基于神经网络模糊控制的单交叉口信号控制  

Single intersection signal control based on fuzzy neural network control

作　　者：曹洁[1] 李振宸[1] 任冰[1] 

机构地区：[1]兰州理工大学电气工程与信息工程学院,甘肃兰州730050

出　　处：《兰州理工大学学报》2010年第1期86-90,共5页Journal of Lanzhou University of Technology

基　　金：甘肃省自然科学基金(0710RJZA060)

摘　　要：在分析城市交通信号控制研究现状的基础上,提出一种基于神经网络模糊控制的单路口交通信号灯控制方法,通过检测当前相位的排队长度和下一相位的排队长度得出当前相位以及下一相位的车流密度,进而判断是否进行相位变换.以每个周期内交叉口的车辆平均延误作为控制指标,来判断该控制器的控制性能.计算机仿真结果表明,该方法能够降低车辆在交叉路口的平均延误.Based on the analysis of current situation of urban traffic signal control, a method of single intersection signal control was presented based on fuzzy neural network control. Density of vehicle flow of current and next phase was determined by detecting the queue length of the current and next phase, so that it was further determined whether the phase should be changed or not. The average delay of the vehicles passing through the intersection in a period was taken as performance index in order to estimate the performance of this controller. It was shown by the result of computer simulation show that this method could decrease the average delay of the vehicles.

关 键 词：神经网络模糊控制 排队长度 车流密度 仿真 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] U491[自动化与计算机技术—控制科学与工程]