Font Size: a A A

Research On Intelligent Control Of Traffic Signal Based On Dynamic-Fuzzy Neural Networks

Posted on:2018-08-19Degree:MasterType:Thesis
Country:ChinaCandidate:H L DongFull Text:PDF
GTID:2322330518966940Subject:Power system and its automation
Abstract/Summary:PDF Full Text Request
Since the 21 st century,with the rapid development of China's economy and technology,the number of cars on the road is exploding and the problem of urban traffic congestion is more and more serious.It has caused severe environmental pollution,energy waste,traffic accident and so on.Especially,the smog brings great trouble to people.Urban traffic congestion mainly occurs in the intersection.The traditional intersection traffic signal control mode has an irrational problem of the green time distribution,so sometimes it can cause unnecessary congestion.A reasonable control system has a profound influence for improving traffic current situation.In the traffic network,traffic flow is nonlinear,real-time and changeable.For the features above,intelligent control method is used for urban traffic control.In this dissertation,we mainly study the special five-road intersection and adjacent intersection in city.To reduce the average delay of vehicles and come true reasonably distributing green time in five-road intersection,fuzzy system combining neural network is used for traffic signal control.Firstly,basic parameters of traffic signal control,statistical distribution of traffic flow,evaluation system of traffic quality and detection of traffic are simply introduced.Secondly,fuzzy control is used in traffic signal control of five-road intersection to achieve intelligent control of five-road intersection.In the case of low peak period and high peak period of traffic flow,time control and fuzzy control are used to study five-road intersection control.The simulation result shows the advantage of fuzzy control.Thirdly,considering the problems of wasting green time and switching phase frequently in fixed phase order control of traffic signal,theory of dynamic-fuzzy neural networks is introduced to come true dynamic control of multi-phase and variable phase order in five-road intersection.Taking the five-road intersection formed by Songzhou Road,Zhenxing Road and Linhuang Road in Chifeng City as an example,the simulation study is carried out to verify the performance of dynamic control of multi-phase and variable phase order.Finally,the coordination control of adjacent intersections is studied.For the adjacent intersections with small distance between the middle section,the correlation is relatively strong.In the control,the influence brought by traffic flow in middle section Entering and leaving the intersection for green light phase is considered.The simulation shows that the coordinated control is more effective than the ordinary isolated intersection control.
Keywords/Search Tags:Traffic signal control, Fuzzy control, Dynamic-fuzzy neural networks, Five-road intersection, Adjacent intersection
PDF Full Text Request
Related items