Hierarchical Reinforcement Learning-Based Cooperative Energy Efficiency-Thermal Safety-Battery Health Management for Distributed 4-wheel Independent Drive Electric Vehicles
As electric vehicle architectures evolve toward distributed configurations, distributed four-wheel independent drive electric vehicles (4WID-EVs) have gained significant attention for independent wheel torque control. To enhance energy efficiency and mitigate health degradation of the battery and motor, it is necessary to adopt torque distribution strategies (TDS) and integrate thermal management systems (TMS) to regulate the temperatures of batteries and motors. Nevertheless, the vehicle longitudinal dynamics and the TMS are characterized by complex nonlinear couplings, which makes it difficult to achieve effective cooperative control through a single integrated strategy. To address this issue, a hierarchical control framework is proposed that combines the soft actor-critic (SAC) with the estimation of distribution algorithm. The upper layer optimizes torque distribution to improve energy efficiency, while the lower layer employs thermal management method to regulate temperatures. Simulation and hardware-in-the-loop (HIL) testing results demonstrate that the proposed framework achieves approximately 93.5% of the driving energy-saving performance of dynamic programming (DP), improves the accuracy of battery and motor temperature control, and effectively mitigates battery health degradation. Moreover, HIL results further validate that the hierarchical control framework provides favorable real-time performance and generalization capability, highlighting its strong potential for engineering applications.