非均衡交通流五岔路口交通信号智能控制研究

发布时间：2018-10-26 14:48

【摘要】：为了缓解交通拥堵,减少车辆在交叉口的等待时间,针对五岔路口非均衡交通流,采用基于人工鱼群算法的交通信号控制方法,实现了五岔路口多相位变相序的智能控制.该方法首先由红灯相位的车辆排队长度和红灯持续时间得到该红灯相位的通行紧急度,把通行紧急度最高的相位作为下一绿灯相位;其次,将当前绿灯相位车辆排队长度和筛选出的下一绿灯相位车辆排队长度与当前绿灯相位车辆排队长度的差值作为输入,利用模糊神经网络控制器实现绿灯延时.为了避免模糊神经网络陷入局部最小值,利用人工鱼群算法对模糊神经网络参数进行优化.在不同的车辆到达率情况下进行仿真研究,结果表明:该方法比传统的控制方法在自动调节信号周期方面效果更好,减少车辆平均延误7.2%左右.
[Abstract]:In order to alleviate traffic congestion and reduce the waiting time of vehicles at intersections, the traffic signal control method based on artificial fish swarm algorithm is adopted to realize the intelligent control of multi-phase sequence in five-fork junctions, aiming at the unbalanced traffic flow at five-fork junctions. Firstly, the traffic emergency degree of the red light phase is obtained from the queue length and the red light duration of the red light phase, and the phase of the highest traffic emergency is taken as the next green light phase. Secondly, the difference between the queue length of the current green phase vehicle and the current queue length of the next green phase vehicle and the queue length of the current green phase vehicle is taken as input, and a fuzzy neural network controller is used to realize the green light delay. In order to avoid the fuzzy neural network falling into the local minimum, artificial fish swarm algorithm is used to optimize the parameters of the fuzzy neural network. The simulation results under different vehicle arrival rates show that the method is more effective than the traditional control method in automatically regulating the signal cycle and reduces the average vehicle delay by about 7.2%.
【作者单位】：兰州交通大学自动化与电气工程学院;
【基金】：甘肃省科技支撑计划资助项目(1304GKCA023) 兰州市科技攻关计划资助项目(2013-4-18)
【分类号】：U491.54

【相似文献】