摘 要:经济的发展,导致交通拥堵加剧,科学合理地解决交通相关的问题已成为一种全社会的共识。短期交通预测是一种直接估计未来短期交通状况的过程。文章介绍了BP 神经网络、RBF 神经网络及其改进算法,通过分析交通流量时间序列,使用BP 神经网络、RBF 神经网络进行短时交通流预测,并分析了在各种不同条件下的预测情况。
关键词:BP 神经网络;RBF 神经网络;交通流量预测
中图分类号:TP183 文献标识码:A 文章编号:2096-4706(2020)23-0087-04
Time Series Prediction of Traffic Flow Based on Neural Network
ZHANG Fan
(China Railway Eryuan Engineering Group Co.,Ltd.,Chengdu 610031,China)
Abstract:With the development of economy,the traffic congestion is aggravating. It has become a consensus of the whole society to solve the traffic related problems scientifically and reasonably. Short-term traffic forecasting is the process of directly estimating the short-term traffic situation in the future. This paper introduces BP neural network,RBF neural network and their improved algorithm. By analyzing the time series of traffic flow,BP neural network and RBF neural network are used for short-term traffic flow prediction,and analyzing the forecasting situation under various conditions.
Keywords:BP neural network;RBF neural network;traffic flow forecast
参考文献:
[1] 韩力群. 智能控制理论及应用 [M]. 北京:机械工业出版社,2007.
[2] 王小川,史峰,郁磊.MATLAB 神经网络43 个案例分析 [M]. 北京:北京航空航天大学出版社,2013.
[3] 喻宗泉,喻晗. 神经网络控制 [M]. 西安:西安电子科技大学出版社,2009.
[4] 李松,刘力军,翟曼. 改进粒子群算法优化BP 神经网络的短时交通流预测 [J]. 系统工程理论与实践,2012,32(9):2045-2049.
作者简介:张帆(1995—),女,汉族,甘肃张掖人,助理工程师,硕士研究生,研究方向:交通运输。