Research on Energy Management Strategy for Marine Methanol–Electric Hybrid Propulsion System Based on DP-ANFIS Algorithm

Abstract

To address the challenges of high fuel consumption and emissions in traditional diesel-powered inland law enforcement vessels, this study proposes a methanol–electric hybrid propulsion system retrofitted with a novel energy management strategy (EMS) based on the integration of Dynamic Programming (DP) and Adaptive Neuro-Fuzzy Inference System (ANFIS). The DP-ANFIS algorithm combines the global optimization capability of DP with the real-time adaptability of ANFIS to achieve efficient power distribution. A high-fidelity simulation model of the hybrid system was developed using methanol engine bench test data and integrated with models of other powertrain components. The DP algorithm was used offline to generate an optimal control sequence, which was then learned online by ANFIS to enable real-time energy allocation. Simulation results demonstrate that the DP-ANFIS strategy reduces total energy consumption by 78.53%, increases battery state of charge (SOC) by 3.24%, decreases methanol consumption by 64.95%, and significantly reduces emissions of CO, HC, NOx, and CO2 compared to a rule-based strategy. Hardware-in-the-loop tests confirm the practical feasibility of the proposed approach, offering a promising solution for intelligent energy management in marine hybrid propulsion systems.