摘要
高速铁路短期客流预测是铁路运输系统的重要组成部分。无论是对列车开行方案的制定,还是对如何采取正确的营销策略,都具有重大的现实意义。通过混合经验模态分解方法和神经网络方法相结合的EMD-BPN方法来预测高速铁路短期客流量。组合方法主要分为三步:首先,使用经验模态分解方法将客流时间序列分解;其次,将IMFs作为BP神经网络的输入;最后,应用神经网络对客流量做出预测。数值实例表明,该方法对于高速铁路短期客流预测在精度和稳定性上都有良好的表现。
High speed rail short-term passenger flow forecasting is a vital component of rail transport system .The forecasting results has a great practical significance not only to developed train operation scheme ,but also to take appropriate marketing strategy .In this paper ,a hybrid EMD-BPN forecasting approach which combines empirical mode decomposition （EMD） and back-propagation neural networks （BPN） is developed to predict the short-term passenger flow in high speed rail systems .The first stage （EMD Stage） decomposes the short-term passenger flow series data into a number of intrinsic mode function （IMF） components .The second stage （Component Identification Stage） identifies the meaningful IM Fs as inputs for BPN .T he third stage （BPN Stage ） applies BPN to perform the passenger flow forecasting .The experimental results indicate that the proposed hybrid EMD-BPN approach performs well and stably in forecasting the short-term High Speed Rail passenger flow .
出处
《交通科技与经济》
2015年第1期10-12,共3页
Technology & Economy in Areas of Communications
基金
国家自然科学基金资助项目(71161016
11361031)
关键词
高速铁路
经验模态分解
神经网络
短期客流预测
high-speed rail
empirical mode decomposition
neural network
short-term traffic forecast
