The invention provides a road section speed multi-step prediction method based on a ponding risk prediction grade. The method comprises the following steps: S1, constructing a ponding network; s2, constructing a ponding risk interval, and constructing a grid ponding risk sample case library; s3, carrying out candidate input variable collinearity analysis; s4, obtaining a ponding risk classification grade and a ponding risk value, and finally intersecting the ponding risk classification grade and the ponding risk value with the vector road network to obtain a fine-grained road segment ponding risk value; s5, establishing an urban road section speed and time long sequence data set with rainfall weather; s6, forming a model input and output data set; and S7, carrying out abnormal value discrimination on the urban road section speed prediction sequence to detect abnormal fluctuation of the road section speed in the prediction time period, and evaluating the road network state. The method is high in practicability, wide in applicability, high in precision and high in robustness, and multiple ponding influence factors are integrated for analysis; the predicted numerical value is not easily influenced by an abnormal value; the device can adapt to different roads; the reliability of analysis and prediction is determined through test verification.

    本发明提供了一种基于积水风险预测等级的路段速度多步预测方法,该方法包括:S1、构建积水网络;S2、构建积水风险区间,构建网格积水风险样本案例库;S3、进行候选输入变量共线性分析;S4、得到积水风险分类等级以及积水风险值,并最终与矢量路网相交,得到细粒度的路段积水风险值;S5、建立带有降雨天气的城市路段速度时间长序列数据集;S6、形成模型输入输出数据集;S7、对城市路段速度预测序列进行异常值判别,以检测路段速度在预测时段内的异常波动,对路网状态进行评价。本发明实用性强、适用性广、精度高、鲁棒性强,综合了多种积水影响因素进行分析;预测数值不易受到异常值的影响;可适应不同道路;经测试验证确定了分析预测的可靠性。


    Access

    Download


    Export, share and cite



    Title :

    Road section speed multi-step prediction method based on ponding risk prediction grade


    Additional title:

    基于积水风险预测等级的路段速度多步预测方法


    Contributors:
    LIN YONGJIE (author) / CHEN YUELIN (author) / LYU DUANYA (author) / LU KAI (author)

    Publication date :

    2024-06-25


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

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



    Vehicle rescue facility for ponding road section

    NIU WENJIE / YANG HAOLING / SUN JIURU et al. | European Patent Office | 2024

    Free access

    Vehicle ponding road section passing method and device, vehicle and storage medium

    LI HE / TAN MINGWEI / CAI SHIMIN et al. | European Patent Office | 2024

    Free access

    Road ponding early warning method and device

    WANG XIUJING | European Patent Office | 2021

    Free access

    Road ponding monitoring equipment with traffic indication function

    ZHANG YOUJUAN / CHEN ZHEN | European Patent Office | 2025

    Free access

    Curve road section allowable speed prediction system and method

    WANG BOTONG / KARADA / ZHOU LUJIE et al. | European Patent Office | 2024

    Free access