Research On Signal Control Under Mixed Traffic Environment

With the rapid development of economy and the acceleration of urbanization,the traffic demand is increasing,urban traffic congestion and a series of problems have become more and more serious.The intersections play an important role in urban traffic network.Therefore,it can effectively solve the traffic problems by the scientific and reasonable intelligent control of the intersection signal.However,the best way to solve these problems is to carry out intelligent control of the intersection signal according to the mixed traffic flow in China,which is of great significance.The prediction methods of short-term traffic flow are analyzed in this paper,the real-time is poor and the online prediction can’t be realized.Aiming at this problem,the BP neural network algorithm based on adaptive moving window is proposed to forecast the short-term traffic flow.The results show that the prediction accuracy of the proposed method is higher,it ensures that the data of signal control is real-time and accurate.According to the characteristics of mixed traffic flow in China,with four phase single intersection as the research object,a phase sequence-changeable fuzzy control model based on the transforming factor is designed.In this model,various factors such as the queue length in each direction of the intersection,vehicle arrival rate and the number of the delay in the release phase are considered to determine the switching sequence of phase and distribution of green light time.And the minimum green time optimization model is established to determine the minimum green light time of intersection in each direction,based on predicted traffic flow and phase distribution of intersections.The average delay of vehicles at the intersection is taken as the index for evaluating the performance of signal control,MATLAB is used for simulation and comparison,the simulation results verify the effectiveness of the designed model.Considering the parameters of the fuzzy controller are designed based on artificial experience,it is not enough accurate and objective.Therefore,on the premise of a phase sequence-changeable fuzzy control model based on the transforming factor,a fuzzy control model based on Particle Swarm Optimization(PSO)algorithm is designed,namely the particle swarm optimization algorithm is used for optimizing the membership functions and rules of the fuzzy controller.The simulation results show that the optimized fuzzy control method can further reduce the average delay of the vehicle,the control effect of the model is improved and the superiority of the proposed method is verified.