Search

This study reviewed the status quo of research on machine learning (ML), including deep learning, in the rail industry. This study conducted a scientometric analysis and critical review of 640 papers selected from 12,675 web-crawled papers. The extensive and complex networks of topics, researchers, and countries were analyzed using the Louvain method, a co-occurrence keyword analysis, a degree centrality analysis, and other network analysis methods. The results indicate that the majority of studies of ML in the rail industry focused on maintenance activities and traffic management, and mainly targeted rolling stock, rails, and passengers. Overhead contact systems, including catenaries, are a high-demand objective for ML-based maintenance. Although analyses of tunnels and stations remain rare, passenger flow prediction, station air quality estimation, shield tunneling performance improvement, and ground settlement are areas of high importance. Geographically, China, the US, and the United Kingdom lead ML studies in the rail industry, and the level of collaboration is higher among European countries than among countries on other continents. Future challenges include ensuring the security and stability of ML, along with considering novel mindsets, the black-box effect, improvements in ML techniques, and resource overload when introducing ML technologies. [ABSTRACT FROM AUTHOR]

Pollution usually accumulates on the surface of the insulator rapidly on high‐speed electric multiple units (EMUs) under operation condition, and the flashover can occur frequently, especially when the EMUs is running on a high‐altitude line. To solve the problem, this paper proposes the calculation method of insulator withstand voltage under the condition of non‐uniform fouling distribution of high‐speed airflow based on the characteristics of high altitude of Lanzhou‐Xin Line in China, and gives the design and test verification of insulator support insulator for 3500‐km altitude. The design and test verification of the supporting insulator of the rolling stock applicable to 3500 km altitude are presented. The result shows that the insulator should be reliable operation on 4430‐km high altitude area if the insulator structure height is 430 mm, the creep distance is 1250 mm. The anti‐pollution performance is fine in high‐speed wind if the radiuses of the large and small shed of the insulator are 196 and 145 mm, respectively, and the shed spacing is 45 mm. The 50‐Hz withstand voltage of the developed insulator is 131 kV and the light impulse voltage is 228 kV which is suitable for lines running on 3500 m. This research provides a theoretical basis and data to support the safety of high‐speed rolling stock in high‐altitude areas. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Railway Science & Engineering is the property of Journal of Railway Science & Engineering Editorial Office 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.)

In an urban rail transit line, train services are performed by the rolling stocks that are initially stored at depots. Before the start of the operation period, rolling stocks consecutively leave the depots and run without passengers (deadhead routing) to the origin station of their corresponding first departure train service in an operation day (first train service) using either direct or indirect routes. This paper investigates the rolling stock deadhead routing problem in an urban transit line with multiple circulation plans, depots, and rolling stock types. Given the rolling stock circulation plans, the problem is to identify a deadhead route for the rolling stock required by the train services to cover the initial operation. By pregenerating all direct and indirect candidate deadhead routes in a polynomial manner, the problem is then nicely formulated as a mixed integer linear programming (MILP) model to minimize the total deadhead mileages. A real-world case from the urban rail transit line 3 of Chongqing in China is adopted to test the proposed method. Computational results demonstrate that the problems of large-scale instances can be quickly solved to optimality by commercial optimization solvers on a personal computer. In addition, our optimization method is better than the empirical practices in terms of the solution quality. Meanwhile, alternative measures can further decrease the total deadhead mileages according to the proposed model, e.g., opening idle switch stations and prolonging the time that is used for the rolling stock departure. Finally, the model is further extended to consider operating costs, and more computation cases are tested for better adapting to the practical operating conditions. [ABSTRACT FROM AUTHOR]

