基于遗传算法的城域交叉路口两级模糊控制

Two-stage fuzzy logic controller based on genetic algorithm for urban traffic intersection

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域交叉路口的交通控制,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,提出了一种面向城域单交叉路口的自适应两级模糊控制系统,并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调整.该控制系统具有分级模糊控制的优点,同时可以让模糊隶属度的选取更为合理,使模糊隶属度函数在不同交通情况下自适应地变化,从而改善控制效果.对一个两相位孤立交叉口进行仿真.结果表明该法能有效降低通行车辆在交叉口的平均等待时间.

Twostage fuzzy logic controller, which is easy to acquire fuzzy rules and can greatly decrease the number of fuzzy rules, is very suitable to complex urban traffic intersection control. But it still presents a difficulty for deciding all the membership functions correctly only by human experience. A hierarchical adaptive fuzzy control system for an isolated urban traffic intersection using genetic algorithm to modify its fuzzy membership functions is proposed. This control system not only possesses the advantages of hierarchical fuzzy control, but can change its membership functions adaptively to an optimal setting in different traffic situations as well, and in this way the currency power of the urban intersection is improved. Simulation of an isolated urban intersection with twophase signal control shows that this method can effectively decrease the average delaying time in the intersection.