基于神经网络的信号交叉口进口车道交通延误预测

摘要

Based on the theories of BP neural network,a network model suit a ble for different conditions is established for traffic delay in average hours at a signalized intersection entrance.It is trained and tested utilizing the data of traffic delay in average hours at an entrance of a signalized intersection in the city of Handan.The predicted results and the actual data are compared,and the results prove the reliability and effectiveness of the BP neural network in predicting traffic delays.Besides,more effective models can be established for the traffic delay based on the research,forecasting at intersections or in the time when the situations are more complicated.%基于误差反向传播(Back Propagation,BP)神经网络建立了适应能力较强的信号交叉口进口车道平峰时的交通延误网络模型,并利用邯郸市某信号交叉口进口车道的平峰小时交通延误的数据,对该BP神经网络预测模型进行训练和测试.比较分析预测结果和实际数据,结果表明该BP神经网络对于交叉口进口车道的交通延误预测结果可靠有效.此外,在交通情况更加复杂的信号交叉口或者时间段,以该模型为基础可以建立更加可靠的预测信号交叉口进口车道交通延误模型.