摘要
为得到高速公路交通量较为准确的流量预测值,本文以京哈高速河北路段内交通量为实例,采用马尔科夫链优化过的BP神经模型进行预测同时加以分析。结果表明:通过对比原有数据发现使用马尔科夫链优化过的BP模型可以将高速路交通量预测值的相对误差下降至3.97%并达到一级精度,该方法不仅可以对高速路交通量进行预测,而且也可以为相关高速路管理部门提供一定理论依据。
In order to obtain more accurate forecast of freeway traffic,this paper takes traffic in Hebei section of Beijing-Harbin Freeway as an example,and uses BP neural model optimized by Markov chain to predict and analyze at the same time.The results show that by comparing with the original data,the BP neural model optimized by Markov chain can reduce the relative error of the predicted value of freeway traffic volume to 3.97%,reaching the first-class accuracy.This method can be used not only to forecast the highway traffic volume but also to provide a certain theoretical basis for related highway management departments.
作者
裴彧
裴同松
唐艳玮
赵伯伦
Pei Yu;Pei Tongsong;Tang Yanwei;Zhao Bolun(Department of Civil Engineering,Hebei Jiaotong Vocational and Technical College,Shijiazhuang 050091;Department of Electrical and Information Engineering,Hebei Jiaotong Vocational and Technical College,Shijiazhuang 050091;China Railway Construction Bridge Engineering Bureau Group Co.,Ltd.Shijiazhuang 050000)
出处
《河北交通教育》
2021年第2期40-44,共5页
Hebei Traffic Education
关键词
马尔科夫模链
BP神经网络
高速交通量
预测
Markov model chain
BP neural network
expressway traffic volume
forecast
