Zbigniew Matuszak

The reliability of ocean-going ship engine fuel systems is crucial for the safety and continuous operation of vessels. Failure of this system can lead to serious operational and economic consequences; therefore, effective diagnostics and failure prediction are essential elements of modern fleet management. This paper presents an analysis of the reliability of fuel systems based on operational data from ten bulk carriers operated by Polska Żegluga Morska in Szczecin. The analysis combined classical statistical methods with artificial intelligence algorithms to develop a hybrid diagnostic and forecasting framework. The Weibull lifetime distribution was applied to estimate time-to-failure parameters, revealing mixed failure mechanisms—random failures (k < 1) and aging-related processes (k > 1). Using the k-means algorithm, ships were automatically classified into two reliability groups: high-failure-rate units and stable operational vessels. Individual linear regression models were then developed for each ship to forecast the time to the next failure, achieving satisfactory predictive performance (R² > 0.75 for most vessels). Sensitivity analysis quantified model robustness under different disturbance scenarios, yielding mean Relative Prediction Deviation (RPD) values of approximately 65% for Missing Data, 60% for False Failure, and 26% for Data Noise. These results confirm that the proposed hybrid reliability–AI framework is resistant to random noise but sensitive to incomplete or erroneous historical data. The developed approach provides an interpretable and effective tool for predictive maintenance, supporting reliability management and operational decision-making in marine engine systems. The article presents a hybrid model that has been developed to enable the detailed characterization of emergency processes and the identification of the most important factors that influence damage forecasting. For systems with variable failure risk, it was found that both classical probabilistic models and machine learning methods must be considered to interpret damage patterns correctly. Implementing data filtration and validation procedures before using data in artificial intelligence models has been shown to improve forecast stability and increase the usefulness of forecasts for planning repairs.

In marine systems, autonomous power generation unit sets play an important (main) function, and the Automatic Voltage Regulator (AVR) is a part of the excitation system of a synchronous generator that is difficult to test, repair, and adjust by the Electro Technical Officer (ETO) and marine automation services. Typically, testing of the AVR on ships is carried out on installed AVRs in an operating generator, which creates significant challenges. Under operating conditions, achieving various generator operating states is practically impossible. In this article, the authors present a solution that replaces traditional AVR testing by using Hardware-in-the-Loop (HiL) technology, allowing for full diagnostics. Testing the AVR in a loop allowed verification of its performance without a real generator, which is simulated in real time. The possibility of diagnosing the AVR under different standalone generator conditions (dynamic load changes and load character changes) was presented. Test scenarios were carried out in real time on a sample AVR from LXCOS V1.4.5.2 and the HiL simulator from Speedgoat. The solution proposed by the authors in the article enables effective diagnostics of the AVR with high practicality and low costs.

The International Maritime Organization are introducing more and more stringent requirements concerning increasing ships’ energy efficiency. They are becoming a huge challenge for design engineers. This article proposes a method to increase the energy efficiency of mechatronic drive systems in ship systems via the use of highly efficient electric permanent magnet synchronous motors (PMSMs). An innovative control strategy is suggested. It is based on the modification of the classic PMSM control and ensuring energy optimization through a reduction in reactive power in the Active Converter–PMSM system. Analytical and simulation studies using the Matlab–Simulink program are presented. They confirm the possibility of reducing reactive power in a PMSM drive system. A verification of the results of analytical and simulation examinations was conducted at a laboratory station with the use of the Speedgoat module operating in the Rapid Control Prototyping mode. Both the simulation and experimental research results indicate the effectiveness of the proposed PMSM control method. This method has good prospects for application in energy-saving marine drive systems.

Landfill gas recovery and utilisation is a solution which reduces the adverse environmental impact of the landfill. Combined heat and power (CHP) generation improves the energy balance of the facility and enables the optimal management of energy generated from a renewable source. This article aims to analyse the operation of the CHP unit in two aspects, that is, in terms of energy generation efficiency and operational availability. Energy ratios were calculated and the analysis was based on the Weibull distribution in order to assess the CHP unit’s operational reliability to minimise costs and maximise energy production. The results of the investigations and analyses demonstrated an increase of the gas yield by 29.5%, an increase of energy production by approx. 42%, and the reduction of downtime by 28.2% from 2018 to 2022. Studies related to the efficiency and reliability of operation of the cogeneration unit showed an increase in all the main parameters analysed, which resulted in greater energy and operational efficiency. The research which has been conducted is a significant scientific contribution to the optimisation of the “waste-to-energy” process for cogeneration units with the capacity of up to 0.5 MW.