Health-Conscious Integrated Thermal Management Strategy Using Hybrid Attention Deep Reinforcement Learning for Battery Electric Vehicles

Effective thermal management strategies (TMSs) can extend the driving range of battery electric vehicles (BEVs) and enhance cabin thermal comfort in high-temperature environments. Considering the development trend toward integrated thermal management systems (ITMSs) and the critical role of the power battery in BEVs, this article establishes an ITMS model embedded with battery health-conscious. To further explore the temperature control and energy-saving potential of the proposed ITMS, a learning TMS is designed using twin delayed deep deterministic policy gradient (TD3). Given the intricate state information within the ITMS, a hybrid attention mechanism is introduced to optimize the original TD3, enabling the TD3 agent to discern the relative importance of various state information and thereby improving its decision-making quality. Simulation results indicate that, compared to rule-based TMS, the proposed improved TD3-based TMS decrease battery health degradation and energy loss by 22.50% and 35.33%, respectively. Additionally, compared to other compared TMSs, the proposed TMS effectively reduces temperature fluctuations in the battery, motor, and cabin, with root mean square errors of 0.13, 0.12, and 0.08, respectively. Moreover, hardware in the loop testing further demonstrates that the proposed TMS can reduce driving costs by 9.13%–12.70% compared to the traditional TMS.