【作者】 张佳佳；

【导师】 黄辉先；

【作者基本信息】 湘潭大学 ， 电力电子与电力传动， 2004， 硕士

【摘要】 随着经济的发展和城市化水平的提高，城市交通问题日益突出，对现有交通进行有效的管理和控制已成为我国交通运输中迫切需要解决的问题，随着交通智能控制系统的展开，交通信号控制仍然是最重要的研究领域和发展项目之一。本课题就是采用人工智能的方法对城市交叉路口交通信号灯实施合理优化配时控制，以缓解日趋紧张的交通拥挤问题，提高交通效益。 本文在分析交通基本理论的基础上，根据交叉路口的实际情况，分别以等待放行车辆数为目标性能指标建立起四相位的单个交叉路口和四个交叉路口网络的信号实时优化配时模型及车流预测模型，采用智能优化算法，即遗传算法对其进行优化、仿真，遗传算法具有寻优能力强的特点使得它成为交通信号控制优化的有效手段，特别对多目标问题的优化。从仿真的结果来看，采用遗传算法优化方法及其改进的遗传算法进行交通信号配时，对单交叉路口要比传统优化方法更符合实际，对多交叉路口可以较为合理地配置交叉口的相位时间，使得路口的车辆延误时间尽可能的短，为实现交通流畅提供了重要合理的信号配时方法。更多还原

【Abstract】 With the development of economy and rise in level of urbanization, the traffic problems become more and more serious. How to manage and control the existing traffic effectively is a very important problem in traffic and transportation field. Along with the movement of Intelligent Transportation System, traffic signal control remains one of the most important research fields and development items. This paper discusses that how to use advanced science methods to control traffic signal. Through the analysis of the basic theory of traffic, the analysis of traffic flow in an intersection, two real-time models of four –phase traffic signal control according to the objective function of vehicle queue length in an intersection are presented. One is about how to distribute the phase green duration of traffic signal, the other is about how to forecast the traffic flow. The objects of these two models are respectively single intersection and traffic network that comprise four intersections. In this dissertation, the principle of the traffic signal control based on intelligent optimization, the basic optimal theories is presented. The simulation tests of phase green duration in the mode are conducted using Genetic algorithm method. The simulation results show that the optimal method of Genetic Algorithm is superior to tradition methods, and it is suitable for determining the green split in a single intersection.更多还原