摘要
精确的预测机场旅客吞吐量对贵阳龙洞堡机场提供最优调配具有重要意义。文章首先运用灰色关联度计算出各个影响因素与旅客吞吐量之间的关联度;然后合理选择隐含层神经元个数及输入层、隐含层、输出层的激励函数,提高预测精度,使误差达到最小;用BP神经网络模型选取2005-2009年数据作为网络训练样本,2010-2014年五年数据为测试样本。结果表明:对2010-2014年旅客吞吐量的预测值与实际值之间的误差较小,然后通过设定好的BP神经网络对2015年的机场旅客吞吐量进行预测。
Abstract： The accurate prediction of airport passenger throughput is very important for the optimal allocation of Guiyang Longdongbao Airport. In this paper, firstly, the grey correlation degree is used to calculate the correlation degree between each influencing factor and the passenger＇s throughput. Then, the number of hidden layer neurons and the excitation functions of the input layer, hidden layer and output layer are reasonably selected to improve the prediction accuracy and make the minimum error smaller. BP neural network model is used to select the data in 2005-2009 as the network training samples, the data in 2010-2014 as the test samples. The results show that the error between the predicted value and the actual value of the passenger throughput in 2010-2014 is small, and the BP neural network is set up to predict the airport passenger throughput in 2015.
出处
《价值工程》
2016年第13期101-103,共3页
Value Engineering
基金
贵州省大学生创新创业训练计划项目"基于BP神经网络的龙洞堡机场旅客吞吐量预测研究"
关键词
BP神经网络
机场旅客吞吐量
预测精度
灰色关联度
BP neural network
airport passenger throughput
prediction accuracy
grey relational degree
