Search

• A novel multi-agent deep reinforcement learning method for solving the train timetabling problem. • A general environment that captures the system dynamics of the single-track and double-track railway systems. • A multi-agent actor-critic algorithm framework of centralized training and decentralized execution. • A case study demonstrating advantages of the proposed method over traditional counterparts. This paper proposes a multi-agent deep reinforcement learning approach for the train timetabling problem of different railway systems. A general train timetabling learning environment is constructed to model the problem as a Markov decision process, in which the objectives and complex constraints of the problem can be distributed naturally and elegantly. Through subtle changes, the environment can be flexibly switched between the widely used double-track railway system and the more complex single-track railway system. To address the curse of dimensionality, a multi-agent actor–critic algorithm framework is proposed to decompose the large-size combinatorial decision space into multiple independent ones, which are parameterized by deep neural networks. The proposed approach was tested using a real-world instance and several test instances. Experimental results show that cooperative policies of the single-track train timetabling problem can be obtained by the proposed method within a reasonable computing time that outperforms several prevailing methods in terms of the optimality of solutions, and the proposed method can be easily generalized to the double-track train timetabling problem by changing the environment slightly. [ABSTRACT FROM AUTHOR]

Engineering systems are complex, amongst others due to the interdependencies between actor and technical aspects. This complexity has consequences for the way of designing such systems and, in particular, for the decision-making process. Recognizing the impossibility of having an optimal system design in such complex systems, this article explores how a game theoretical characterization of a decision-making process assists in the organization and design of the process itself. In contrast to a game theoretical analysis, which results in optimal outcomes, the characterization is fed back to the designers of the decision-making process during the course of the process. The study analyses how the game concept characterization was used, i.e., which strategies were defined during the game theory interventions, and what the consequences of these strategies were for the design of the decision-making process. The design of a new safety system ERTMS for the Dutch railway sector is the context in which the study was performed. The contribution is a successful approach to complex decision-making in multi-actor systems by identification of multiple game concepts over time, with periodic feedback into the designing system, and not the actual decision-making itself. In short, it supported adapting to an actor focus on the process, it affected the role and responsibilities of the program management, it contributed to (de)coupling of issues, and it influenced the capability of creating awareness amongst actors of the urgency of the decision window. The paper ends with reflections on the experience of intervening in a decision-making process with game theoretical concepts. [ABSTRACT FROM AUTHOR]

Proper operation of railway vehicles is the basis for the functioning of a safe railway system. At the same time, it is not possible to talk about the safe use of a vehicle without adequately carried out maintenance processes. Due to legislative changes in August 2017, the maintenance system of railway vehicles has changed significantly. In most cases, it is the entities responsible for maintenance that are fully liable for the shape of the maintenance documentation, not the national security authority (in Poland the President of the Rail Transport Office) as has been the case so far. That is a big challenge for everyone involved in maintaining railway vehicles. The article presents the system of maintenance of railway vehicles as critical for the railway system safety, with the division into those registered in the National Railway Register and the unregistered ones. National and EU requirements for maintenance systems as well as the conditions for the implementation of “changes” in these systems have been presented, based, among others, on the results of the risk assessment of the threats they generate.

Cohesion policy is one of the European Union’s policies, which provides Member States with the possibility of financial support under the European Structural and Investment Funds (ESI Funds) as well as with the Connecting Europe Facility (CEF), to reduce disparities and encourage the development of less developed Member States. By funding through Cohesion policy funds, the European Union seeks to accomplish a prosperous economy by achieving appropriate European standards in the individual Member States. Cohesion policy emphasizes the development of transport and mobility, and in particular, the investment in key transport links and sections of international importance through the revitalization of railway infrastructure in line with European Union standards. The railway system of the Republic of Croatia has been under-invested for many years, which is why it has not followed the requirements and needs of the development of the transport market. Membership in the European Union has provided the Republic of Croatia with co-financing for the development of the railway system. This paper will analyse the current investments in the railway system and the development potentials that are planned to be achieved in the next programming period. Therefore, the purpose of this paper is to analyse the importance of the Cohesion Policy of the European Union for the development of the railway system of the Republic of Croatia in the Programming period 2021-2027. The analysis aims to identify opportunities for further development of the railway system as the ‘cleanest’ transport industry, guided by the need to reduce harmful emissions following the European Green Deal by using funds from the European Structural and Investment Funds. [ABSTRACT FROM AUTHOR]

