组合模型在机场旅客吞吐量预测中的应用

Application of Combination Model in Airport Passenger Throughput Prediction

研究机场运输优化控制问题,机场旅客吞吐量受到政治、经济、节假日、票价和天气等多种因素影响,具有周期性和非线性变化特点,传统单一预测方法只能描述其部分变化规律,预测精度低。为了提高机场旅客吞吐量预测,将灰色模型和BP神经网络相结合,形成一种机场旅客吞吐量组合预测模型。首先组合预测模型利用灰色模型对线性变化部分进行预测,然后采用BP神经网络对非线性变化部分进行预测,并对预测误差进行补偿。仿真结果表明,组合模型,解决了单一预测模型存在的缺陷,提高了机场旅客吞吐量预测精度,为机场旅客吞吐量预测提供一种新的思路。

Study the optimal control problem of airport transportation.Airport passenger throughput is affected by political,economic,holidays,fares and weather and other factors,has periodicity and nonlinear characteristics.The traditional single prediction methods can only describe the part of its variation,and the accuracy of prediction is low.In order to improve the airport passenger throughput prediction,grey model and BP neural networks were combined to form a combined forecasting model of airport passenger throughput.The combined forecasting model used gray model to predict linear change part,and then the BP neural networks was used to predict the nonlinear variation rule.Finally,the BP neural network was used to compensate the forecast error.The simulation results show that combined model has solved the defects of the single prediction model and improved the airport passenger throughput prediction accuracy.It provides a new thought for the airport passenger throughput prediction.