Artificial intelligence seems to be a new point of view to classical problems that, in the past, could not be understood in depth, leaving certain gaps in each knowledge area. As an example of this, maritime accidents are one of the most recognised international problems, with clear environmental and human life consequences. From the beginning, statistical studies have shown that not only the typical sampled variables must be considered but the accidents are related to human factors that, at the same time, are related to some variables like fatigue that cannot be easily sampled. In this research work, the use of machine learning algorithms on over 300 maritime accidents is proposed to identify the relationship between human factors and the main variables. The results showed that compliance with the minimum crew members and ship length are the two most relevant variables related to each accident for the Spanish Search and Rescue (SAR) region, as well as the characteristics of the ships. These accidents could be understood as three main groups of accidents related to the general tendency to not meet the minimum number of crew members and its difference in the year of construction of the ship. Finally, it was possible to use neural networks to model accidents with sufficient accuracy (determination factor higher than 0.60), which is particularly interesting in the context of a control system for maritime transport.

It is a well-known fact that humans are subject to circadian alterations caused by the action of sunlight. This strongly affects their behaviour and skill, making them change their level of alertness from high at daytime to low at night-time. Taking into account this biological feature, and considering that commercial shipping is one of the oldest round-the-clock activities, raises the question whether bridge watchkeepers can carry out their tasks on night shifts with the same level of alertness as on day shifts. Furthermore, night bridge watchkeeping has to be performed in darkness or very dim light to improve the visual capacity of lookouts. A sample of vessel collisions was analysed and it was find out that this kind of accident tends to be more frequent and more serious during the darkness period of the solar day.

Despite the IMO’s efforts and the large quantity of research carried out over the years concerning the sudden loss of stability in fishing vessels, and even the damage done to merchant fleets due to cargo shifting, accidents with very relevant consequences continue to occur. This paper can be considered as a continuation of the recent research of authors which was carried out with ships in static conditions, with pure beam seas and without resistance. The aim of the present research is to provide a reference for ships’ operators to improve the ship’s behavior and seakeeping, to alter the ship’s loading conditions or the navigational parameters (heading and speed), and even be aware of the time available to carry out these modifications before reaching dangerous situations. For this, all sea state conditions were mathematically modelled for, including the ship’s rolling motion both in static and in realistic and dynamic conditions, with the waves influencing the vessel by coming from any direction. Relevant results of easy comprehension for ships’ operators are shown in each of the models, which were validated with a representative real case study.

General cargo ships are the most numerous in the merchant fleet. In these vessels, the stowage and securing of non-standardized cargo must be designed prior to being shipped. Furthermore, during sea navigation, the shipmaster must be confident that the secured cargo is safe in any weather conditions. One of the goals of the present research is to provide helpful guides to ship operators about the optimal navigational parameters. Despite different criteria being followed by the shipping industry to calculate the rolling motion accelerations, relevant accidents and losses related to an inadequate securing arrangement still occur. Firstly, this paper analyzes and compares the IMO’s and classification societies’ criteria, obtaining relevant results about the different safety levels along the ship’s dimensions. Secondly, it obtains a novel mathematical model of angular transverse acceleration, considering the sea state conditions and navigational parameters. For this reason, it investigates the combinations of optimization of these parameters. Finally, it proposes novel 3D surface graphs as being easy, useful, and quick to be interpreted by shipmasters when sailing in certain sea state conditions, to know if the limits of the maximum securing arrangement are exceeded and predict the ship’s optimal speed and heading in order to set out.

The present paper shows an original study of more than 163 ship accidents in Spain showing which of the usually employed variables are related to each type of vessel accident due to the lack of information in this region. To this end, research was carried out based on the Spanish Commission for Investigation of Maritime Accidents and Incidents (CIAIM) reports. Detailed combinatory ANOVA analysis and Bayesian networks results showed a good agreement with studies of other regions but with some particularities per each type of accident analyzed. In particular, ship length was defined as the more relevant variable at the time to differentiate types of accidents. At the same time, both the year of build and the fact that the ship meets the minimum crew members required were excellent variables to model ship accidents. Despite this, the particularities of the Spanish Search and Rescue (SAR) region were defined at the time to identify accidents. In this sense, although variables like visibility and sea conditions were employed in different previous studies as variables related to accidents occurrences, they were the worst variables to define accidents for this region. Finally, different models to relate variables were obtained being the base of deterministic dynamic analysis. Furthermore, to improve the accuracy of the developed work some indications were obtained; revision of CIAIM accidents scales, identification of redundant variables, and the need for an agreement at the time to define the classification limits of each identification variable.

This study presents a data-driven methodology to optimize the operational efficiency of a tugboat equipped with a Voith-Schneider Propeller (VSP) based on full-scale fuel consumption and vessel performance data. The objective is to identify optimal combinations of engine RPM and propeller pitch to reduce fuel consumption during low-demand phases without compromising maneuverability. Sea trials were conducted under controlled conditions using a dual flowmeter system and onboard speed measurements. The data enabled the construction of performance curves, efficiency ratios, and interpolated maps of fuel consumption. Optimal configurations were identified across defined speed ranges, and continuous efficiency zones were visualized through iso-consumption and contour plots. The results reveal a nonlinear relationship between propeller pitch, speed, and fuel demand, with maximum efficiency occurring at medium-to-high pitch values and speeds between 3 and 6 knots. This methodology provides a replicable tool for energy management in port operations and supports informed decisions during accompanying operations and standby periods. Efficiency differences over 300% between RPM–pitch settings were found, highlighting the operational impact of informed configuration choices. Moreover, the structured dataset and visual analysis framework lay the groundwork for future digital twin models aimed at enhancing operational efficiency in VSP-powered tugboats.