Solution of the transport problem by artificial intelligence for maritime transport

Abstract

The purpose of this work is to solve the transport problem for sea freight using the Mashine Learning algorithms. An important task related to the work of transport is the organization of freight. In particular, the maritime freight network is a large, complex system whose modeling is compounded by additional difficulties due to the complexity of route maps and the variety of ship traffic. When investigating the characteristics of the sea freight system, it is generally advisable to use coarse models that introduce significant approximations and do not take into account a number of details. At the same time, a detailed study of isolated sections of the network uses an exact model, in which the connections of this area with others are not actually considered, but this area is explored in detail. In this case, one should not overlook the deviation of the model from the real network in the first case and the consequences of ignoring the linkages of the plots in the second. Building a model that accurately takes into account and describes all the details leads to an unreasonable complication of the design process, so in practice, the simulation always uses a number of assumptions and approximations of the real characteristics of the movement of ships, depending on the specific task. Four models are used to build an optimal cargo transportation system: the Transnational Cargo Model; Model of cargo transportation with dedicated initial port of departure of cargo; Model of cargo transportation with dedicated initial ports of departure and final port of cargo distribution; Model of cargo transportation on a circular chain of ports. Describe the route through n-ports using n-dimensional differential equations. The route conditions are given by the traveling wave equation. On the basis of these calculations the optimal route of movement of cargo ships is built. Conditions affecting freight traffic include: number of ports, quantity of fuel, final port of cargo, as well as distances between ports and intermediate ports. The scientific novelty is that the role of the person is reduced only to the observer of the system, which will simplify the calculations for freight, as well as help reduce the cost of fuel and human costs.