The invention provides a hierarchical energy management method of a hybrid electric vehicle based on a deep reinforcement learning algorithm. The hierarchical energy management method comprises the following steps: S1, establishing a hierarchical energy management model of the hybrid electric vehicle comprising a hydrogen fuel cell model, a lithium battery model and a super capacitor model; s2, constructing a hierarchical energy management method with minimum equivalent hydrogen consumption as an optimization target according to the hierarchical energy management model; and S3, performing real-time energy management on the hybrid electric vehicle by adopting an improved deep reinforcement learning algorithm according to a hierarchical energy management method. According to the change of the required power and the weighted SOC of the energy storage system, the fuzzy rule is set, the adaptive low-pass filter is adopted to carry out frequency division processing on the required power, the high-frequency power is borne by the super capacitor, and the medium and low-frequency power is borne by the fuel cell and the lithium battery together, so that the influence of peak power on the fuel cell and the lithium battery is avoided; and the power performance of the vehicle is improved.

    本发明提供的基于深度强化学习算法的混合动力汽车分层能量管理方法,分层能量管理方法包括以下步骤:S1、建立包括氢燃料电池模型、锂电池模型和超级电容模型的混合动力汽车的分层能量管理模型;S2、根据分层能量管理模型构造一种以等效氢消耗最小为优化目标的分层能量管理方法;S3、根据分层能量管理方法,采用改进深度强化学习算法对混合动力汽车进行实时能量管理。本发明根据需求功率和储能系统加权SOC的变化,通过设立模糊规则,采用自适应低通滤波器对需求功率进行分频处理,高频功率由超级电容承担,中低频功率由燃料电池和锂电池共同承担,避免了峰值功率对燃料电池和锂电池的影响,提升了车辆的功率性能。


    Access

    Download


    Export, share and cite



    Title :

    Hierarchical energy management method for hybrid electric vehicle based on deep reinforcement learning algorithm


    Additional title:

    基于深度强化学习算法的混合动力汽车分层能量管理方法


    Contributors:
    FU ZHUMU (author) / GONG HUIXIAN (author) / TAO FAZHAN (author) / GAO SONG (author) / JI BAOFENG (author) / DONG YONGSHENG (author) / FAN PENGYU (author) / WU YANG (author)

    Publication date :

    2022-04-12


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen





    Electric flywheel hybrid electric vehicle energy management method based on multi-agent deep reinforcement learning

    LIN YANHONG / ZHANG HONGXIN / YANG CHAOHUI et al. | European Patent Office | 2025

    Free access

    Hybrid electric vehicle energy management method based on reinforcement learning

    LOU DIMING / ZHAO YINGHUA | European Patent Office | 2021

    Free access