基于小波-Elman神经网络的信号交叉口首车到达时间预测  

Forecasting the First Vehicle’s Arrival Time at the Signalized Intersection Based on Wavelet-Elman Neural Network

作　　者：张惠玲 刘晓晓[2] 杨林玉 ZHANG Hui-ling;LIU Xiao-xiao;YANG Lin-yu(Chongqing Key Lab of Traffic System&Safety in Mountain Cities;School of Traffic&Transportation,Chongqing Jiaotong University,Chongqing 400074,China;Fangchenggang Logistics Planning and Construction,Fangchenggang 538001,China)

机构地区：[1]山地城市交通系统与安全重庆市重点实验室,重庆400074 [2]重庆交通大学交通运输学院,重庆400074 [3]防城港市物流规划建设管理办公室,防城港538001

出　　处：《科学技术与工程》2019年第28期366-371,共6页Science Technology and Engineering

基　　金：国家自然科学基金(51508061);重庆市教委项目(KJQN201800727);山地城市交通系统与安全重庆市重点实验室开放基金(2018TSSMC03)资助

摘　　要：信号交叉口首车到达时间与交叉口进口道的延误等参数具有密切的关系。选取信号交叉口首车到达交叉口时间与红灯启亮时间的时间差作为分析对象,对首车的到达时间进行了预测。考虑到周期时长的首车到达时间序列数据波动性较大,首先,使用互信息法和Cao方法确定相关参数,并应用最大李雅普诺夫指数判别时间差时间序列的混沌特性,然后,运用小波-Elman神经网络预测方法对首车的到达时间进行了预测,结果表明,预测数据的误差均值为3. 13 s。研究成果为信号交叉口延误参数的提取和信号配时优化提供了可靠的数据来源。The approach delay has close relationship with the first vehicle’s arriving time at the signalized intersections. The research parameter is the difference time between the red light beginning time and the first vehicle’s arriving time,and the parameter has been forecasted. Considering the volatile of the first vehicle’ arrival time series,the mutual information and Cao method has been used to calculate the parameter that needed in the maximum Lyapunov index discrimination,and the chaotic characteristics has been proved. Then,the time has been forecasted using the wavelet-Elman neural network method. It is proved that the average error is 3. 13 s. The research result can provide reliable data for the delay extraction and signal time optimization.

关 键 词：交通工程 信号交叉口 首车到达时间 小波分析-Elman神经网络 短时预测 

分 类 号：U491[交通运输工程—交通运输规划与管理]