With the improvement of railway running speed, the safe running of locomotive and rolling stock is particularly important. At present, China has built a series of world-leading high-speed railways with speeds of 350Km/h. With the increase of high-speed train running speed and actual traction capacity, higher requirements for high-speed railway operation safety are put forward. Braking is a very important problem for electric locomotive whether it is in the process of high speed or heavy load. At present, the braking devices of electric locomotives are mainly cast iron brake shoes, which are made of cast iron or other materials to produce braking force through the mechanical friction between the brake shoes and the wheel tread. However, there is no detection of brake working condition in the online detection of electric locomotive operation. This paper analyzes the technical research status of brake shoe of electric locomotive, and analyzes the shortcomings of existing technology. Based on the current technical background, a monitoring system for brake shoe of electric locomotive is designed, which provides a firm foundation for reliable braking of electric locomotive. [ABSTRACT FROM AUTHOR]

In high-speed rail networks, train units are scheduled to periodically meet all maintenance requirements while at the same time continuing to serve all scheduled passenger trips. Motivated by the trip demand variances on the days of every week in China, this paper studies a weekly rolling stock planning (W-RSP) problem that aims to optimize the rotation plan for the train units on each day of a week, so as to minimize their operating cost, including any (un)coupling costs and maintenance costs. We model the W-RSP on a newly developed rotation network by adopting particular nodes and arcs to address the (un)coupling operations of train units, and then propose an integer linear programming formulation for the problem. To solve this formulation, we develop a customized branch-and-price algorithm, which relies on a reduced linear programming relaxation for computing the lower bound, embeds a diving algorithm for computing the upper bound, and integrates advanced branching rules for effective explorations of the solution space. Computational results validate the effectiveness and efficiency of the proposed solution algorithm, which is able to solve large instances with up to 5034 trips to near-optimality. • A weekly rolling stock problem integrating rolling stock rotation and maintenance routing decisions. • A set-covering-like integer programming formulation based on a newly developed weekly rotation network. • A customized branch-and-price algorithm to solve the weekly rolling stock problem. • Conduct extensive numerical experiments to validate the effectiveness and efficiency of the solution algorithm. [ABSTRACT FROM AUTHOR]

High-speed railway in china embraced rapid development in recent years. The operating environment of high-speed railway in china is unique, containing long routing of high-speed trains, low temperatures, corrosive and sand environments. As an important safety component of rolling stock, the safety and reliability of the wheels is of deep concern and high value. It is significant to carefully study and systematically summarize the damage from different failure types in high-speed railway wheels under current conditions, and determine the influencing factors and mechanisms of wheel failures in order to improve railway operation safety. In this paper, the damage forms of high-speed railway wheels in China are introduced, and the main influencing factors of wheel failure are discussed in combination with wheel damage characteristics. What's more, damage mechanism is analyzed aiming at providing theoretical references for reducing failure rate and improving train operation quality. • Main influencing factors and damage characteristics of high-speed railway wheels failure are discussed. • Brittle non-metallic inclusions at a depth of 10-20 millimeters under the wheel tread are the main cause of the rim crack. • Sliding spalling in wheel tread is caused by the hard and brittle martensitic phase at the shelling position. • Foreign particles show greater hardness, when they pressed in, plastic deformation and micro cracks occur in wheel matrix. [ABSTRACT FROM AUTHOR]

• A two-stage approach for considering maintenance requirements when scheduling rolling stock. • A computational study using two actual instances provided by the Chinese High Speed Railway. • Verified improvements of approximately 10% compared to existing manual approaches. Efficient rolling stock schedules have always been the focus of railway companies. At the Chinese High-Speed Railway, rolling stock scheduling is usually done manually by dispatchers. Such an approach often makes it difficult to quickly obtain an optimal rolling stock schedule that can be used to operate the proposed timetable and which is also feasible with respect to the rolling stock maintenance requirements. In this paper, we consider the problem of rolling stock scheduling with maintenance requirements and propose a heuristic approach that decomposes the problem into two main stages. In the first stage, the maintenance restrictions are ignored and a conventional Mixed Integer Programming model is used to generate multiple candidate rolling stock schedules. In the second stage, we check to see whether any of the candidate rolling stock schedules are feasible when maintenance restrictions for the individual rolling stock units are also considered. Checking a candidate rolling stock schedule can be performed using an assignment problem. To provide some structure to the search, candidate rolling stock schedules generated in the first stage are sorted in descending order according to their objective values. The two stages can be iteratively performed to avoid generating all schedules in the first stage before proceeding to the second stage. We analyze the performance of the proposed approach on real-life instances provided by the Chinese High-Speed Railway. These instances focus on the railway network within the Zhengzhou Group, which is one of the busiest transportation networks in China. Comparisons with the manual approach that is currently used in practice show that the proposed approach yields far superior schedules. The optimized schedules improve rolling stock efficiency and lead to a reduction in operating cost of approximately 10.5%. [ABSTRACT FROM AUTHOR]

