基于遗传算法的交叉口信号配时优化研究  

Research on Intersection Signal Timing Optimization Based on Genetic Algorithm

作　　者：张军[1] 刘克非 Zhang Jun;Liu Kefei(School of Artificial Intelligence;School of Mechanical Engineering,Anhui University of Science and Technology,Huainan,Anhui 232001,China)

机构地区：[1]安徽理工大学人工智能学院,安徽淮南232001 [2]安徽理工大学机械工程学院,安徽淮南232001

出　　处：《黑龙江工业学院学报（综合版）》2023年第10期82-88,共7页Journal of Heilongjiang University of Technology(Comprehensive Edition)

基　　金：国家自然科学基金资助项目(项目编号:51175005);教育部协同育人项目(项目编号:202101054003);安徽理工大学研究生核心课程项目(项目编号:2021HX013)。

摘　　要：随着城市化进程的不断推进,汽车保有量逐年提高,交通拥堵问题愈发严重,改善交叉口通行效率成为当务之急。以交叉口平均延误最短、平均停车次数最少、通行能力最大为优化目标,以各相位有效绿灯时间和信号周期时长为约束,构建平面交叉口信号配时多目标优化非线性函数模型,并进行归一化。选取淮南市某一典型交叉口为研究对象,实地统计交叉口交通数据,借助MATLAB仿真平台对模型进行遗传算法优化,同时利用Webster信号配时优化。研究表明,遗传算法优化后的交叉口信号周期从140s变为107s,减少了23.57%,平均延误时间从52.48s变为42.0371s,减少了19.89%,车辆平均停车次数从0.862次/辆变为0.7844次/辆,减少了9.1%,通行能力从4398.3pcu/h提高至4832.2pcu/h,提高了9.86%,能够有效减少停车延误及停车次数,缩短信号周期,优于已有控制方案和传统Webster配时,城市交叉口的交通拥堵问题能够被缓解。With the development of urbanization,car ownership is increasing annually,and traffic congestion is becoming more serious.This paper takes the minimum average delay,the minimum average number of stops,and the maximum capacity as the objectives of the intersection,limits the effective green light time and signal cycle time of each phase,constructs and normalizes the multi-objective optimization nonlinear function model of signal timing at a plane intersection.A typical intersection in Huainan city was selected as the research object.Traffic data of the intersection were counted in the field.Genetic algorithm and Webster signal timing optimization were solved by MATLAB simulation platform.The study showed that the GA optimized intersection signal cycle decreased by 23.57%from 140s to 107s,average delays decreased by 19.89%from 52.48s to 42.0371s,average stops decreased by 9.1%from 0.862 times/vehicle to 0.7844 times/vehicle,capacity increased from 4398.3pcu/h to 4832.2pcu/h,improved 9.86%,can effectively reduce the stopping delay and the number of stops,shorten the signal cycle,is better than the existing control scheme and the traditional Webster timing,and the traffic congestion problem of urban intersections can be alleviated.

关 键 词：单点信号交叉口 信号配时 遗传算法 多目标优化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] U491.51[自动化与计算机技术—计算机科学与技术]