Enhanced Reinforcement Learning-Based Energy Management via Prioritized Exploration and Experience Replay for Axle-Split Hybrid Electric Vehicles

Abstract

Axle-split hybrid electric vehicles (HEVs) have gained attention for their potential to improve fuel economy and enable electric all-wheel-drive operation through dual-motor (P0+P4) configurations. This configuration allows energy harvesting during deceleration events from both motors, effectively balancing braking safety with energy regeneration – a challenge in traditional P0-only systems. However, adding a P4 motor introduces additional control complexity. This study presents a reinforcement learning (RL)-based energy management strategy for a 48 V P0+P4 HEV using a Twin-Delayed Deep Deterministic Policy Gradient with Prioritized Exploration and Experience Replay (TD3-PEER) algorithm. To address the control complexity, a motor activation threshold is introduced, consolidating the on/off switching and power control of each motor into a single decision variable. Consequently, the three-power-source system requires only two control variables, one for each motor, simplifying the control task. Furthermore, this work validates the benefits of the prioritized exploration technique without relying on DP-derived expert demonstrations or supervisory control heuristics. The results reveal that the proposed TD3-PEER algorithm effectively learns a charge-sustaining strategy for a complex P0+P4 HEV system without prior knowledge of the driving cycle or DP-derived expert action guidance. In a case study, the proposed method achieves 95.1% and 94.2% of global optimality in training and validation cycles, respectively.