The invention discloses a model reinforcement learning-based self-adaptive energy management framework for a hybrid electric vehicle. The adaptive energy management framework comprises a feedforward controller and a feedback controller, the feedforward controller is a deep neural network controller obtained based on offline training of a model-free reinforcement learning algorithm, the feedback controller is obtained based on online learning of the model reinforcement learning algorithm, and parameters of the feedforward controller can be periodically updated according to latest driving data. According to the invention, the problems of long training time and low data utilization rate of an existing control framework based on a model-free reinforcement learning algorithm are solved, the feedback controller can be efficiently updated online, the adaptability of the hybrid electric vehicle energy management control framework is improved, and the reliability of the system is improved. And the fuel economy can be ensured and the charge state of the power battery can be well maintained under various new road working conditions.

    本发明公开了基于模型强化学习的混合动力汽车自适应能量管理框架;所述自适应能量管理框架包括一个前馈控制器和一个反馈控制器,前者是基于无模型强化学习算法离线训练获得的深度神经网络控制器,而后者是基于模型强化学习算法在线学习获得,它的参数可以根据最新的驾驶数据定期更新。本发明解决了现有基于无模型强化学习算法控制框架训练时间长、数据利用率低的问题,可以实现在线高效更新反馈控制器,提高了混合动力汽车能量管理控制框架的适应性,能够在多种新的道路工况下保证燃油经济性并较好地维持动力电池荷电状态。


    Access

    Download


    Export, share and cite



    Title :

    Hybrid electric vehicle adaptive energy management framework based on model reinforcement learning


    Additional title:

    基于模型强化学习的混合动力汽车自适应能量管理框架


    Contributors:
    SHI CUIDUO (author) / ZHAO KEGANG (author) / LIANG ZHIHAO (author)

    Publication date :

    2023-06-02


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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