【摘要】 热管理系统效率直接影响纯电动汽车的能耗与续航，高温工况下其高能耗问题尤为突出。为解决该难题，提出了基于径向基函数（RBF）神经网络与非支配排序遗传算法Ⅱ(NSGA-Ⅱ)的双层优化控制策略。上层采用RBF神经网络对压缩机转速进行优化，在稳定乘员舱温度的同时减小系统超调；下层采用NSGA-Ⅱ对电池端电子膨胀阀开度进行调节，以实现多目标优化。仿真结果表明，在中国轻型汽车行驶工况（CLTC）下，双层优化控制策略有效降低了压缩机和热管理系统的能耗，显著提升了车辆能效，为整车热管理系统优化提供了新思路。更多还原

【Abstract】 The efficiency of the thermal management system directly affects the energy consumption and driving range of battery electric vehicles, with its high energy consumption being particularly prominent under high-temperature conditions. To address this challenge, a dual-layer optimization control strategy based on radial basis function(RBF) neural network and non-dominated sorting genetic algorithm Ⅱ(NSGA-Ⅱ) is proposed. The upper layer utilizes an RBF neural network to optimize the compressor speed, stabilizing the cabin temperature while reducing system overshoot. The lower layer employs NSGA-Ⅱ to adjust the opening degree of the electronic expansion valve on the battery side, achieving multi-objective optimization. Simulation results demonstrate that under the China light-duty vehicle test cycle(CLTC), the dual-layer optimization control strategy effectively reduces the energy consumption of both the compressor and the thermal management system, significantly improving vehicle energy efficiency and providing a new approach for optimizing vehicle thermal management systems.更多还原