The invention discloses a fuel cell vehicle deep reinforcement learning energy management method based on strategy migration, and belongs to the field of fuel cell hybrid power energy management. And the training convergence speed and the automobile fuel economy of the migrated agent model are improved. The method mainly comprises the following steps: establishing two obviously different fuel cell automobile models; establishing a depth deterministic policy gradient agent model based on policy migration; for a vehicle type, training a DDPG proxy model, and obtaining a network strategy of the trained DDPG proxy model; and migrating the strategy to a new vehicle model, continuing to train the DDPG agent model, and performing energy management on the new vehicle model by using the finally trained DDPG agent.

    本发明公开了一种基于策略迁移的燃料电池汽车深度强化学习能量管理方法,属于燃料电池混合动力能量管理领域,所构建的策略迁移技术可以有效利用其他车型的车辆能量管理策略,提高迁移后代理模型的训练收敛速度和汽车燃油经济性。本发明方法主要包括:建立两种显著不同的燃料电池汽车模型;建立基于策略迁移的深度确定性策略梯度代理模型;针对一种车型,训练DDPG代理模型,获取训练后DDPG代理模型的网络策略;迁移策略至新的车型上,继续训练DDPG代理模型,利用最终训练完成的DDPG代理进行新车型的能量管理。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Strategy migration-based fuel cell vehicle deep reinforcement learning energy management method


    Weitere Titelangaben:

    一种基于策略迁移的燃料电池汽车深度强化学习能量管理方法


    Beteiligte:
    XU DA (Autor:in) / ZHOU JIANHAO (Autor:in) / ZHAO WANZHONG (Autor:in) / LI CHAOXIONG (Autor:in) / WU XUYANG (Autor:in)

    Erscheinungsdatum :

    2022-08-30


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / 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 / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Fuel cell vehicle deep reinforcement learning energy management method based on experience pool migration

    ZHOU JIANHAO / XU DA / GUO AIJUN et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Fuel cell hybrid electric vehicle energy management method based on deep reinforcement learning

    MA YAN / LUAN YU | Europäisches Patentamt | 2024

    Freier Zugriff

    Hydrogen fuel unmanned aerial vehicle energy management method based on deep reinforcement learning

    WU YU / ZHANG MINGXUAN / WANG YUYANG et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Fuel cell vehicle energy management method combining working condition prediction and reinforcement learning

    LU YANHUI / ZHANG YUNRUI / WANG PENGYU et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    HEV energy management method based on deep reinforcement learning in vehicle following environment

    TANG XIAOLIN / CHEN JIAXIN / YANG KAI et al. | Europäisches Patentamt | 2020

    Freier Zugriff