Container ship length was estimated using artificial neural networks (ANN), as well as a random search based on Multiple Nonlinear Regression (MNLR). Two alternative equations were developed to estimate the length between perpendiculars based on container number and ship velocity using the aforementioned methods and an up-to-date container ship database. These equations could have practical applications during the preliminary design stage of a container ship. The application of heuristic techniques for the development of a MNLR model by variable and function randomisation leads to the automatic discovery of equation sets. It has been shown that an equation elaborated using this method, based on a random search, is more accurate and has a simpler mathematical form than an equation derived using ANN.

The article concerns the problem of evacuation from passenger ships. It is important because it has not yet been possible to eliminate all the hazards associated with sea travel. In this paper, a concept of a method allowing to determine the arrangement of evacuation routes, for which evacuation time would be minimal, was presented. The genetic algorithm method was used in the calculations, and an original method of coding the considered problem was proposed. Sample calculations were performed to verify the correctness of the proposed algorithm. The results of applying the developed method to calculate the evacuation time on a real passenger ship are presented.

As the maritime transport of containers continues to grow and container ships change in terms of design and construction, it is important to ensure the appropriate level of safety for this type of transport. Over the decades, the size and cargo capacity of container ships have been changing, and so have their manoeuvring restrictions and required stability criteria. It seems that changes in the regulations, technological development and increased stability requirements are not yielding satisfactory results – the causes of container ship accidents continue to show similar patterns. The present article refers to the problem of ensuring safety in sea container transport, with a particular focus on cargo processes. Its purpose is to determine cause-and-effect relations leading to the loss of containers at sea, and to develop a model of loading that could significantly raise the level of safety of container transport. The article provides a general description of threats to ships related to weather conditions, loading methods or stability limitations. A statistical analysis of the occurrence of damage and/or loss of cargo from container ships was carried out and the risk of cargo loss was assessed on the basis of data from 2015‒2019. A Pareto diagram was used for this purpose. The authors present the concept of the container ship loading model, which may contribute to increasing the safety of shipping in the future.

This article concerns the assessment of the level of risk at the stage of construction of a seaport, with particular emphasis on selected adverse incidents that can significantly affect the timeliness of the investment. In this article, the matrix method was used to analyse and evaluate the level of risk, and statistical analysis and case studies were used to identify incidents occurring during the port construction project. This allowed the identification of incidents with the highest probability of occurrence during the port construction process and to determine their impact on environmental pollution and the timeliness and success of the investment. The risk analysis performed identified 15 typical incidents of technical nature. The determined risk level for these incidents is at a moderate level or lower, which can be considered acceptable. For all undesirable incidents the values of probability and loss levels have been averaged, because e.g., a fire can have an extremely different dimension and can cause a different scale of losses. Analysis presented in the paper indicate the need to develop procedures for proceeding during the implementation of significant technical tasks to minimize the level of risk of adverse incidents and their consequences.

This article concerns safety during ship docking operations. It presents its specificity for this type of operation, describes selected problems that may occur during its operation and identifies the main factors initiating extraordinary situations. The article presents 4 examples of accidents during docking operations in recent years. Cause and effect analysis was carried out and presented graphically. This analysis illustrated the occurring errors in the safety system during the docking operation.