This article deals with the problem of new threats that appear in areas that have not been affected by them so far. The considerations concern asymmetric threats and the railway system. The analysis of this issue was carried out on the basis of general information on the problem of asymmetric threats and the knowledge of the railway system, its operation and identified threats that can be attributed to the characteristics of asymmetric threats. The aim of the article is to draw attention to new phenomena that are beginning to affect transport on a global basis, including rail transport. [ABSTRACT FROM AUTHOR]

This article presents a novel transfer learning approach for evaluating structural conditions of rail in a progressive manner, by using acoustic emission monitoring data and knowledge transferred from an acoustic-related database. Specifically, the low-level layers of a model pre-trained on large audio data are leveraged in our model for feature extraction. Compared with conventional transfer learning approaches that transfer knowledge from models pre-trained on normal images, the proposed approach can handle acoustic emission spectrograms more naturally in terms of both data inner properties and the way of data intaking. The training and testing data used for rail condition evaluation contains two months of acoustic emission recordings, which were acquired from an in situ operating rail turnout with an integrated acoustic emission –based monitoring system. Results show that the evolving stages of rail from intact to critically cracked are successfully revealed using the proposed approach with excellent prediction accuracy and high computation efficiency. More importantly, the study quantitatively shows that audio source data are more relevant to the acoustic emission monitoring data than Image data, by introducing a maximum mean discrepancy metric, and the transfer learning model with smaller maximum mean discrepancy does lead to better performance. As a by-product of the study, it has also been found that the features extracted by the proposed transfer learning model ("bottleneck" features) already exhibit a clustering trend corresponding to the evolving stages of rail conditions even in the training process before any label is annotated, indicating the potential unsupervised learning capability of the proposed approach. Through the study, it is suggested that selecting source data more correspondingly and flexibly would maximize the benefit of transfer learning in structural health monitoring area when facing heterogenous monitoring data under varying practical scenarios. [ABSTRACT FROM AUTHOR]

The railway system is a very complex system of operations influenced by many factors. In this paper are given some considerations on the influence factors on improvement of the quality of the railway system operation. Considerations relate to several aspects in order to improve the quality of rail operations. The analysis is concerned with the results of the research on the proposal of measures for improvement of the quality of rail operations.

Due to the limited space on the train, the shielded cables were utilized to protect signal cables against influence by the disturbance from power cables which arranged in parallel with the signal cables. To reduce cable coupling, the cables are usually arranged close to train body. The influence of the body of the train should not be ignored. To analyze the coupling of shielded cables in the train, a hybrid method is proposed based on the circuit model. To solve the influence from the reflection of the train body, Green's function deduced from image theory is utilized. The current on the shielding layer is calculated by lumped circuit model, which is set up by admittance parameter matrix. And then, the coupling voltage on the core of shielded cable is given by using BTL function. Finally, a laboratory test case and a field test were investigated. Results of the proposed method were validated by measurement results.

Reducing passenger waiting time and energy consumption through train scheduling can have a great impact on improving the quality of service and energy efficiency from an operational view. However, there is a lack of studies of timetable optimization for connecting different modes of rail transit while considering the passenger transfer demand. This research considered the connection between a one-direction metro timetable and a railway timetable. Based on the spatiotemporal distribution of the demand of passenger flow, the optimal metro timetable for transfer passengers in different planning horizons was determined by optimizing and adjusting the following headway, running time of sections, and dwell time at stations. We proposed a multi-objective programming model consisting of three objective functions to minimize energy consumption, passenger waiting time at stations and the waiting time of transfer passengers at transfer stations. We used a fuzzy multi-objective optimization algorithm to solve the multi-objective programming model and added different weight factors to the three objective functions to obtain three optimal timetables, namely, timetables for energy-savings (E-timetable), passenger waiting time (WT-timetable), and transfer passenger waiting time (TWT-timetable); these timetables maximize energy efficiency, the quality of passenger service, and the transfer efficiency respectively. Finally, two practical cases based on real-world operational data were used to demonstrate the performance of the proposed models. The results showed that the three optimized timetables met the different requirements of the decision-makers; the combined use of the three optimized timetables can be used to guide actual operations.

