This study proposed a deep reinforcement learning-based energy management strategy (DRL-EMS) that can be applied to a hybrid electric ship propulsion system (HSPS) integrating liquid hydrogen (LH₂) fuel gas supply system (FGSS), proton-exchange membrane fuel cell (PEMFC) and lithium-ion battery systems. This study analyzed the optimized performance of the DRL-EMS and the operational strategy of the LH₂-HSPS. To train the proposed DRL-EMS, a reward function was defined based on fuel consumption and degradation of power sources during operation. Fuel consumption for ship propulsion was estimated with the power for balance of plant (BOP) of the LH₂ FGSS and PEMFC system. DRL-EMS demonstrated superior global and real-time optimality compared to benchmark algorithms, namely dynamic programming (DP) and sequential quadratic programming (SQP)-based EMS. For various operation cases not used in training, DRL-EMS resulted in 0.7% to 9.2% higher operating expenditure compared to DP-EMS. Additionally, DRL-EMS was trained to operate 60% of the total operation time in the maximum efficiency range of the PEMFC system. Different hydrogen fuel costs did not affect the optimized operational strategy although the operating expenditure (OPEX) was dependent on the hydrogen fuel cost. Different capacities of the battery system did not considerably change the OPEX.

This study analyzes the thermodynamic, economic, and regulatory aspects of boil-off hydrogen (BOH) in liquid hydrogen (LH₂) carriers that can be re-liquefied using a proposed re-liquefaction system or used as fuel in a fuel cell stack. Five LH₂ carriers sailing between two designated ports are considered in a case study. The specific energy consumption of the proposed re-liquefaction system varies from 8.22 to 10.80 kWh/kg as the re-liquefaction-to-generation fraction (R/G fraction) is varied. The economic evaluation results show that the cost of re-liquefaction decreases as the re-liquefied flow rate increases and converges to 1.5 $/kg at an adequately large flow rate. Three energy efficient design index (EEDI) candidates are proposed to determine feasible R/G fractions: an EEDI equivalent to that of LNG carriers, an EEDI that considers the energy density of LH₂, and no EEDI restrictions. The first EEDI candidate is so strict that the majority of the BOH should be used as fuel. In the case of the second EEDI candidate, the permittable R/G fraction is between 25% and 33%. If the EEDI is not applied for LH₂ carriers, as in the third candidate, the specific life-cycle cost decreases to 67% compared with the first EEDI regulation.

This study introduced the methodology for integrating ethylene glycol/water mixture (GW) systems which supply heat energy to the liquid hydrogen (LH₂) fuel gas supply system (FGSS), and manage the temperature conditions of the battery system. All systems were designed and simulated based on the power demand of a 2 MW class platform supply vessel assumed as the target ship. The LH2 FGSS model is based on Aspen HYSYS V11 and the cell model that makes up the battery system is implemented based on a Thevenin model with four parameters. Through three different simulation cases, the integrated GW system significantly reduced electric power consumption for the GW heater during ship operations, achieving reductions of 1.38% (Case 1), 16.29% (Case 2), and 27.52% (Case 3). The energy-saving ratio showed decreases of 1.86% (Case 1), 21.01% (Case 2), and 33.80% (Case 3) in overall energy usage within the GW system. Furthermore, an examination of the battery system’s thermal management in the integrated GW system demonstrated stable cell temperature control within ±3 K of the target temperature, making this integration a viable solution for maintaining normal operating temperatures, despite relatively higher fluctuations compared to an independent GW system.

The International Maritime Organization (IMO) has been continuously strengthening environmental regulations to reduce greenhouse gas emissions from ships, which has led to increased attention on hybrid ship propulsion systems combining hydrogen fuel cells and batteries. This study analyzes the energy management strategy of a hybrid ship propulsion system in relation to changes in the battery system’s energy capacity. The target vessel was set as a 500 kW-class ferry operating for 24 h, and the maximum current rate (C-rate) and effects of the equivalence factor, which are key elements of the energy management problem, in relation to changes in energy capacity were investigated. The results show that while changes in the battery system’s energy capacity do not significantly affect the optimal operating point of the hybrid ship propulsion system, they are highly influenced by the response speed of the hydrogen fuel gas supply system and fuel cells, as well as the maximum C-rate required by the battery system. Furthermore, the equivalence factor, one of the key parameters in the optimization problem, tends to vary depending on the degree of charging and discharging, as it affects the equivalent fuel consumption of the battery system.