The invention provides an intelligent driving fuel cell vehicle control method fusing driving road multi-dimensional information spatialization, which comprises the following steps of: obtaining a target vehicle speed output by decision planning, and collecting vehicle state information and battery data information; establishing a time-varying driving environment model through a road recognition convolutional neural network based on VGG16 to estimate a real-time road adhesion coefficient and an optimal slip rate, and calculating the maximum acceleration and deceleration of the current road surface; acceleration and deceleration required for achieving the target vehicle speed are output through brain emotion learning, the current acceleration and deceleration are limited, and the opening degrees of an accelerator and a brake pedal are obtained through an accelerator and brake calibration table so as to achieve the target vehicle speed; constructing a multi-dimensional stereo control network suitable for a nine-dimensional state space and a three-dimensional action space, and proposing an energy management strategy based on a deep Q network; according to the method, multi-dimensional information is fused, a motor rotating speed fine tuning strategy is applied, power source power is distributed, and the method has good speed tracking precision, environment adaptability and economical efficiency.

    本发明提出一种融合行驶道路多维信息空间化的智能驾驶燃料电池汽车控制方法,包括以下步骤:获取决策规划输出的目标车速,采集车辆状态信息与电池数据信息;通过基于VGG16的道路识别卷积神经网络,建立时变驾驶环境模型估计出实时道路附着系数以及最佳滑移率,计算出当前路面最大的加、减速度;通过大脑情感学习输出达到目标车速需要的加、减速度,并由当前加、减速度限制,通过油门刹车标定表获取油门、刹车踏板开度,以达到目标车速;构建适用于九维状态空间和三维动作空间的多维立体控制网络,提出基于深度Q网络的能量管理策略;本发明融合多维信息,并运用电机转速微调策略以及分配动力源功率,具有良好的速度跟踪精度、环境自适应性和经济性。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Intelligent driving fuel cell vehicle control method fusing road multi-dimensional information spatialization


    Weitere Titelangaben:

    融合道路多维信息空间化的智能驾驶燃料电池车控制方法


    Beteiligte:
    LIN XINYOU (Autor:in) / HUANG QIANG (Autor:in) / TANG YUNLIANG (Autor:in) / YE JINZE (Autor:in) / CHEN XIANKANG (Autor:in)

    Erscheinungsdatum :

    2022-10-14


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen / G06K Erkennen von Daten , RECOGNITION OF DATA / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen




    TELEMAC-2D upgrades: Rainfall spatialization and control sections

    Hocini, Nabil / Pons, Frédéric / TELEMAC-MASCARET Core Group | HENRY – Bundesanstalt für Wasserbau (BAW) | 2023

    Freier Zugriff

    Self-vehicle driving path identification method fusing multi-sensor information for ACC and AEB

    PI DAWEI / WANG XU / WANG HONGLIANG et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Intelligent vehicle intersection straight-going speed decision-making method fusing driving style game

    ZHAO HAIYAN / LI CHENG / LU XINGHAO et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    REAL TIME MULTI DIMENSIONAL IMAGE FUSING

    ROBERT C ALLEN / BRENDAN BLANTON / LAUREN GRESKO et al. | Europäisches Patentamt | 2016

    Freier Zugriff