This paper deals with the energy recovery resulting from the braking transient of trains arriving in a railway station, to feed a railway micro-grid that would be purposely connected to the railway traction circuit to feed the electrical infrastructure required for charging a fleet of electrical vehicles that are parked nearby the station and offered for providing train plus electric vehicle integrated mobility. Based on results of an experimental campaign intended to recording the mechanical quantities related to the braking transient of regional trains arriving in a medium-size station of the Italian railways network, this paper describes a suitable quasi-stationary model that allows the evaluation of the amount of energy that is recoverable over each single day of operation, as well as the micro-grid dynamic electric behaviour due to the sudden energy recovery transient in the railway catenary. The proposed railway micro-grid is discussed, particularly concerning the configuration of the dual-active-bridge converter for regulating the power flow from the railway catenary to the micro-grid during an energy recovery transient, as well as by considering the DC-DC converter that is used in the micro-grid, together with battery storage to provide voltage stability according to the micro-grid operating condition.

• The vehicle-ballasted track-subgrade interaction is formulated by finite elements. • The modelling versatility for track-subgrade FEM system has been improved. • Discrete element method has been introduced to model the railway ballast layer. • Extensive examples have shown the engineering practicality of this model. In this work a three-dimensional vehicle-ballasted track-subgrade interaction model is developed, where the vehicle is modeled as a multi-rigid-body system, the track-subgrade interaction is modelled by finite element method (FEM) with the rail modelled as beam elements, the sleeper and the subgrade layers modelled as solid elements, and the vehicle and the track-subgrade system are coupled by unified matrix formulations and solved simultaneously and time-dependently. As the modelling advancement, the versatility for FEM construction of track-subgrade systems has been promoted, where the elemental scale can be arbitrarily chosen without consideration of the node-to-node matching principle as the conventional methods; besides the vehicle and the track-subgrade systems have been coupled effectively by wheel-rail contact models. The applicability of various wheel-rail contact models has been discussed, and to reveal the effectiveness of this model in solving engineering problems such as the soil elasticity unevenness and the contact break of "hanging sleepers", numerical examples have also been presented with referencable conclusions. [ABSTRACT FROM AUTHOR]

High particulate matter (PM) concentrations have been measured on subway networks worldwide, with serious implications for human health. Such concentrations are known to be mainly produced by wear and friction of the metal parts and can accumulate in subways over time, causing a sort of age effect. Surveys have also shown that particle resuspension, caused by train arrivals and departures, significantly increases particulate matter concentrations. The research aim was threefold: (1) to provide a literature review on particulate matter concentrations in urban subway systems; (2) to measure the influence/incidence of the resuspension of PM2.5 and PM10 caused by subway train transit; and (3) to investigate the presence of a subway age effect. A sampling campaign was carried out on the station platforms of the Naples (Italy) Subway Line. The results show that particle resuspension significantly influences PM concentrations, reaching daytime values up to + 1200% greater than those at nighttime. Furthermore, to investigate any age effect, the results were compared with those of a previous study performed in 2014, concluding that, in the absence of tunnel cleaning and/or washing and with a standard ventilation system on station platforms, no statistically significant difference was observed between PM concentrations over the two measurement periods. These results suggest that the particles generated by mechanical wear-and-tear and friction processes constitute a very slow phenomenon. A useful solution could be tunnel washing, thereby removing fine particles that would no longer be available for resuspension. [ABSTRACT FROM AUTHOR]

