本发明公开了一种基于深度强化学习的列车受电弓智能控制方法,具体为:信息采集单元获取受电弓状态信息、列车运行信息和接触网信息;建立控制器控制动作与接触网交互样本数据集;基于所建立的交互样本数据集采用确定性策略梯度DDPG深度强化学习网络学习最优行为策略;根据最优行为策略作为控制器,将控制器补偿动作输出受电弓气阀板上的精密调压阀从而控制气囊压强。本发明能有效对高铁受电弓的精准、提前控制,保证受电弓和接触网的良好接触,提升列车的受流质量,降低接触部件的磨损、提升服役寿命。

    The invention discloses a train pantograph intelligent control method based on deep reinforcement learning. The train pantograph intelligent control method specifically comprises the steps that an information acquisition unit obtains pantograph state information, train operation information and contact network information; establishing a controller control action and contact network interaction sample data set; learning an optimal behavior strategy by adopting a deterministic strategy gradient (DDPG) deep reinforcement learning network based on the established interactive sample data set; the optimal behavior strategy serves as a controller, and the compensation action of the controller is output to a precise pressure regulating valve on a pantograph air valve plate, so that the pressure intensity of an air bag is controlled. According to the method, the high-speed rail pantograph can be effectively and accurately controlled in advance, good contact between the pantograph and an overhead line system is guaranteed, the current collection quality of a train is improved, abrasion of contact parts is reduced, and the service life is prolonged.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    一种基于深度强化学习的列车受电弓智能控制方法


    Erscheinungsdatum :

    2024-06-18


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung