摘要
公路客运量具有小样本及非线性的特征,文章通过结合灰色理论与BP神经网络方法构建模型。该方法首先采用GM(1,1)模型预测出公路客运量的变化趋势,再利用BP神经网络模型对GM(1,1)模型的预测结果的残差值进行修正,以提高预测精度,弥补单一模型的不足。最后以2008年—2017年陕西省公路客运量为例,对该预测模型的精度进行验证,结果表明灰色神经网络模型能够有效地改善预测精度,具有较大的现实意义。
The small sample and non-linear characteristics of railway passenger traffic,this paper adopts the method of combining grey theory with BP neural network to build the prediction model.This method first uses the GM(1,1)model to predict the change trend of road passenger traffic,and then using the BP neural network model revise the results of the residual value of the GM(1,1)model,in order to improve the prediction accuracy and make up the lack of a single model.Finally in 2008-2017 years of road passenger traffic of shanxi province as an example,the accuracy of the prediction model is validated,the result shows that grey neural network model can effectively improve the prediction precision and has great practical significance.
作者
焦卓彬
明菲菲
石磊
Jiao Zhuobin;Ming Feifei;Shi Lei(Chang'an University,Shaanxi Xi'an 710064)
出处
《汽车实用技术》
2019年第11期246-248,共3页
Automobile Applied Technology
关键词
公路客运量
灰色预测
BP神经网络
road passenger volume
Grey prediction
BP neural network