The invention relates to a traffic flow parameter hybrid prediction method and device, belongs to the technical field of intelligent traffic, and solves the problems that in an existing prediction method, time consumption of model calibration is long, and road accidental situations cannot be reflected in real time. The method comprises the following steps: selecting a to-be-predicted road section AB and acquiring real-time traffic flow data at a grid point A and historical traffic flow data at a grid point B of the to-be-predicted road section; establishing a GKT macroscopic traffic flow model, and inputting the real-time traffic flow data at the position A into the model to predict future traffic flow data at the position B as a macroscopic traffic flow model prediction result U1; establishing and training an LSTM deep learning model, and predicting future traffic flow data at the position B by using the model as a deep learning model prediction result U2; and fusing the macroscopic traffic flow model prediction result U1 and the deep learning model prediction result U2 into a final prediction result U3 of future traffic flow parameters of the B by using a linear Kalman filter. Advantages of macroscopic and deep learning models are concentrated and complemented with each other.

    本发明涉及一种交通流参数混合预测方法和装置,属于智能交通技术领域,解决现有预测方法中模型校准耗时长,无法实时反应道路偶发情况的问题。方法包括:选择待预测路段AB并获取待预测路段的网格点A处的实时交通流数据和网格点B处的历史交通流数据;建立GKT宏观交通流模型并将A处的实时交通流数据输入该模型以预测B处的未来交通流数据作为宏观交通流模型预测结果U1;建立并训练LSTM深度学习模型,利用模型对B处的未来交通流数据进行预测作为深度学习模型预测结果U2;利用线性卡尔曼滤波器将宏观交通流模型预测结果U1与深度学习模型预测结果U2融合为B的未来交通流参数的最终预测结果U3。宏观与深度学习模型的优势被集中和相互补充。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic flow parameter hybrid prediction method and device


    Weitere Titelangaben:

    一种交通流参数混合预测方法和装置


    Beteiligte:
    LI LIN (Autor:in) / HUANG QINGYUE (Autor:in) / FENG MEILING (Autor:in) / OH YONG-SIK (Autor:in)

    Erscheinungsdatum :

    2023-07-28


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Traffic situation assessment method based on traffic flow parameter prediction

    XIANG YUNHAO / SHE KUN / HU CHENGHUA | Europäisches Patentamt | 2022

    Freier Zugriff

    Highway Traffic Flow Prediction Supporting Multi-Traffic Parameter Detection

    Zhu, Ruixin / Chen, Ling / Jiang, Xinyu et al. | IEEE | 2023


    Short-term traffic flow parameter prediction method fusing traffic event influence

    JIN SHENG / CHEN NUO / YANG YING et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    TRAFFIC FLOW PREDICTION DEVICE, TRAFFIC FLOW PREDICTION METHOD, AND PROGRAM

    MATSUDAIRA MASAKI / HAYASHI MASAHIRO / MASUDA JUNKI | Europäisches Patentamt | 2020

    Freier Zugriff