Abstract
Th e article deals with formation of a traffic assignment forecast model on railway lines while introducing high-speed trains. The procedure for adjusting a forecast model based on a genetic algorithm with coding has been proposed. The main aim of the research is to improve a traffic assignment forecast model on railway lines while introducing high speed trains based on evolution modelling. Methods of fuzzy algebra, genetic algorithms and mathematic programming have been implemented to solve the scientific problem under consideration. It enabled to develop a procedure for adjusting a mathematical model based on an objective function which minimizes an average relative error in forecast and actual data of the testing set. Apart from a search for a fuzzy relation in a relational equation, the article proposes a method to adjust membership functions of output linguistic terms for a variable models (within a genetic algorithm) to improve the accuracy of adjustment for a forecast model. The adjustment procedure proposed has improved the forecast model accuracy. A relative error in a forecast model for the testing set is less than 10,0144 %. The results of the research can be implemented on railways while designing automated programme complex for traffic assignment forecast between cities in strategic planning.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
