The invention discloses a hybrid vehicle energy management method based on a reinforcement learning training network model, and the method comprises the following steps: customizing basic elements, building an application scene database of a hybrid vehicle, correspondingly selecting a data set for reinforcement learning algorithm training according to the application scene database, constructing the reinforcement learning training network model, and carrying out the algorithm iteration training. And extracting the energy management strategy function obtained by training. According to the method, the cost function c is creatively added in the reinforcement learning training network model, so that the training evaluation indexes of the method comprise the accumulated award value sigma r, the accumulated cost value sigma c and the expected minimum cost value Min (sigma c), and the overall algorithm robustness is better; the reward function and the cost function are separately arranged, so that the training target of the reinforcement learning algorithm is clear, and the interpretability is higher; and the customization requirement of a customer on the hybrid power vehicle can be quickly met.

    本发明揭示了一种基于强化学习训练网络模型的混动车辆能量管理方法,包括以下步骤:自定义基本元素,建立混动车辆的应用场景数据库,据其相应选择用于强化学习算法训练的数据集,构建强化学习训练网络模型,进行算法迭代训练,提取训练得到的能量管理策略函数。本发明在强化学习训练网络模型中创新地增加了代价函数c,因此其训练评价指标除了累积奖励值Σr外,还包括累积代价值Σc和期望最小代价值Min(Σc),整体算法鲁棒性更好;奖励函数和代价函数分开设置,使得强化学习算法的训练目标明确、可解释性更高;可以快速满足客户对于混动车辆的定制化需求。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Hybrid vehicle energy management method based on reinforcement learning training network model


    Weitere Titelangaben:

    基于强化学习训练网络模型的混动车辆能量管理方法


    Beteiligte:
    HONG ZE (Autor:in) / XU XUEMEI (Autor:in) / SI WEN (Autor:in) / XUE XIANG (Autor:in)

    Erscheinungsdatum :

    13.12.2022


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

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



    Hybrid electric vehicle energy management method based on reinforcement learning

    LOU DIMING / ZHAO YINGHUA | Europäisches Patentamt | 2021

    Freier Zugriff

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

    SHI CUIDUO / ZHAO KEGANG / LIANG ZHIHAO | Europäisches Patentamt | 2023

    Freier Zugriff

    Parallel hybrid electric vehicle energy management method based on hierarchical reinforcement learning

    XIAO FENG / QI CHUNYANG | Europäisches Patentamt | 2022

    Freier Zugriff

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

    MA YAN / LUAN YU | Europäisches Patentamt | 2024

    Freier Zugriff

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

    FU ZHUMU / GONG HUIXIAN / TAO FAZHAN et al. | Europäisches Patentamt | 2022

    Freier Zugriff