城市单路口交通信号两级模糊优化控制与仿真  

Optimal Two-stage Fuzzy Control for Urban Traffic Signals at Isolated Intersection and Its Simulation

作　　者：杨文臣[1] 张轮[1] 何兆成.[2] 

机构地区：[1]同济大学交通运输工程学院,上海201804 [2]中山大学工学院∥广东省智能交通重点实验室,广东广州510275

出　　处：《中山大学学报（自然科学版）》2012年第6期41-47,共7页Acta Scientiarum Naturalium Universitatis Sunyatseni

基　　金：国家自然科学基金资助项目(50408034);上海市创新基金资助项目(11ZZ27)

摘　　要：该文提出交通信号两级模糊控制的两种优化方法。首先,针对两级模糊控制器在低流量下考虑多维交通状态变量致使路口交通状态弱化,提出一种两级组合模糊控制器,其采用0-1组合思想,立足路口交通状态特征选取模糊控制器的交通状态变量的组合及结构。接着,针对模糊控制器参数经验设置及不具备学习能力,提出一种两级模糊在线优化控制器,其引入滑动时间窗思想,采用混合遗传算法在线同时优化模糊控制器隶属函数和控制规则的参数;最后,开发两级模糊在线优化控制的Paramics仿真平台,对两种模型进行效用评价;仿真结果表明所提出的方法分别从模糊控制器结构和参数优化的角度改进了两级模糊控制器的不足,控制效果符合交通管理者的控制目标。Two optimal approaches of two-stage fuzzy controller for traffic signals at isolated intersections are presented. Firstly, from the perspective of structural optimization, a two-stage combination fuzzy controller is designed, for the consideration of multi-dimensional traffic status variables leading to the inefficiency of traffic states at intersections under low traffic flow. The controller introduces 0 - 1 combination and determines the combination of traffic status variables of fuzzy controller＇s inputs. Secondly, aiming at the problems of fuzzy controller parameter empirical settings and functional disability of learning, a two- stage fuzzy logic traffic signal controller with online optimization is proposed, for the insufficiency of fuzzy controller parameter settings and functional disability of learning. This controller introduces the rolling horizon framework and optimizes the parameters of membership functions and fuzzy rules of fuzzy controllers by using hybrid genetic algorithm. Finally, the performance of the two proposed models is validated via online Paramics-based simulation platform, and extensive relative simulation tests have demonstrated the potential of the developed controllers for adaptive traffic signal control.

关 键 词：交通工程 交通信号 模糊逻辑 组合模糊 遗传算法 

分 类 号：U491.51[交通运输工程—交通运输规划与管理] TP391.9[交通运输工程—道路与铁道工程]