The invention discloses a parallel hybrid electric vehicle energy management method based on hierarchical reinforcement learning. The method is characterized in that the method comprises the steps: S1, building a simulation model of a parallel vehicle; S2, constructing an energy management control model and a reward function; S3, constructing a network structure of a hierarchical reinforcement learning algorithm; S4, training and updating the hierarchical reinforcement learning algorithm; and S5, performing energy management of the parallel hybrid electric vehicle under different working conditions based on parameters influencing energy management in actual driving of the vehicle and the trained hierarchical reinforcement learning algorithm. According to the invention, the vehicle can more effectively find the exploration mode with the lowest fuel oil, the problem that reward sparsity occurs when the reinforcement learning intelligent body faces all working conditions is solved, and meanwhile the convergence speed of the reinforcement learning algorithm is increased.
本发明公开了一种基于分层强化学习的并联式混合动力汽车能量管理方法,其特征在于,包括:S1:建立并联式汽车的仿真模型;S2:构建能量管理控制模型以及奖励函数;S3:构建分层强化学习算法的网络结构;S4:对分层强化学习算法进行训练更新;S5:基于汽车实际行驶中影响能量管理的参数以及训练后的分层强化学习算法,进行并联式混合动力汽车不同工况下的能量管理。本发明使得车辆更有效地寻找到燃油最低的探索方式,解决了强化学习智能体面对各个工况时出现reward稀疏的问题,同时提高了强化学习算法的收敛速度。
Parallel hybrid electric vehicle energy management method based on hierarchical reinforcement learning
基于分层强化学习的并联式混合动力汽车能量管理方法
2022-02-01
Patent
Electronic Resource
Chinese
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion |
European Patent Office | 2022
|Hybrid electric vehicle energy management method based on reinforcement learning
European Patent Office | 2021
|SAE Technical Papers | 2023
|Fuel cell hybrid electric vehicle energy management method based on deep reinforcement learning
European Patent Office | 2024
|European Patent Office | 2025
|