No abstract

Purpose. The scientific paper involves formalizing the process of building a plan for the operational work of the marshalling yard in the conditions of processing carloads with dangerous goods. The developed mathematical model is implemented in the form of an intelligent planning system that will minimize both operational costs and technological risks during the work of the marshalling yard. Methodology. Based on the analysis of modern approaches to the management of transport systems under risk conditions, a mathematical model has been formed that includes the objective function of technological costs associated with all the main technological operations that are performed at the marshalling yard: reception, disbanding, form and departure of trains, accumulation of cars, processing of trains containing cars with dangerous goods, operations with local cars. In addition, the model also contains an objective function of the risk exposure, which also requires minimization in order to minimize the risk of accidents and their consequences when operating cars with dangerous goods. The model should be optimized under certain conditions that correspond to the technological features of the marshalling yard and which were formalized as a system of constraints. Optimization of the model is proposed to be carried out using methods of multiobjective optimization based on a genetic algorithm of a special type. Findings. A mathematical model is created that allows in an automated mode to build an operational plan for a marshalling yard operation with simultaneous consideration of two criteria: operational costs and risk exposure. The model was implemented as part of the created software product with the use of which the simulation was carried out. Originality. An intelligent planning technology has been developed that uses multiobjective optimization methods and allows finding a compromise solution while taking into account both the criterion of operational expenses and the risk exposure one in the conditions of handling carloads with dangerous goods. Practical value. During the simulation it was revealed that the effectiveness of the proposed technology of intelligent planning based on the developed model in comparison with the traditional planning technology is about 6.5% by the criterion of operating costs and about 8% by the criterion of the risk exposure.

No abstract

In this paper we consider the problem of distributing empty freight cars in a railway polygon. We show how the process can be improved using an optimization model. The optimization model can be characterized as a combination of minimum-cost flow problem with vehicle routing problem. In general, problem of empty railroad car distribution between stations and definition of way-freight train route is presented as integer combinatorial optimization problem. Computational tests show that the model can be solved in acceptable time for real size problems, and indicate that the model generates distribution plans that can improve the quality of the planning process.