Optimization of train routes based on neuro-fuzzy modeling and genetic algorithms

The article is devoted to the rationalization of the train routes on the railway network. It is proposed to improve the model of a decision support system based on the use of neuro-fuzzy modeling and a genetic algorithm intended for the formation of routes. Based on the improved model, it is possible to create an automated control system for the formation of optimal routes for passenger and freight trains. An optimization mathematical model of the railway network capacity control is also developed on the basis of the Ford-Fulkerson method. The model takes into account the limitations of the capacity of the sites of the landfill, the size of train flows (including speed) and the cost of following the train for each section. The implementation of the model will make it possible to more efficiently distribute train traffic on the railway network in the conditions of mass transportation of passengers and cargo. (C) 2019 The Authors. Published by Elsevier B.V.