Generating initial population of evolutionary algorithms used in the process of weather ship route optimization requires the determination of the area where it may find the points of designated routes. The problem may be a need to sail around the continent, circumnavigate the islands, and the restrictions from the ice fields and other closed areas. Comparing routes to the rhumb line or great circle may be also impossible. It is proposed to determinate the preliminary route using Dijkstra's algorithm using land / ocean data of the GFS model. It will be used during generation an initial population on the ocean area in these cases

The article presents an algorithm developed for determining conditions of safe ship operation in a system of sea waterways consisting of three components, or subsystems: waterways, navigation and traffic control. A model of the optimization of sea waterway system parameters is describe

Basic principles of the fault tree analysis are discussed in reference with the marine power plant. The basics of qualitative and quantitative analysis of the fault tree are presented. Principal parameters being determined and the manner of their estimation by selected methods are given.

This article presents the underlying concepts of a mathematical model optimizing the routes of vessels carrying dangerous goods proceeding in the vicinity of passenger ferries. The method is based on the estimated risk of collision between a chemical tanker and a passenger vessel. Risk assessment was performed using three models. The first model determines the distance of the passing ships on the selected area on the basis of the AIS data. The second one is a stochastic model of navigational safety assessment, which provides statistical data on the probability of collision between the two chosen types of vessels. The third model determines the consequences of collisions between passenger ships and chemical tankers. The study defines the scope of the parameters affecting the objective function of vessel route optimization and their importance in the optimization problem

The goal of research presented in this article is to check if a neuroevolutionary method with direct encoding is able to be a part of autopilot of the vessel. One of the important tasks of vessel autopilots is to keep a course as straight as possible or to bring the ship back on the route as efficiently as possible. In this paper, the adaptive neuroevolutionary autopilot is described and tested on a simulation model of a ferry. Neuroevolution is a combination of two different but related fields of artificial machine learning: evolution and neural networks. The combined method is very flexible and can be applied to other ship control tasks. The results of computer simulation of the neuroevolutionary course-keeping system have been included.