the operation safety of high-speed railway, the detection of personnel and foreign matter intrusion is difficult, and the preventive measures are limited, mainly because of its strong randomness and complexity. This paper systematically introduces the development status of high-speed railway line protection technology at home and abroad, especially summarizes the development status of high-speed railway line monitoring technology in China, and proposes a new design of foreign object intrusion detection and alarm device based on new sensors and networks, which has certain reference value for high-speed railway line protection and railway bureaus and departments in related fields.

Prediction of thermal regime and frost heave deformations of subgrade soils during non-stationary heat and moisture transfer

This paper studies the effect of wheel polygonalization and material properties on the fatigue failure of fastener clips in high-speed railway lines and puts forward the corresponding inhibition measures. Vibration frequencies excited by 24th-order wheel out-of-roundness (OOR) were analysed by on-site tests of the axle box vertical vibration acceleration. A finite element modelling method of polygon-shaped wheels was proposed, which was verified by comparing the field measurement with the dynamic simulation. The dynamic response of the fastener clip was simulated by using a rigid–flexible coupled model of the wheelset-track system. The effect of amplitudes as well as typical wavelengths of wheel OOR on the fracture of the clip was analysed based on the Miner fatigue damage accumulation ruler. The results show that when the wheelset ran at 237 km/h on the track, the 24th-order wheel OOR had no obvious effect on the Mises equivalent stress of the clip. When the amplitude of the 24th-order wheel OOR reached 0.225 mm and above, excited vibrations of about 1172 Hz were transmitted from the wheelset-rail system to the fastener systems, thus reducing the safe operating life of the clips. This phenomenon can be inhibited by setting a reasonable amplitude threshold for wheel re-profiling. Wheel eccentric wear (first-order OOR) and 12th-order OOR had lesser effects on the fatigue failure of the clip. The decrease of Poisson’s ratio or the increase of Young’s modulus of the material could cause the maximum Mises equivalent stress at the clip to increase, which might induce cracks, thus leading to the fracture of the clip. Therefore, during the production process, the Poisson’s ratio and Young’s modulus of fastener clips should be strictly controlled to ensure that they are within the permitted range.

Predicting the non-linear critical speed for high-speed railways in singular geotechnical scenarios

Objective: To consider the main approaches to organization of systems and communication networks on high-speed railway transport and provide cyber security on the basis of current international and home practice in the given sphere. Methods: Game-theory approach, hierarchy analysis method as well as topological transformation of stochastic networks were applied in the given study. Results: It was detected that a single realization of organizational and technical measures on cyber security cannot provide strong security from threats of cyber security during a long period of time; the latter is connected with constant development of data infrastructure, modification of methods, as well as the methods of attacks, potential attacker opportunities and other factors. Telecommunication networks’ security (TKS) of OJSC “Russian railways” and high-speed railway lines (VSM) from cyber impact is a systemic problem, for the solution of which fundamental research studies are to be conducted, aimed at the detection of basic patterns of information confrontation and directions of TKS cyber security provision and, subsequently, research and development activities for creating an automated communication control system of OJSC “Russian railways” and VSM, the constituent part of which is a subsystem of TKS information security. It is advisable to create an expert council based at regional transport universities, which provide extensive analysis conduct of systems and means of providing information security offered by the industry, as well as cyber security of OJSC “Russian railways” and VSM critically important systems including TKS. Practical importance: The realization of the suggested approach to OJSC “Russian railways” and VSM cyber security provision will make it possible to form the conditions for safe functioning of elements of information infrastructure, provide the creation, effective functioning and the improvement of cyber security control system, as well as to minimize damage from possible attack attempts.

With increasing train speeds, the emission of micro-pressure waves from tunnel portals, when high-speed trains enter the tunnel at the opposite side, can contribute significantly to the annoyance of residences near a high-speed railway line. In Europe at present no established assessment guidelines or standards exist explicitly devoted to this effect. Counter-measures can be applied to the tunnel portals or to the tunnel interior.

Seismic damage analysis of bridge-CRTS Ⅲ slab ballastless track system on high-speed railway

Following the appearance of urban shrinkage in Western countries, scholars have taken note of increasing amounts of urban shrinkage with significant regional characteristics in China in recent years. Focusing on the Yellow River Basin, this study comprehensively measured prefecture-level and county-level city shrinkage based on China’s fifth, sixth and seventh national census data. Furthermore, the spatiotemporal patterns, types and modes of urban shrinkage were analyzed, and the factors influencing urban shrinkage were explored using a multiple linear regression model and a sorting model. The study results show that the number of shrinking cities and the shrinking degree significantly increased at the prefecture and county levels in the last 20 years. The identified shrinking cities are concentrated in the upper and middle reaches of the river basin, spatially configured around major cities and along the high-speed railway line. The regional pattern shows a typical “core–periphery” characteristic. Peripheral shrinkage is the main mode in which cities shrink. The strength and speed of economic development and industrial transformation positively affect urban shrinkage; the ageing degree, high-speed railway opening and other factors negatively affect urban shrinkage.