Urban rail transit train operation plan is a comprehensive production plan encompassing line planning, timetabling, and rolling stock scheduling. In order to solve the problem of infeasibility of the line plan and timetable because the number of rolling stocks could be only precisely considered in the rolling stock scheduling. An integrated optimization solution is proposed which considers the line plan, timetable, and rolling stock schedule. Candidate service routes are generated according to the layout of the turn-back stations. Considering the constraints of operation and passenger flow demand, an integer nonlinear programming model is established to minimize the cost of operation and passenger waiting time. The model complexity is analyzed and based on its decomposability a deterministic search algorithm is designed. Taking Chongqing Metro Line 3 in China as an example to verify the effectiveness of the proposed model and algorithm. Compared with the train operation plan based on manual experience and compiled by stages, the integrated optimization model can better improve the quality of train operation plan. [ABSTRACT FROM AUTHOR]

It is of great practical significance to save train traction energy for reducing the operation cost of urban rail transit. The energy-efficient train scheduling without combining with train circulation planning may inadvertently increase the other cost of rolling stocks, and finally lead to an increment of the total operation cost. This paper studies the integrated problem of energy-efficient train scheduling and train circulation planning for urban rail, and aims to reduce the total operation cost of rolling stocks including energy consumption. Its main challenge is to simultaneously solve three subproblems, namely the saving of train's traction energy in each rail section, the utilizing of regenerative braking energy and the optimizing of train circulation plan. We construct an optimization model to simultaneously optimize schedule and train circulation plan. Based on the designing of a strategy to create the train circulation plan for each train schedule, an efficient particle swarm algorithm is formed to solve our proposed model. The numerical experiments based on Guangzhou Metro Line 9 of China illustrate that the collaborative optimization can reduce the total operation cost of trains by 4.48% compared with the initial train schedule. • Integrate train circulation planning with energy-efficient train scheduling. • Optimize trains' traction strategies to reduce traction energy consumption. • Regenerative braking energy can be utilized in the same substation to save energy. • The effectiveness is demonstrated in a real-word case. [ABSTRACT FROM AUTHOR]

With the planning and progress of the construction of the trans-Eurasian high-speed rail (HSR) network, it becomes an important issue for Chinese contractors to enter the European HSR market. Facing the world's most competitive contractors and their high technology levels, Chinese contractors will need to know their advantages and disadvantages, so as to make necessary improvements. In this study, contractors for HSR are divided into two groups: construction contractors and rail equipment suppliers. In order to evaluate the competitiveness of HSR contractors, a Grey-BPNN model that combines the grey relational analysis and backpropagation neural network (BPNN) is proposed. The Grey-BPNN model is expected to analyze the overall competitiveness of Chinese contractors in the European HSR market and provide informative decision support for them. The study results show the following: (1) in the field of HSR construction, the competitiveness gap between the top-tier Chinese contractors and the most competitive international contractors is small. Chinese contractors' competitive advantages lie in medium- and low-technology-level projects, with a strong development potential. However, they highly depend on Chinese domestic market and lack in intangible resources, like management ability and market development ability; (2) for rail equipment suppliers, China Railway Rolling Stock Corporation (CRRC) ranks among the top-tier leaders of the international market. CRRC's greatest competitor in the European HSR market is Siemens, and CRRC is much more competitive than others in the sustainable development capability. However, CRRC needs to increase the quantity of patents and Research and Development (R&D) expenditures in transportation. As a weak transportation patent holder, CRRC has a potential risk of getting intellectual property litigations in the European HSR market. [ABSTRACT FROM AUTHOR]