The invention provides a BP neural network-based variable lane traffic flow prediction method, which comprises the steps of obtaining a day type and a time period type of a to-be-detected time period, and obtaining environmental influence factors in the to-be-detected time period; arranging the day type, the time period type and the corresponding environmental influence factors into a prediction set; processing the prediction set into a prediction vector set; and inputting the prediction vector set into a pre-trained BP neural network model, and obtaining the traffic flow in the to-be-detected time period through the pre-trained BP neural network model. The traffic flow in the to-be-measured time period is obtained through the BP neural network model, and the left turn and straight traffic flow can be predicted by inputting the day type, the time period type and the environmental influence factors; furthermore, the variable lane is changed into a left-turn lane or a straight lane at the current section through left-turn and straight traffic flow data prompts, so that the passing efficiency is effectively improved.
本发明提供一种基于BP神经网络的可变车道车流量的预测方法,包括:获取待测时段的日类型和时段类型,并获得所述待测时段内的环境影响因素;将所述日类型、所述时段类型及对应的所述环境影响因素整理为预测集合;将所述预测集合处理为预测向量集合;将预测向量集合输入预先训练好的BP神经网络模型,通过预先训练好的BP神经网络模型获取待测时段内的车流量。通过BP神经网络模型获取待测时段内的车流量,可实现输入天类型、时段类型及环境影响因素,即可预测左转、直行车流量;进一步通过左转、直行车流量数据提示将可变车道在此时段变为左转车道或直行车道,从而有效提高通行的效率。
BP neural network-based variable lane traffic flow prediction method
一种基于BP神经网络的可变车道车流量的预测方法
2021-11-19
Patent
Electronic Resource
Chinese
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 / 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 |
A Neural Network Based Traffic Delay Prediction Model for Freeway Lane Closure
British Library Conference Proceedings | 1994
|Intersection variable lane control method based on short-time traffic state prediction
European Patent Office | 2020
|Traffic flow prediction using neural network
IEEE | 2018
|