The invention discloses an electric vehicle economic self-adaptive cruise control method based on a multi-step DDQN, and the method comprises the following steps: 1, constructing a model, and obtaining a state variable of a longitudinal dynamic model; step 2, inputting the state variable X (t) into a BP neural network to obtain a motor demand torque; 3, inputting the state variable and the difference value between the demand torque and the actual torque into the DDQN network to obtain a Q value, and obtaining an optimal action according to a multi-step tree backtracking strategy; 4, executing an action to obtain a state variable at the next moment; step 5, updating the network weight of the DDQN network; step 6, judging whether the DDQN meets the maximum number of iterations or whether the tolerance meets a self-adaptive iteration value; and step 7, after iteration is terminated, obtaining control input, and applying the control input to the main vehicle. According to the method, communication facilities between the vehicles are utilized, so that the main vehicle can obtain the acceleration and other information of the front vehicle, the vehicle following effect is achieved, and the purpose of reducing power consumption in the vehicle following process is achieved.

    本发明公开了一种基于多步DDQN的电动汽车经济自适应巡航控制方法,包括如下步骤:步骤1、构建模型,获取纵向动力学模型的状态变量;步骤2、将状态变量X(t)输入BP神经网络得到电机需求扭矩;步骤3、将状态变量以及需求扭矩与实际扭矩差值输入到DDQN网络中得到Q值,并根据多步树回溯策略获得最佳动作;步骤4、执行动作得到下一时刻的状态变量;步骤5、对DDQN网络的网络权值进行更新;步骤6、判断DDQN网络是否满足最大迭代次数或容差是否满足自适应迭代值;步骤7、迭代终止后,获得控制输入,并应用于主车车辆上。该方法利用了车辆之间的通信设施,使得主车能够获取前车加速度等信息以及实现跟车效果,在跟车过程中实现降低耗电量的目标。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Economical self-adaptive cruise control method for electric vehicle based on multi-step DDQN


    Weitere Titelangaben:

    一种基于多步DDQN的电动汽车经济自适应巡航控制方法


    Beteiligte:
    XIE RONG (Autor:in) / ZHAI CHUNJIE (Autor:in) / CHEN CHUQIAO (Autor:in) / QIU JIANYUN (Autor:in) / CHEN HUIQIN (Autor:in) / YIN KE (Autor:in)

    Erscheinungsdatum :

    2023-07-14


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    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



    Electric vehicle economical self-adaptive cruise control method and system based on reinforcement learning

    PENG JUN / JIA XI / ZHOU FENG et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Vehicle self-adaptive cruise control method and device

    ZHOU LIN / PAN GUODONG | Europäisches Patentamt | 2020

    Freier Zugriff

    Self-adaptive cruise system and self-adaptive cruise method

    WU JUN | Europäisches Patentamt | 2022

    Freier Zugriff

    Electric vehicle cruise control method

    WU HAIXIAO / JIANG PENGCHANG / PENG JINGQI et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Self-adaptive cruise control method

    CHEN HUI / LI JINWEI / LIU GANG et al. | Europäisches Patentamt | 2023

    Freier Zugriff