本文在分析城市交通信号控制研究现状和交叉口交通信号控制原理、评价方

法的基础上，设计了单交叉口交通信号两级模糊控制系统。分级模糊控制能有效

减少模糊规则数，易于提取模糊规则，适合于交通状况复杂的城市交叉口交通信

号控制。但它存在难以由人工合理定义全部模糊隶属度函数的问题。为此本文进

一步采用遗传算法对两级模糊控制器中模糊隶属度函数进行优化。本文提出的方

法具有分级模糊控制的优点，同时可以使模糊隶属度的选取更为合理，获得更好

的控制效果。对一个四相位单交叉口，利用MATLAB在不同的交通条件下进行

了仿真，并利用交通仿真软件PARAMICS进行了可视化仿真。仿真结果表明该

方法能有效降低通行车辆在交叉口的平均等待时间，明显优于传统控制方法-After analyzing the city-traffic developments,the grade crossings control theory

its method of evaluation,the paper designs a traffic signal two-stage fuzzy control

tem for single intersection.Two-stage fuzzy controller,which is easy to acquire

zy rules and can greatly decrease the number of fuzzy rules,is very suitable to

plex urban intersection control.But it still presents a difficulty for deciding all the

bership functions correctly only by human experience.Therefor,to solve this

blem,a technique using genetic algorithm to modify its fuzzy membership

ctions is proposed.This method not only possesses the advantages of hierarchical

zy control,but also can change its membership functions adaptively to an optimal

ing in different traffic situations as well,and in this way the currency power of the

an intersection is improved.For a single urban intersection with four-phase,

ulation of different traffic condition is processed by using MATLAB.Moreover,

ble simulation is proce