高速公路进出流量差异的BP神经网络预测模型

An Algorithm Based on BP Artificial Neural Network to Predict Differences between Input Traffic Volume and Output Traffic Volume

进出高速公路收费站车流量的差异和变化给营运管理带来一定难度。分析了造成流量差异的部分因素,建立了BP神经网络预测模型,并运用Matlab工具进行仿真及误差分析。结果显示,采用本模型可缩短训练时间,避免训练陷入局部极小值,并可对近期4d的车流量差值进行可靠预测。

The differences and changes between input traffic volume and output traffic volume in a tolling station bring some problems in management. This paper analyzes some factors bringing about the differences and changes, and presents a model based on BP Artificial Neural Network and Matlab tools. The results indicate that the model can reduce the train period, avoid minimum training, and predict the differences of recent 4D traffic flow.