Abstract:

We performed a statistical analysis of the time series of the volumes of cargo transportation. Studies have shown sufficiently high accuracy of prediction relative to the actual values of a railway transport system based on the mathematical apparatus of artificial neural network. The experiment revealed that the mean absolute percentage error for the volumes of transportation of grain and the products of flour mills amounted to 5.56 %. Given that railway transport is a fairly inert system, indicator of 5.56 % is sufficient for management decision making. By having predicted the level of cargo transportation, we determined the required number of wagons of a particular type, which would conform to the conditions of transportation of this particular cargo. The optimal technology of organization of railway wagon flows implies minimization of operational costs for the transportation of cargo. In order to find the best variant to move the wagons, we proposed to take into account irregularity factor, or seasonality. The application on the railway network of the result of solution of the proposed model enables the dispatcher, the one who handles wagons, to make rational management decisions. Such technology makes it possible to take both long-term and operational decisions directly in the system of organization of railway wagon flows.To automate management decision-making by operational personnel of railway transport, we simulated organization of wagon flows using the software. The simulation was carried out on a virtual polygon of railways. The procedure for obtaining rational decisions when managing freight rolling stock is universal and makes it possible to perform calculations for polygons of any size and at arbitrary time of planning Author Biographies Tetiana Butko, Ukrainian State University of Railway Transport Feierbakha sq., 7, Kharkiv, Ukraine, 61050 Doctor of Technical Sciences, Professor Department of management of operational work

Keywords: