The invention provides a highway travel time prediction method and system under a sparse data condition, and belongs to the technical field of highway management and operation, and the method comprises the steps: obtaining highway vehicle trajectory data, and carrying out the calculation to obtain a space-time velocity field under a real traffic condition; constructing a physical information deep learning model to estimate a space-time velocity field; and constructing an STALSTM model to predict the highway travel time. According to the method, a deep learning model based on physical information is constructed and used for estimation and reconstruction of the space-time velocity field, the model provides prior knowledge of a traffic flow theory for a deep learning neural network, and sparse data is utilized to perform more accurate space-time velocity field estimation with higher generalization ability. According to the method, the importance of space-time information in traffic data is considered, a space and time attention mechanism is combined, a space-time attention long-short-term memory network model is constructed to predict travel time, space weights and time weights are dynamically distributed to input elements, the space-time information is better captured, and the accuracy and robustness of travel time prediction are improved.
本发明提供一种在稀疏数据条件下的高速公路行程时间预测方法及系统,属于高速公路管理运营技术领域,获取高速公路车辆轨迹数据,计算得到真实交通状况下的时空速度场;构建物理信息深度学习模型估计时空速度场;构建STA_LSTM模型预测高速公路行程时间。本发明构建基于物理信息的深度学习模型,用于时空速度场的估计重建,该模型为深度学习神经网络配备了交通流理论的先验知识,利用稀疏数据进行更准确更具泛化能力的时空速度场估计。考虑交通数据中的时空信息的重要性,结合空间和时间注意力机制,构建时空注意力长短期记忆网络模型来预测行程时间,动态分配空间权重和时间权重给输入要素,更好地捕捉时空信息,提高了行程时间预测的准确性和鲁棒性。
Expressway travel time prediction method and system under sparse data condition
在稀疏数据条件下的高速公路行程时间预测方法及系统
2024-09-13
Patent
Electronic Resource
Chinese
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 / 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 |
Travel Time Prediction Method for Expressway Using Toll Collection System Data
British Library Conference Proceedings | 2000
|Travel Time Calculation Method for Expressway Using Toll Collection System Data
British Library Conference Proceedings | 1999
|Travel Time Prediction of Urban Expressway in Unstable Traffic Flow
British Library Conference Proceedings | 2007
|