In this paper a new reinforcement learning system for generating marshaling plan of freight cars in a train is designed. In the proposed method, the total transfer distance of a locomotive is minimized to obtain the desired layout of freight cars for an outbound train. The order of movements of freight cars, the position for each removed car, the layout of cars in a train and the number of cars to be moved are simultaneously optimized to achieve the minimization of the transfer distance of locomotive. Initially, freight cars are located in a freight yard by the random layout, and they are removed and lined into a main track in a certain desired order in order to assemble an outbound train. Q-Learning is applied to reflect the transfer distance of the locomotive that is used to achieve one of the desired layouts in the main track. After adequate autonomous learning, the optimum schedule can be obtained by selecting a series of movements of freight cars that has the best evaluation.
A New Design Method for Train Marshaling Evaluating the Transfer Distance of Locomotive
Lect. Notes Electrical Eng.
2011-12-11
14 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Train control system compatible method based on virtual marshaling
Europäisches Patentamt | 2022
|Commutation circuit, flexible marshaling unit and flexible marshaling method
Europäisches Patentamt | 2022
|Online coupling method and online un-marshaling method for train
Europäisches Patentamt | 2020
|Train automatic marshaling method based on train vehicle-mounted wireless network equipment
Europäisches Patentamt | 2015
|A New Reinforcement Learning for Train Marshaling with Generalization Capability
Trans Tech Publications | 2014
|