多相位交通信号模糊控制规则的优化  

Optimization of Multiphase Traffic Signals Fuzzy Control Rule

作　　者：陈淑燕[1] 周振国[1] 陈森发[1] 

机构地区：[1]东南大学系统工程研究所

出　　处：《公路交通科技》2003年第6期89-92,104,共5页Journal of Highway and Transportation Research and Development

摘　　要：讨论应用遗传算法优化多相位交通信号模糊控制器的规则库,给出编码方案、基于随机模拟的适配度计算方法以及基于适配度比例的选择、均匀交叉、自适应变异算子的具体实现细节,并构造检测染色体合法性的约束条件。为了比较GA优化所得规则库和人工设定规则库的控制效果,在相同车流状况下,对一个四相位交叉口进行仿真试验,仿真结果表明优化效果比较满意,使用GA优化所得的规则库可以明显提高模糊控制器的性能。In this paper, the rule optimization method based on genetic algorithm is applied to optimize the rules of multiphase traffic signal fuzzy controller The encoding scheme, fitness calculating method based on stochastic simulation, the realization details of fitness proportionate selection, uniform crossover, self-adaptive mutation are discussed, and the constraint is also constructed to inspect the legality of chromosome. In order to compare the controlling effect of the rule base optimized by GA with artificial rule base, a simulation experiment at a four-phase intersection is also performed under the same vehicle flows. The computer simulation results show that the effect of the optimization is satisfactory, and the rule base obtained by GA can improve the performance of the fuzzy controller obviously.

关 键 词：模糊控制 遗传算法 规则 优化 

分 类 号：TP273.4[自动化与计算机技术—检测技术与自动化装置]