Railway Station Planning Using ArtificialIntelligence Techniques (original) (raw)

Discrete optimization in public rail transport

Mathematical Programming, 1997

Many problems arising in traffic planning can be modelled and solved using discrete optimization. We will focus on recent developments which were applied to large scale real world instances.

Intelligent train scheduling on a high-loaded railway network

Algorithmic Methods for …, 2007

We present an interactive application to assist planners in adding new trains on a complex railway network. It includes many trains with different characteristics, whose timetables cannot be modified because they are already in circulation. The application builds the timetable for new trains linking the available time slots to trains to be scheduled. A very flexible interface allows the user to specify the parameters of the problem. The resulting problem is formulated as a CSP and efficiently solved. The solving method carries out the search assigning values to variables in a given order verifying the satisfaction of constraints where these are involved. When a constraint is not satisfied, a guided backtracking is done. Finally, the resulting timetable is delivered to the user who can interact with it, guaranteeing the traffic constraint satisfaction.

Advanced modelling of train operations in stations and networks

Transportation Research Part B: Methodological, 2007

When studying the papers on scheduling of railway operations published in international scientific journals, one gets the impression that many authors are not fully aware of the state-of-the-art of railway traffic engineering in different European countries, especially in Germany, France and Italy. Many papers dealt with scheduling of trains in low-frequency single-track networks typical for American rail freight transport and only a minority came from engineering disciplines. At the same time, substantial advances were being made in the theory and practice of railway operations and scheduling for highly complex, high density, scheduled rail networks in Europe and Asia by railway researchers, typically with an engineering background, but this work was not reflected in the international scientific journals for transport. Meanwhile many authors who had no close relationship with the railway industry made valiant efforts to solve scheduling problems by means of new mathematical programming techniques without having fully reviewed the current state of traffic engineering theory and practice. Furthermore, European transport deregulation policy, privatization of British Railways and European Railway Directives contributed, in first instance, to some confusion and fragmentation of the railway research community.

Optimization of railway operations using neural networks

Transportation Research Part C: Emerging Technologies, 1996

Railroad operations involve complex switching and classification decisions that must be made in short periods of time. Optimization with respect to these decisions can be quite difficult due to the discrete and non-linear characteristics of the problem. The train formation plan is one of the important elements of railroad system operations. While mathematical programming formulations and algorithms are available for solving the train formation problem, the CPU time required for their convergence is excessive. At the same time, shorter decision intervals are becoming necessary given the highly competitive operating climates of the railroad industry. The field of Artificial Intelligence (AI) offers promising alternatives to conventional optimization approaches. In this paper, neural networks (an empirically-based AI approach) are examined for obtaining good solutions in short time periods for the train formation problem (TFP). Following an overview, and formulation of railroad operations, a neural network formulation and solution to the problem are presented. First a training process for neural network development is conducted followed by a testing process that indicates that the neural network model will probably be both sufficiently fast, and accurate, in producing train formation plans.

Planning of the amount of trains needed for transportation by rail

Transport, 2007

The article analyses the importance of planning process of rail transportation. Railway planning problems are presented in this paper. Planning the railways for years, months, weeks or days ahead leads to substantially different problems; in this regard ...

The role of artificial intelligence in the development of railway transportation

Design of machines and structures, 2023

Artificial intelligence (AI) has been a revolutionary force in modern transportation systems. In recent years, AI has played an important role in the development of railway transportation. This paper explores the role of AI in railway transportation and the potential impact it may have on the industry. The paper begins by discussing the different types of AI technologies that are being used in railway transportation. It then examines the advantages of AI in railway transportation, including improved safety, increased efficiency, and reduced costs. Finally, the paper discusses the challenges associated with implementing AI in railway transportation and concludes with a discussion of future developments in this area.

Automatic Data for Applied Railway Management

Transportation Research Record: Journal of the Transportation Research Board, 2013

In 2009, London Overground management implemented a new tactical plan for AM and PM Peak service on the North London Line (NLL). This paper documents that tactical planning intervention and evaluates its outcome in terms of certain aspects of service delivery (the operator's perspective on system performance) and service quality (passenger's perspective). Analyses of service delivery and quality, and passenger demand contribute to the development, proposal, and implementation of the new tactical plan. It is found that NLL trains were routinely delayed en route and excessive dwell time is major cause. Near-random passenger incidence behavior suggests an even headway service may be more appropriate for NLL. The confluence of these analyses is confirmed by the corresponding excess journey time (EJT) results. Based on longitudinal analysis, evaluation shows that on-time performance increased substantially and observed journey time (OJT) decreased with the introduction of the new plan. EJT decreases by substantially more than OJT for the line as a whole. Overall, the effects of this implementation appear to have been positive on balance. This case study thus demonstrates the applicability of automatic data generally, and certain measures and techniques in London Overground specifically, to support tactical planning of an urban railway.

Real-time railway traffic management optimization and imperfect information: preliminary studies

2015 International Conference on Industrial Engineering and Systems Management (IESM), 2015

The real time railway traffic management seeks for the train routing and scheduling that minimize delays after an unexpected event perturbs the operations. In this paper, we propose a mixedinteger linear programming formulation for tackling this problem, modeling the infrastructure in terms of track-circuits, which are the basic components for train detection. This formulation considers all possible alternatives for train rerouting in the infrastructure and all rescheduling alternatives for trains along these routes. To the best of our knowledge, we present the first formulation that solves this problem to optimality. We tested the proposed formulation on real perturbation instances representing traffic in a control area including the Lille Flandres station (France), achieving very good performance in terms of computation time. 1998 ACM Subject Classification G.1.6 Optimization Keywords and phrases real time railway traffic management, mixed-integer linear programming, track-circuit, complex junction Digital Object Identifier 10.4230/OASIcs.xxx.yyy.p Conference/workshop/symposium title on which this volume is based on.

A decision support system for intermodal train planning

Train planning is the process of assigning containers to certain wagons on an intermodal train. Currently, there is limited decision support used for train planning in Australia leading to costly rehandles when loading trains. Intermodal terminals are highly integrated systems that create a difficult planning environment for computerised decision support systems. We have addressed this difficulty for the specific problem of train planning by developing a detailed mathematical optimisation model. This paper describes the model and how it was implemented within a software system called ITP -Intermodal Train Planner. Numerical experiments are presented to demonstrate the effectiveness of ITP.