基于BP神经网络的终端区拥挤等级预测

Terminal Area Congestion Level Prediction Based on BP Neural Network

为了准确和有效地预测机场终端区拥挤等级,进而提高终端区空中交通运行效率,首先,从拥挤原因和拥挤后果2类指标入手,提取出4个终端区拥挤指标,并将其量化;然后,建立了基于反向传播(BP)神经网络的终端区拥挤等级预测模型;最后,以国内某终端管制区为例进行验证,结果表明,该预测方法对终端区拥挤等级预测的准确率达73.3%,并具有实用性。

In order to accurately and effectively predict the airport terminalarea congestion and improve the air traffic operation efficiency of terminal area,four terminal area congestion indicators are extracted and quantified from the two indexes of congestion causes and consequences.Then,a prediction model of terminal congestion level based on the back propagation(BP)neural network is established.Finally,a domestic terminal control area is taken as an example to verify,and the results show that the accuracy of the prediction method for the congestion level of the terminal area is up to 73.3%,and the prediction method is practical.