Changcheng Wu

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.

Battery Electric Vehicles (BEVs) experience significant range degradation and reduced thermal comfort in low-temperature environments, underscoring the importance of energy-efficient Heat Pump Air Conditioning (HPAC) systems as a core thermal management technology. However, existing Thermal Management Strategies (TMSs) struggle with HPAC's strong coupling and nonlinearity, and rarely consider joint health optimization of batteries and motors. To address these gaps, this study proposes a Deep Reinforcement Learning (DRL)-based TMS integrating component health awareness. This study proposes an optimization framework considering both battery State of Health (SOH) and motor aging, and improves the original Proximal Policy Optimization (PPO) by embedding the Beta Distribution (BD) to enhance its adaptability to bounded continuous action spaces. Simulations and Hardware-in-the-Loop (HIL) tests validate the strategy: compared with the original PPO-based TMS, the compressor energy consumption is reduced by approximately 11.26%. Relative to existing TMSs, battery energy consumption and health degradation show respective reductions of 4.20% and 6.90%, while motor health degradation is reduced by 5.64%. The proposed TMS achieves stable temperature control of battery, motor, and cabin under different initial temperatures, demonstrating superior energy efficiency, robustness, and engineering deployability.

To address the challenge of coordinated optimization between energy consumption and thermal comfort in electric vehicle thermal management systems under low-temperature conditions, this article proposes an intelligent control framework integrating a channel–temporal attention mechanism with knowledge distillation. A channel–temporal attention-enhanced dual-delay deep deterministic policy gradient (DDPG) algorithm [twin delayed deep deterministic policy gradient with channel and temporal attention (CT-TD3)] is developed to enable dynamic feature selection and long-term temporal dependency modeling of thermal states across coupled subsystems—including the battery, motor, and cabin—thereby significantly improving algorithmic convergence speed and enhancing the foresight of control decisions. Furthermore, response-layer knowledge distillation is employed to construct a lightweight thermal comfort prediction network, reducing computational latency to 0.514 ms while preserving high prediction accuracy, thus enabling real-time optimization under comfort constraints. Simulation results demonstrate that, at a low ambient temperature of $- 10~^{\circ }$ C, the proposed method reduces total system energy consumption by 5.27% compared to the baseline strategy while increasing the proportion of occupant thermal comfort ratio to 75.03%.

An effective regenerative braking control strategy for electric vehicles can extend the driving range of battery electric vehicles (BEVs) and improve braking stability. Considering the development trends in integrated BEVs regenerative braking control strategies and the critical role of power batteries in BEVs, this study establishes a regenerative braking model that accounts for energy recovery efficiency, braking stability, and battery state of health (SOH). To further explore the comprehensive performance of the proposed model, a regenerative braking control strategy was designed using the twin delayed deep deterministic (TD3) policy gradient algorithm. Addressing the high time cost associated with hyperparameter optimization in deep reinforcement learning (DRL), Bayesian optimization (BO) was introduced to replace grid or random search, reducing debugging effort and computational load. Furthermore, a prioritized experience replay (PER) mechanism was incorporated to replace the original random sampling, enabling the TD3 agent to assign higher weights to important samples and thereby improving training speed and convergence performance. Simulation results demonstrate that the proposed PER-TD3 control strategy improves energy recovery efficiency by approximately 5% and braking stability by 67% compared with the rule-based regenerative braking control strategy. In addition, relative to the baseline TD3, the PER-TD3 strategy achieves enhanced energy recovery efficiency and braking stability under both testing and training cycles.

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.

Thermal management systems (TMSs) are crucial for driving safety, mileage, and comfort in battery electric vehicles (BEVs). To maximize the potential of the integrated TMSs in terms of temperature control and energy saving, the deep deterministic policy gradient (DDPG) is utilized to design a learning thermal management methodology (TMM) for it. Considering the key challenges faced, the linear mapping trick and the gated recurrent unit (GRU) are employed to improve the original DDPG. The former empowers the DDPG agents with the ability to make decisions in the discrete-continuous hybrid action space while helping it avoid the “curse of dimensionality.” The latter provides the DDPG agents with beneficial historical information, which enhances its decision-making quality. Simulation results show that the proposed TMM decreases the convergence episode to 77 while increasing the convergence reward to 553.4. Further adaptive tests demonstrate that the suggested TMM promptly stabilizes the motor and battery temperatures at the desired values. Simultaneously, energy consumption decreases by 14.71% and 11.45% for two cases compared to the conventional rule-based TMM. In conclusion, the proposed method provides a theoretical foundation for addressing the hybrid action space optimization problem in integrated TMSs.