Signal Adaptive Control of Isolated Intersection Based on Type-Two Fuzzy Control

Abstract

In this paper, the signal control problem of isolated intersection during peak period is studied based on the type-two fuzzy control method to reduce the vehicle delay of isolated intersection. Firstly, the traffic flow model and evaluation index model of isolated intersection are established, and the factors of saturation flow rate and lane length are fully considered. In order to relieve the traffic pressure effectively, a type-two fuzzy controller is proposed for the signal control method, which solves the coordination and dynamic uncertainty problems in the traffic of isolated intersection. By using adaptive genetic algorithm to optimize the parameters of membership function in the type-two fuzzy controller, the parameters of the type-two fuzzy controller can be adjusted in real time according to the change of traffic flow, so that the controller can achieve adaptive control effect of traffic signals. At last, the simulation results show that the type-two fuzzy controller designed in this chapter has a better control effect in the peak period of traffic flow and reduces the vehicle delay of isolated intersection. 1 Establishment of four phase isolated intersection model In the field of traffic control, the study of signal control algorithms at isolated intersections is the basis [1] . In recent years, the development of artificial intelligence technology is getting faster and faster, so the research on the intelligent control methods of isolated intersection signals is also increasing. Among them, fuzzy control is very popular in the field of traffic control [2] because it does not rely on the mathematical model of the controlled system. J. Guo proposed a particle swarm optimization to reduce vehicle delays based on Akcelik delay model [3] . Junjie Lu designed a two-step fuzzy controller for a isolated intersection system and optimized the controller parameters using a differential evolution algorithm. The results prove that the controller has achieved good control results [4] . M. J. Shirvani Shiri adopted a fuzzy control method to adjust the maximum green light time in response to real-time traffic conditions in an isolated intersection, proving the effectiveness and robustness of the proposed method [5-6] . D. Nagarajan proposed an improved interval neutron number scoring function using triangular interval type II fuzzy numbers and interval neutron number scores to control traffic flow by identifying intersections with more vehicles [7] . Based on the above discussion, this paper designs a type-two fuzzy controller. At the same time, the adaptive genetic algorithm was used to optimize the membership parameters