The embodiment of the invention provides a train attitude control method based on DQN reinforcement learning. The method comprises the steps of obtaining attitude parameters of a vehicle in real time;determining the current operation state of the vehicle according to the attitude parameters of the vehicle; generating a vibration reduction control instruction used for enabling the vehicle to operate stably according to the current operation state and the target operation state of the vehicle and based on a DQN algorithm model; and adjusting the running posture of the vehicle in real time according to the vibration reduction control instruction. According to the embodiment of the invention, the current running state of the vehicle is determined by acquiring attitude parameters of the vehicle in real time; the vibration reduction control instruction capable of enabling the vehicle to run stably is generated, a primary vertical vibration reducer of the vehicle is controlled in real time,the effect of actively guiding the controllable vibration reducer to act can be achieved, the problem in vertical stability of a vehicle bogie in the on-road running process of the vehicle is solved,and then the purpose of keeping the on-road running vehicle running continuously and stably is achieved.

    本发明实施例提供一种基于DQN强化学习的列车姿态控制方法,方法包括:实时获取车辆的姿态参数;根据车辆的姿态参数确定车辆当前所属的运行状态;根据车辆当前所属的运行状态以及目标运行状态,基于DQN算法模型,生成用于使得车辆平稳运行的减振控制指令;根据所述减振控制指令对车辆运行姿态进行实时调整;本发明实施例通过实时获取车辆的姿态参数确定车辆当前运行状态,生成可以使车辆平稳运行的减振控制指令,对车辆的一系垂向减振器的实时控制,可以达到主动指导可控减振器作动的效果,解决车辆在途运行过程中车辆转向架的垂向平稳性问题,进而以保持在途运行车辆持续平稳运行的目的。


    Access

    Download


    Export, share and cite



    Title :

    Train attitude control method based on DQN reinforcement learning


    Additional title:

    一种基于DQN强化学习的列车姿态控制方法


    Contributors:
    FU YUNXIAO (author) / TIAN YIN (author) / TANG HAICHUAN (author) / GONG MING (author) / SUN BANGCHENG (author) / FAN YUMING (author) / LIU QI (author)

    Publication date :

    2020-10-16


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G05D SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES , Systeme zum Steuern oder Regeln nichtelektrischer veränderlicher Größen / B61C Lokomotiven , LOCOMOTIVES / B61F Untergestelle für Schienenfahrzeuge, z.B. Fahrgestellrahmen, Drehgestelle oder Anordnungen der Radsätze , RAIL VEHICLE SUSPENSIONS, e.g. UNDERFRAMES, BOGIES OR ARRANGEMENTS OF WHEEL AXLES / G05B Steuer- oder Regelsysteme allgemein , CONTROL OR REGULATING SYSTEMS IN GENERAL / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Train operation control method and system based on train attitude

    SHI JING / CUI JUNFENG / LIU LING et al. | European Patent Office | 2024

    Free access

    REINFORCEMENT LEARNING FOR SPACECRAFT ATTITUDE CONTROL

    Vedant, Fnu / Allison, James / West, Matthew et al. | TIBKAT | 2020


    Reinforcement Learning for UAV Attitude Control

    Koch, William / Mancuso, Renato / West, Richard et al. | ArXiv | 2018

    Free access

    SYSTEM AND METHOD FOR REINFORCEMENT LEARNING-BASED TRAIN CONTROL

    KANG BYONG KWAN / PARK KAPLEE | European Patent Office | 2024

    Free access

    Attitude Control Based on Reinforcement Learning for Quadrotor

    Wang, Yao / Zhang, Weiping / Mou, Jiawang et al. | TIBKAT | 2022