Intelligent Energy Management Strategy for PHEV with Adaptive Rule-Parameter Updating

To address the poor adaptability to diverse driving cycles and the imbalance between optimization performance and computational efficiency in existing energy management strategies (EMSs) for plug-in hybrid electric vehicles (PHEVs), this paper proposes a lightweight intelligent EMS (IEMS) with adaptive rule-parameter updating. The key contributions lie in constructing an optimized rule library using parameter optimization, and developing an online adaptive updating mechanism for rule parameters combined with driving cycle prediction, realizing dynamic self-adjustment of energy management rules. The results show that compared with the rule-based EMS (RBEMS), the strategy reduces energy consumption by 9.09%, 10.85% and 9.25% under NEDC, WLTC and real-world test cycles, respectively, with drastically lower computation times than dynamic programming (DP). The proposed IEMS can effectively balance fuel economy, driving cycle adaptability and computational efficiency.