Ships entering designated emission control areas (ECAs) are required to reduce emission gases drastically, in accordance with international maritime organization (IMO) regulations or local policies. In this regard, a hybrid power system, which is a combination of conventional generators and lithium-ion batteries as a type of energy storage system (ESS), has been applied to ships. However, this hybrid concept has been focused on small-sized coastal ships, because they have a short voyage time or require high peak power for a short time. And by extension, this paper demonstrates the potential of a hybrid power system for medium-sized oceangoing ships. First, a medium-sized container ship is selected as a target ship. The electric load profile near ports is defined to select the optimum capacity of the ESS and generators. Then, to verify the advantage of the proposed system, this study uses MATLAB/Simulink software for simulation. Finally, carbon dioxide (CO2) emissions are compared between the proposed power system and the conventional one which uses only generators. The results show that overall, 8.6 ~ 20.7% CO2 emissions can be reduced, depending on the electric load conditions of a ship. Hence, a hybrid power system can be an eco-friendly solution for medium-sized oceangoing ships, as well as small-sized coastal ships.

The transition to environmentally sustainable maritime operations has gained urgency with the International Maritime Organization’s (IMO) 2023 GHG reduction strategy, aiming for net-zero emissions by 2050. While alternative fuels like LNG and methanol serve as transitional solutions, lithium-ion battery energy storage systems (ESSs) offer a viable low-emission alternative. However, safety concerns such as thermal runaway, overcharging, and internal faults pose significant risks to marine battery systems. This study presents an AI-based fault prediction algorithm to enhance the safety and reliability of lithium-ion battery systems used in electric propulsion ships. The research employs a Long Short-Term Memory (LSTM)-based predictive model, integrating electrochemical impedance spectroscopy (EIS) data and voltage deviation analyses to identify failure patterns. Bayesian optimization is applied to fine-tune hyperparameters, ensuring high predictive accuracy. Additionally, a recursive multi-step prediction model is developed to anticipate long-term battery performance trends. The proposed algorithm effectively detects voltage deviations and pre-emptively predicts battery failures, mitigating fire hazards and ensuring operational stability. The findings support the development of safer and more reliable energy storage solutions, contributing to the broader adoption of electric propulsion in maritime applications.