The assessment of the power quality (PQ) could be a valuable tool to foster the efficiency of the railway systems. PQ is a well-addressed topic in conventional ac 50/60 Hz power systems, and many procedures, algorithms and measurement systems were presented in the international standards and widely discussed in the scientific literature. A less explored research field is the assessment of the PQ in the railway traction supply systems, in particular with reference to the dc and 16.7 Hz systems. The article explores this theme, proposing an extension of the definitions and of the standard measurement procedures for some of the main PQ indexes, well defined and widely used for conventional power systems, in order to be used also in all railway traction supply systems. The limits or difficulties of applicability are discussed with reference to measurements performed both on-board and in substation. The proposed procedures are applied to an experimental case of a real dc railway system with a large measurement campaign. [ABSTRACT FROM AUTHOR]

Issues about train driver fatigue are important in the safety of railway systems. This study investigates the subjective perception of fatigue of conventional railway system drivers. The multidimensional Rasch model was used to measure two subjective latent constructs, namely, perceived fatigue awareness and perceived fatigue control. Analytical results show that 21% of the train drivers are unable to control fatigue. Randomly assigned vehicles with various cabin control systems for work shifts is the most unlikely scenario for drivers to perceive and control fatigue. Our results demonstrate that a driver who is unmarried, holds a university degree and has limited driving experience exhibits a low perceived ability to control fatigue. Thus, segmented programs for fatigue risk mitigation should be developed for specific drivers. The findings of this study can help railway safety managers and government regulators in developing and evaluating a management system for driver fatigue risk. [ABSTRACT FROM AUTHOR]

Route planning for multiple destinations via a railway system (RS) is challenging, especially in a complex network with hundreds of stations and interchanges, resulting in a railway traveling salesman problem (RTSP), which is a variant of the traveling salesman problem (TSP). Limited attention has been devoted to solving the RTSP, despite the increase in the number of people using RSs and the added complexity of network expansions. An optimization algorithm and mathematical model based on the foraging behavior of bees and decision theory were used in this paper to identify the optimum RS route to multiple destinations before returning to the first station. Data collected from RSs in Japan and Malaysia were used to create 200 test cases (100 cases with each dataset), and the results were compared to specific solutions and the official optimum route planner to prove that the model is a promising approximation method. The solutions were evaluated and verified by comparing results from another 200 brute-force cases generated by the Wiley TSP Solver. The results obtained from the experiments prove the reliability and capability of the route planning and optimization solutions for RSs with different complexities and in different environments without the assistance of information technology. [ABSTRACT FROM AUTHOR]

The traction motor of trains, which is the core equipment in the railway industry, is a major noise source. As the protection of the environment becomes increasingly more important, the regulations regarding acceptable train noise are becoming stricter. Therefore, more studies on the traction motor of trains are required to find a method to reduce the noise. The existing studies on this topic are insufficient because of the high cost of producing prototypes and the absence of an aerodynamic noise analysis scheme with proven reliability. In this study, the noise performance of the traction motor of trains was evaluated using the numerical analysis of the lattice Boltzmann method, and its effect on the design variables of the traction motor was analyzed. To conduct this study, a reliable numerical analysis scheme was established by evaluating the performance of the base model through an experiment and numerical analysis and comparing the two results. In addition, seven major noise sources, including the size of the cooling fan, blade shape, number of blades, slot wedge shape, and clamp shape, were selected by analyzing the result of the numerical analysis of the base model. The effect of each design variable on the performance of the base model was analyzed by assessing the performance of cases that reflect the design modification of the chosen design variables. Based on the result, a complementary design model was designed to reduce noise, and the performance of this model was evaluated using numerical analysis and compared with that of the base model. From the results, it was confirmed that the newly created model produces much lower noise than the base model. [ABSTRACT FROM AUTHOR]

