The invention relates to the technical field of maglev control, in particular to an EMS type maglev train suspension frame deep reinforcement learning cooperative control method, which comprises the following steps: establishing a dynamic model of a single-side suspension frame suspension system in a maglev train, the system comprising two electromagnet modules located at the same side of a suspension frame; establishing a deep reinforcement learning cooperative control algorithm which comprises the following steps: establishing a single-side suspension frame suspension system deep reinforcement learning environment model based on a system dynamics model; after an SAC algorithm and an initial SAC agent are established, a deep reinforcement learning cooperative control algorithm is obtained through the SAC algorithm and the initial SAC agent and the deep reinforcement learning environment model; a SAC agent model is obtained through training of a deep reinforcement learning environment model and a deep reinforcement learning cooperative control algorithm, and control over any one single-side suspension frame suspension system under different disturbances is achieved through a trained SAC agent controller. According to the method, stable operation of the suspension system of the single-side suspension frame is ensured.

    本发明涉及磁悬浮控制技术领域,尤其涉及一种EMS型磁悬浮列车悬浮架深度强化学习协同控制方法,方法包括:建立磁悬浮列车中的单侧悬浮架悬浮系统的动力学模型,系统包括位于悬浮架同侧的两块电磁铁模块;建立深度强化学习协同控制算法,其包括:基于系统动力学模型建立单侧悬浮架悬浮系统深度强化学习环境模型;建立SAC算法及初始SAC智能体后通过其与深度强化学习环境模型得到深度强化学习协同控制算法;通过深度强化学习环境模型和深度强化学习协同控制算法训练得到SAC智能体模型,通过训练后的SAC智能体控制器实现在不同扰动下对任一单侧悬浮架悬浮系统的控制。该方法保证了单侧悬浮架悬浮系统的稳定运行。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Deep reinforcement learning cooperative control method for EMS type maglev train suspension frame


    Weitere Titelangaben:

    EMS型磁悬浮列车悬浮架深度强化学习协同控制方法


    Beteiligte:
    WANG MEIQI (Autor:in) / XU JIAYUE (Autor:in) / LIU PENGFEI (Autor:in) / WANG RUICHEN (Autor:in) / LIU YONGQIANG (Autor:in) / YANG SHAOPU (Autor:in)

    Erscheinungsdatum :

    18.10.2024


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen / G05B Steuer- oder Regelsysteme allgemein , CONTROL OR REGULATING SYSTEMS IN GENERAL



    Maglev train suspension frame and maglev train

    ZHANG SHUO / DAI RUIZHEN / WANG BIAO et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Maglev train suspension frame and maglev train

    LI LIANGJIE / HAN LU / LIU ZHIKUN et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Suspension frame for maglev train, vehicle, rail group and maglev train

    BU GL STEFAN / SAMONO BERT / FAES STEFFEN et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Maglev train and suspension frame thereof

    YU DALIAN / GU CHENLIANG / ZHAI CHAOZHI et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Suspension type maglev train

    WANG YUNFEI / ZHANG ZHIQIANG / FU SHANQIANG et al. | Europäisches Patentamt | 2025

    Freier Zugriff