The invention discloses a toll station exit flow prediction method based on a gating circulation unit. The prediction method comprises: S1, collecting the historical data of a corresponding toll station, forming a toll station exit time sequence, and dividing the time sequence into a training set and a test set; S2, establishing an initial gating cycle unit model by adopting data in the training set; S3, optimizing parameters of the initial gating cycle unit model by utilizing a locust optimization algorithm to obtain an optimal parameter combination of a gating cycle unit flow prediction model; and S4, constructing a gating cycle unit model by using the optimal parameter combination to obtain a flow prediction result of the toll station at a next moment. According to the invention, a circulation gating unit network is used for training the toll station exit flow time sequence data, correlation and potential essential characteristics between data points are deeply mined, the problem that a linear model cannot cope with randomness and instability of traffic flow is solved, parameter selection of a gating cycle network is optimized by utilizing the locust optimization algorithm, theparameter selection problem in the model training process is solved, and the precision of a final prediction result is improved.

    本发明公开了一种基于门控循环单元的收费站下道流量预测方法,预测方法包括以下内容:S1:采集对应收费站的历史数据,构成收费站下道流量时间序列,并将时间序列分为训练集和测试集;S2:采用训练集中的数据建立初始门控循环单元模型;S3:利用蝗虫优化算法对初始门控循环单元模型的参数进行优化,得到门控循环单元流量预测模型的最佳参数组合;S4:利用最佳参数组合,构建门控循环单元模型,得到下一时刻收费站的流量预测结果。本发明利用循环门控单元网络对收费站下道流量时间序列数据进行训练,深入挖掘了数据点之间的相关性以及潜在本质特征,解决了线性模型无法应对交通流随机性和不稳定性的问题,同时利用蝗虫优化算法对门控循环网络的参数选择进行了优化,解决模型训练过程中的参数选择问题,提高了最终的预测结果的精度。


    Access

    Download


    Export, share and cite



    Title :

    Toll station exit prediction method based on gating circulation unit


    Additional title:

    一种基于门控循环单元的收费站下道流量预测方法


    Contributors:
    SUN DIHUA (author) / ZHAO MIN (author) / ZHANG QIANG (author) / WU XIAO (author) / CAO WENMENG (author) / CHEN XINGZHOU (author) / JIANG CHENHU (author) / LIAO CHUNSHAN (author)

    Publication date :

    2020-10-16


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Dynamic prediction inspection method for vehicle exit station and exit time based on ETC (Electronic Toll Collection) data

    RUAN XUEFEI / LI DAQUAN / ZHU QIUSHI et al. | European Patent Office | 2023

    Free access

    Road section main line toll station exit traffic jam prediction method and system

    YANG TONG / ZHANG YUN / XIANG PENGCHENG et al. | European Patent Office | 2023

    Free access

    Expressway toll station exit flow prediction method and system based on multi-source data fusion

    ZHANG JIAN / ZHOU KAICHENG / QIAN PINZHENG et al. | European Patent Office | 2023

    Free access

    Collaborative prediction method and system for entry and exit traffic flow of highway toll station

    ZHANG YUNFAN / CHAI QINGGANG / DING XIAO'E et al. | European Patent Office | 2025

    Free access

    TOLL PROCESSING SYSTEM, EXIT PROCESSING DEVICE, CENTRAL DEVICE AND EXIT TOLL PROCESSING METHOD

    YUMIKURA YOSUKE / KARASAWA SHIGERU / NAKATANI HIROSHI et al. | European Patent Office | 2021

    Free access