The Study Of Intelligent Control Method For Traffic Signal Of Urban Single Intersection

With the development of automotive industry and people's living standards, the number of urban motor vehicles has also increased dramatically, the contradiction between road capacity and traffic demands has become more and more prominent. Under the present traffic condition, the advanced traffic signal control technology is an effective way to alleviate traffic jams and improve the traffic efficiency. This paper takes a single intersection as research object, through the study of intelligent control for the single intersection, to improve the performance of a single control. This paper studies single control with two methods, the signal timing based on improved-PSO (Particle Swarm Optimization) algorithm and fuzzy control based on the phase sequence optimization. The simulation experiments verify the effectiveness and rationality of the two control methods.Firstly, the signal timing based on improved-PSO algorithm is studied. This paper takes queue length of each phase as the optimization objectives, and uses multi-objective signal timing model to satisfy diffident traffic demands, and introduces improved-PSO algorithm to solve the problem, realize four-phase stationary sequence signal timing under different traffic conditions. On the basis of the research and analysis for PSO, the variability factor and inertia weight self-adaptability strategy were introduced to improve the PSO algorithm. The improved PSO algorithm not only plays the advantage of fast convergence speed, but also conquers the shortcoming of PSO algorithm which is easily plunging into the local minimum, and improves the performance of optimization greatly.Secondly, the fuzzy control method of traffic signal based on the phase sequence optimization is studied. Fuzzy controller takes queue length of current phase and next phase as input variables, extension time of current phase's green signal as output variable, and according to the length of the extension time to determine whether to optimize the phase sequence. This paper designs a phase optimization algorithm. On the basics of not changing main phase sequence (east-west, north-south phase), the sequence of each main phase can be adjusted flexibly based on actual traffic conditions. This method can acquire better control effect. The input variables and output variables' membership function of fuzzy controller are numerous, which are set by people presently, so the rationality can't be ensured. And unchanged membership function can't adapted time-varying traffic flow, so Genetic Algorithm (GA) was used to optimize the membership function. In the end, the two control program designed by this paper is simulated by Matlab. The simulation indicates that, the two control methods acquire better control effect than timing control. The signal timing method based on improved-PSO can get good result in balance traffic flow intersection, and the fuzzy control based on the phase sequence optimization can be used in uneven traffic flow single intersection more adaptively.