Accurate velocity prediction is crucial for predictive torque distribution in dual-motor electric vehicles (EVs). This paper proposes a surrounding vehicle-aware predictive torque distribution strategy to enhance energy efficiency. A Transformer-based velocity predictor is developed by integrating the historical velocities of ego vehicle and surrounding vehicles with relative distance, achieving 49% MAE and 48% RMSE reductions compared to a single-vehicle prediction baseline. The predicted velocity sequence is embedded into a model predictive control framework to optimize front/rear motor torque distribution, generating 8.2-16.1% more high-efficiency motor working points while maintaining battery state-of-charge (SOC). Simulation results demonstrate 0.35% improvement in end-of-cycle SOC and smoother current profiles under real driving cycles, validating the effectiveness of spatiotemporal interaction modeling for energy-saving torque distribution.

Gear ratio optimization is essential for improving transmission efficiency and dynamic performance of four-wheel distributed drive electric heavy trucks. This study proposes a gear ratio optimization method that integrates battery health and shifting-induced energy losses and considers shift frequency. The method employs particle swarm optimization to optimize front and rear axle gear ratios under realistic truck operating conditions, followed by dynamic programming to determine the optimal gear-shifting sequence and real-time torque allocation. Through iterative refinement, the proposed method achieves optimal gear ratios of [32.17, 18.16] for the front axle and [35.53, 14.61] for the rear axle. Simulation results demonstrate that the optimized configuration reduces annual operational costs by 0.5%-1.9% compared to other optimization methods, yielding savings of 103,328 RMB per year while mitigating battery degradation and kinetic energy loss during gear shifts.

Deep reinforcement learning (DRL) has emerged as a promising approach for energy management in hybrid electric vehicles. However, the current focus of energy management in DRL primarily centers on energy-saving performance while neglecting safety constraints during the training process. To address this challenge, this paper proposes a rational-safe reinforcement learning energy management strategy for hybrid electric vehicles. First, a safety evaluation mechanism based on eXtreme Gradient Boosting is developed to assess the safety of actions generated by the agent. Subsequently, a physics-informed safety layer is introduced to modify irrational control signals through constrained optimization when the agent’s outputs are evaluated as unsafe. Experimental results demonstrate that the proposed method ensures the safety of output actions while improving fuel economy by 5.64%-6.28% compared to existing reinforcement learning approaches.

For distributed drive electric vehicles, energy consumption is affected by the power demand and energy management strategy. In this paper, an adaptive cruise control and energy management strategy cooperative framework for dual-motor electric vehicles is proposed based on the deep deterministic policy gradient algorithm. Firstly, the energy management problem in the car-following scenario is decomposed into two subproblems: the adaptive cruise control governs vehicle acceleration, while the energy management strategy allocates driving torque. Then, based on the cooperative architecture, the speed trajectory and torque allocation strategy are co-optimized to realize cooperation between the adaptive cruise control and the energy management strategy. Finally, the proposed cooperative strategy is compared with the traditional hierarchical strategy under the worldwide harmonized light vehicles test cycle. Results show that the proposed cooperative strategy can reduce the maximum acceleration and maximum deceleration by 10.8% and 10.4%, respectively, and improve energy consumption by 4.3% compared with the traditional hierarchical strategy.