Copyright of Scientific Journal of the Military University of Land Forces is the property of Gen. Tadeusz Kosciuszko Military Academy of Land Forces and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Seismic hazard assessment (SHA) and evaluation of seismic risk (SR) require an adequate understanding of the actual distribution of earthquakes over magnitude, space, and time ranges. Neo-deterministic seismic hazard assessment (NDSHA) methodologies have been developed to improve the reliability and accuracy of reproducible seismic hazard maps. In the last decade, the application of NDSHA in many regions of the world has confirmed the availability of reliable and effective input for mitigating object-oriented earthquake risks NDSHA results have passed intensive testing by historical evidence and realistic modelling of scenario earthquakes. We used two NDSHA tools – (i) Unified Scaling Law for Earthquakes (USLE) and (ii) anisotropic propagation of the seismic effect – to evaluate SR for the Lake Baikal regional railroad system represented by Open Street Map (OSM) data of tracks, bridges and tunnels on the basis of seismic hazard maps of maximum macroseismic intensity expected in 50 years with 10%, 5%, and 1% probability of exceedance. We compare the achieved USLE−based results with the SR evaluations based on the General Seismic Zonation 2016 maps at identical levels of probability of exceedance. • Innovative assessment of seismic risk for the Lake Baikal Railway System (LBRS). • Maps based on probabilistic seismic hazard analysis overestimate damage and risks. • Our estimates expose doubling of expected overall reconstruction costs of GSZ2016. • Evidence in favour of neo-deterministic vs standard probabilistic hazard assessment. [ABSTRACT FROM AUTHOR]

Abstract Nowadays, the railway is considered as a means of fast, aggregate and secure transportation. The issue of the rail and wheel contact is one of the most fundamental aspects in the railway system since inappropriate interactions create problems such as wear and a negative effect in the dynamic functioning of the train. In this research, we analyze one of the most important phenomenon in a railway system which is the contact of the rail and wheel. This review is done in the scope of the most fundamental deteriorating aspect of the rail and wheel system, the wear. The wear in the contact of objects along with its occurrence between the wheel and rail is also analyzed.

Although rail is one of the most sustainable transport systems, there is still room to reduce its energy demand. In particular, during the braking of DC powered trains, a significant amount of energy is wasted. The recent developments in energy storage system technologies, combined with the widely used technique of regenerative braking, can considerably increase energy saving. This paper explores this theme, quantifying the amount of braking energy that can be potentially recovered in a real case study, starting from the experimental data measured on-board train. A simplified numerical model of the recovery process has been implemented. Adopting it, the energy that can be saved, with one or two energy storage systems, has been quantified for each possible position along the track. The procedure allows to determine the optimal position. Further findings about the impact of voltage level on the efficiency of the recovery process have been reported. The optimal level of voltage has been determined, also considering the additional losses in the catenary, both during the traction and braking phase of the train. Moreover, it allows dimensioning of stationary storage systems considering two different energy management strategies and their impact on the peak of stored energy. The proposed approach will be presented with reference to the concrete case of a specific route on the Italian rail network, analyzing a train in normal commuter service and the obtained results will be discussed. In the best situation, about the 73% of the braking energy can be recovered.

Copyright of e-GFOS is the property of Electronic Journal of the Faculty of Civil Engineering Osijek-e-GFOS and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

• Human reliability assessment is an essential work to guarantee the safety of locomotive driving process. • It is imperative to overcome the deficiencies of HEART and obtain a more accurate APOA. • A hybrid HEART method is proposed to fuse multi raters' opinions to EPCs determination and APOA for each corresponding EPC. • Monte Carlo simulation is used to validate the hybrid HEART method. Human reliability assessment is an essential work to guarantee the safety of locomotive driving process. Human Error Assessment and Reduction Technique (HEART) is a well-known approach applied to determine human error probability (HEP). However, the deficiencies of HEART are that the list of Error-producing conditions does not include many relevant railway operating performance shaping factors, and HEART does not provide the practitioners with a concrete method to determine the assessed proportion of affect (APOA), which force a heavy reliance on the judgement of single rater in the field. To overcome this problem and to obtain a more accurate APOA, we propose a hybrid HEART method which utilizes the evidence theory to fuse raters' opinions to EPCs determination and APOA for each corresponding EPC and quantify the subjective judgment. A complete locomotive driving process is performed to evaluate HEP. Finally, we apply Monte Carlo simulation to obtain system reliability and validate proposed method. The calculated results are consistent with the experience and knowledge of safety management and simulation results. This hybrid HEART approach is useful to reduce the likelihood of occurrence of errors, and improve the overall safety level in locomotive driving operation and other industries. [ABSTRACT FROM AUTHOR]