摘要
当前国内铁路运输行业发展迅速,需要对客运量进行准确的预测以达到合理地调度。以青岛市为例,通过分析全市人口、GDP等因素,分别建立多元回归数学分析模型以及BP神经网络预测模型,将两组预测模型计算结果与实际对比,研究表明BP神经网络预测模型误差较低,预测效果优于回归预测分析模型。
The domestic railway transportation industry is developing rapidly at present,so it is necessary to predict the passenger volume accurately in order to achieve reasonable dispatch.Taking Qingdao as an example,this paper establishes the multivariate regression mathematical analysis model and BP neural network prediction model by analyzing the population,GDP and other factors of Qingdao.Compare the results of the two prediction models with the actual situation.The research shows that the BP neural network prediction model has lower error and better prediction effect than the regression prediction analysis model.
作者
王小凡
朱永强
WANG Xiao-fan;ZHU Yong-qiang(School of Mechanical and Automotive Engineering,Qingdao University of Technology,Qingdao 266520,China)
出处
《黑龙江交通科技》
2019年第6期184-185,189,共3页
Communications Science and Technology Heilongjiang
关键词
铁路
客运量
BP神经网络
回归分析
预测
Railway
Passenger volume
BP neural network
Regression analysis
Prediction
