The invention discloses a traffic flow prediction method based on an improved combination model and application. The method comprises the following steps: 1, extracting original traffic flow data of a predicted road section and processing the original traffic flow data into traffic flow input of the combination model; 2, a differential complementary set empirical mode decomposition (CEEMD) algorithm is adopted to decompose the traffic flow sequence into a series of traffic mode components (IMF) and residual components, and boundary local feature continuation is utilized to improve the endpoint flying wing problem in the decomposition process; 3, an improved sparrow search algorithm is used to preferentially select weight parameters of each bidirectional gating cycle unit (BiRGU), and each BiGRU network prediction model with optimal performance is constructed; and 4, taking each IMF component as an input, using each BiGRU model with the best performance to predict the IMF component, and superposing and reconstructing each predicted value to obtain a final prediction result. The invention aims to improve the accuracy of traffic flow prediction so as to assist an intelligent traffic system in relieving the traffic pressure of a road network.

    本发明公开了一种基于改进组合模型的交通流量预测方法及应用,包括:1、提取预测路段的原始交通流量数据并处理为组合模型的交通流量输入;2、采用差分互补集合经验模态分解(CEEMD)算法,将交通流量序列分解为一系列交通模态分量(IMF)及残差分量,利用边界局部特征延拓改善分解过程中的端点飞翼问题;3、使用改进麻雀搜索算法对各双向门控循环单元(BiRGU)的权值参数择优,构建性能最佳的各BiGRU网络预测模型;4、以各IMF分量为输入,使用性能最佳的各BiGRU模型分别对其进行预测,并将各预测值叠加重构得到最终预测结果。本发明旨在提升交通流量预测的精度,从而辅助智能交通系统缓解路网交通压力。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic flow prediction method based on improved combination model and application


    Weitere Titelangaben:

    一种基于改进组合模型的交通流量预测方法及应用


    Beteiligte:
    YIN LISHENG (Autor:in) / LIU PAN (Autor:in) / WU YANGYANG (Autor:in) / SHI CHENG (Autor:in)

    Erscheinungsdatum :

    16.12.2022


    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



    Improved adaptive traffic flow combination prediction method

    YIN LISHENG / SHI CHENG / LIU PAN et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Traffic flow combination prediction method

    XIONG HAO / ZHANG LI | Europäisches Patentamt | 2023

    Freier Zugriff

    Short-time traffic-flow combination prediction method

    YANG CHUNXIA / FU YIQIN / WU WENLU et al. | Europäisches Patentamt | 2015

    Freier Zugriff

    Traffic flow prediction method based on SVM algorithm improved in combination with reverse bat algorithm

    SUN YUHANG / PEI SHUJUN / REN DINGXIANG | Europäisches Patentamt | 2023

    Freier Zugriff

    Research on traffic flow prediction method based on combination models

    Nie, Jun / Xie, Weiqing / Zhang, Wen | SPIE | 2023