This paper presents the application of machine learning (ML) methods in setting up a model with the aim of predicting the energy efficiency of seagoing ships in the case of a vessel for the transport of liquefied petroleum gas (LPG). The ML algorithm is learned from shipboard automation system measurement data, noon logbook reports, and related meteorological and oceanographic data. The model is tested with generalized linear model (GLM) regression, multilayer preceptor (MLP), support vector machine (SVM), and random forest (RF). Upon verification of modeling framework and analyzing the results to improve the prediction accuracy, the best numeric prediction algorithm is selected based on standard evaluation metrics for regression, i.e., primarily root mean square error (RMSE) and relative absolute error (RAE). Experimental results show that, by taking an adequate combination and processing of relevant measurement data, RF exhibits the lowest RMSE of 17.2632 and RAE 2.304%. Furthermore, this paper elaborates the selection of measurement data, the analysis of input parameters, and their significance in building the prediction model and selection of suitable output variables by the ship’s energy efficiency management plan (SEEMP). In addition, discretization was introduced to allow the end user to interpret the prediction results, placing them in the context of the actual ship operations. The results presented in this research can assist in setting up a decision support system whenever energy consumption savings in a marine transport are at stake.

The aim of this article is to enhance performance monitoring of a two-stroke electronically controlled ship propulsion engine on the operating envelope. This is achieved by setting up a machine learning model capable of monitoring influential operating parameters and predicting the fuel consumption. Model is tested with different machine learning algorithms, namely linear regression, multilayer perceptron, Support Vector Machines (SVM) and Random Forests (RF). Upon verification of modelling framework and analysing the results in order to improve the prediction accuracy, the best algorithm is selected based on standard evaluation metrics, i.e. Root Mean Square Error (RMSE) and Relative Absolute Error (RAE). Experimental results show that, by taking an adequate combination and processing of relevant sensory data, SVM exhibit the lowest RMSE 7.1032 and RAE 0.5313%. RF achieve the lowest RMSE 22.6137 and RAE 3.8545% in a setting when minimal number of input variables is considered, i.e. cylinder indicated pressures and propulsion engine revolutions. Further, article deals with the detection of anomalies of operating parameters, which enables the evaluation of the propulsion engine condition and the early identification of failures and deterioration. Such a time-dependent, self-adopting anomaly detection model can be used for comparison with the initial condition recorded during the test and sea run or after survey and docking. Finally, we propose a unified model structure, incorporating fuel consumption prediction and anomaly detection model with on-board decision-making process regarding navigation and maintenance.

Having come into effect, the International Convention for the Control and Management of Ships’ Ballast Water and Sediments of 2004 requires ships to process their ballast water in accordance with specific standards. Different processing methods require different use of ship power, thus affecting fuel oil consumption, ships’ energy efficiency, and the ship economics in general. This paper presents the analysis and comparison of the economic viability of systems using two dominant ballast water treatment methods on merchant ships. The cost effectiveness of these methods, UV irradiation and electrochlorination, is compared to the standard efficiency of ballast water exchange using sequential flow method as a reference. The process efficiency is measured through fuel oil consumption on board. Taking into account possible variations in efficiency due to different designs and environmental constraints and assumptions, the findings are in favor of the electrochlorination method.

This review paper summarizes the legislative framework and the available technologies for ballast water treatment with regard to the approval process and relevant issues. The International Maritime Organization (IMO) sets the limits of organism concentration in ballast water allowed to be discharged into the sea. The 2004 International Convention for the Control and Management of Ships Ballast Water and Sediments is the first international document that introduced obligatory ballast water management and control. Even though ballast water treatment systems are not 100 % effective, they significantly reduce the risk of spreading of invasive species through ballast water exchange. An increased manufacturer interest in the system’s approval or development of new technologies is not expected in future because the procedure is time-consuming and expensive. The final choice of optimal ballast water treatment system depends on the ship owner or operator taking into account the price, type of the ship, whether it is a newbuilding or an existing ship, ballast system capacity and the seas where ships ply as well as harbours at which they call.

The integration of machine learning (ML) in marine engineering has been increasingly subjected to stringent regulatory scrutiny. While environmental regulations aim to reduce harmful emissions and energy consumption, there is also a growing demand for the interpretability of ML models to ensure their reliability and adherence to safety standards. This research highlights the need to develop models that are both transparent and comprehensible to domain experts and regulatory bodies. This paper underscores the importance of transparency in machine learning through a use case involving a VLGC ship two-stroke propulsion engine. By adhering to the CRISP-DM standard, we fostered close collaboration between marine engineers and machine learning experts to circumvent the common pitfalls of automated ML. The methodology included comprehensive data exploration, cleaning, and verification, followed by feature selection and training of linear regression and decision tree models that are not only transparent but also highly interpretable. The linear model achieved an RMSE of 23.16 and an MRAE of 14.7%, while the accuracy of decision trees ranged between 96.4% and 97.69%. This study demonstrates that machine learning models for predicting propulsion engine fuel consumption can be interpretable, adhering to regulatory requirements, while still achieving adequate predictive performance.