Research On Optimization Control For Urban Traffic Signal Based On Fuzzy Logic

With the rapid increase of motor vehicles,the problem of urban traffic congestion is more and more serious,which restricts the development of economy and society,and brings great inconvenience to the travel of residents.So it is especially important to solve the problem of urban traffic congestion.Improving the control efficiency of traffic signal has become an effective method to solve the problem.Aiming at the shortage of current intersection signal control methods and control subarea division methods,combined with the intelligent control theory,several aspects are researched and discussed in this dissertation,including the selection of intersection signal control scheme,the intersection significance evaluation and dynamic division of control subareas.The main contents are as follows:(1)The traffic signal control theory and the fuzzy control theory are introduced systematically.A single-stage fuzzy controller and a two-stage fuzzy controller are used in intersection signal control.The control effects of two kinds of controllers are studied under different traffic flow and the configuration of fuzzy controller is determined under different traffic flow.(2)In traffic signal control,a single control model cannot well adapt to the changes of traffic flow.To handle this problem,a combined control model is proposed,which combines the single-stage fuzzy control strategy and the two-stage fuzzy control strategy.Using SOM neural network,the switching of two control strategies is realized.In order to solve the problem that the fuzzy control rules and membership functions of the two-stage fuzzy controller are set artificially,the chaos genetic algorithm is used to optimize the parameters of the two-stage fuzzy controller.In order to ensure the real-time control,combined with the sliding time window,the rapid identification of traffic state and the online optimization of two-stage fuzzy controller parameters are achieved based on the real-time acquired data.The proposed combined control model is validated by case simulation.(3)Intersection node degree,peak traffic flow and lane occupancy as the evaluation indexes,entropy weight-TOPSIS method is used to evaluate the intersection significance.The specific steps of the intersection significance evaluation are given.The method can identify which one junction is the hub mode in the urban regional road network.(4)Most traffic control subarea division methods only take into account the correlation degree of the two intersections and ignore the importance of the hub intersection node.Aiming at this problem,a dynamic traffic control subarea division method is put forward based on hub intersection node.The hub intersection node is set as a starting point and its surrounding intersection nodes are traversed.The correlation value between two adjacent intersections is calculated using fuzzy inference.On this basis,the division of control subarea is determined by calculating the period difference between the coordinated intersection and the key intersection.Combined with an example,the subarea division model is analyzed.