高速公路交通流建模及匝道控制研究
|
摘要
准确的交通流模型不仅有利于理解车辆的行驶行为,而且对分析交通状况,规划交通网络和实现交通优化控制策略都有十分重要的作用。入口匝道控制通过调节进入高速公路的车辆数目可以使高速公路交通流运行在最佳状态,从而提高主线的通行能力,避免拥挤和阻塞。本文详细探讨了高速公路交通流建模及入口匝道控制。全文的主要工作如下:
1.提出用小波变换消除交通噪声和干扰信号,用动态回归神经网络建立交通流模型。分析了高速公路宏观交通流模型,阐述了小波消噪方法,并用Elman回归神经网络对交通流动态建模,采用一种改进的算法得到神经网络的权值,最后对一条5路段,1个入口匝道和1个出口匝道的高速公路进行仿真。为了比较,还用BP神经网络和RBF神经网络对交通流建模。结果表明,Elman回归神经网络模型训练步数最少、误差最小、泛化能力最好。
2.采用非线性反馈方法对高速公路进行入口匝道控制。建立了高速公路交通流动态模型,在此基础上,结合先进的PID控制设计了三种非线性反馈匝道控制器:免疫控制器、单神经元自适应控制器以及模糊免疫控制器,并分别用MATLAB对它们进行了系统仿真,仿真结果表明,非线性反馈方法具有良好的控制效果。
3.采用递阶结构和CMAC进行高速公路多匝道控制。建立了反映高速公路交通流动态变化的宏观模型,研究了CMAC与PID复合控制算法。递阶结构分为两层:协调控制层负责计算各路段的期望密度轨线,直接控制层采用CMAC与PID复合控制决定各匝道的调节率,最后用MATLAB进行系统仿真。结果表明,与模糊逻辑控制相比较,复合控制具有更好的动态性能,更快的响应速度,该方法能有效地消除交通拥挤,实现车辆在高速公路上高效、安全地运行。
Accurate model of traffic flow is important not only for better understanding of the collective behaviour of vehicles, but also for analyzing flow conditions, planning traffic networks, and designing efficient control strategies. On-ramp control can make traffic flow move in optimum conditions by regulating the number of vehicles entering a freeway entrance point, thus improve the passing capability of the mainline, and avoid traffic jams and congestion. Freeway traffic flow modeling and on-ramp metering have been presented and discussed in detail. The main contributions can be stated as follows.
1. The wavelet transform is used to eliminate traffic noise and disturbance, and the traffic flow model is built based on a recurrent neural network in this paper. First, the freeway macroscopic traffic flow model is analyzed. Then the noise elimination method of wavelet transform is formulated, and Elman recurrent network is used for traffic flow modeling. The weights of the Elman network are obtained with an improved algorithm. Finally, a freeway with five segments, an on-ramp and an off-ramp is simulated. BP and RBF neural networks are chosen in contrast to the Elman network. The results show that the Elman network has the fewest training epochs, the smallest error and the best generalization ability.
2. Nonlinear feedback methods are proposed for freeway on-ramp metering. The freeway traffic flow dynamic model is built. Based on the model and in conjunction with advanced PID control, three nonlinear feedback ramp controllers are designed: artificial immune controller, single neuron network self-adaptation controller, and fuzzy-immune controller. The above controllers are simulated seperately in MATLAB software. Simulation results show that nonlinear feedback is effective to the on-ramp control.
3. The hierarchical structure and CMAC (Cerebellar Model Articulation Controller) are used for freeway ramp metering. The macroscopic model to describe the evolution of freeway traffic flow is first established. The algorithm of the composition controller of PID and CMAC is then studied. There are two layers in this control architecture: the coordinated control layer is responsible for computing the desired state of each segment, and the direct control layer is in charge of the ramp metering rate via the composition controller of PID and CMAC. Finally, the control system is simulated in MATLAB software and fuzzy logic control is also chosen in contrast to the composition control. The result shows that the composition controller improves evidently on the aspects of response speed and dynamic performance. The method can effectively eliminate traffic jams, andmake vehicles travel more efficiently and safely.
1.提出用小波变换消除交通噪声和干扰信号,用动态回归神经网络建立交通流模型。分析了高速公路宏观交通流模型,阐述了小波消噪方法,并用Elman回归神经网络对交通流动态建模,采用一种改进的算法得到神经网络的权值,最后对一条5路段,1个入口匝道和1个出口匝道的高速公路进行仿真。为了比较,还用BP神经网络和RBF神经网络对交通流建模。结果表明,Elman回归神经网络模型训练步数最少、误差最小、泛化能力最好。
2.采用非线性反馈方法对高速公路进行入口匝道控制。建立了高速公路交通流动态模型,在此基础上,结合先进的PID控制设计了三种非线性反馈匝道控制器:免疫控制器、单神经元自适应控制器以及模糊免疫控制器,并分别用MATLAB对它们进行了系统仿真,仿真结果表明,非线性反馈方法具有良好的控制效果。
3.采用递阶结构和CMAC进行高速公路多匝道控制。建立了反映高速公路交通流动态变化的宏观模型,研究了CMAC与PID复合控制算法。递阶结构分为两层:协调控制层负责计算各路段的期望密度轨线,直接控制层采用CMAC与PID复合控制决定各匝道的调节率,最后用MATLAB进行系统仿真。结果表明,与模糊逻辑控制相比较,复合控制具有更好的动态性能,更快的响应速度,该方法能有效地消除交通拥挤,实现车辆在高速公路上高效、安全地运行。
Accurate model of traffic flow is important not only for better understanding of the collective behaviour of vehicles, but also for analyzing flow conditions, planning traffic networks, and designing efficient control strategies. On-ramp control can make traffic flow move in optimum conditions by regulating the number of vehicles entering a freeway entrance point, thus improve the passing capability of the mainline, and avoid traffic jams and congestion. Freeway traffic flow modeling and on-ramp metering have been presented and discussed in detail. The main contributions can be stated as follows.
1. The wavelet transform is used to eliminate traffic noise and disturbance, and the traffic flow model is built based on a recurrent neural network in this paper. First, the freeway macroscopic traffic flow model is analyzed. Then the noise elimination method of wavelet transform is formulated, and Elman recurrent network is used for traffic flow modeling. The weights of the Elman network are obtained with an improved algorithm. Finally, a freeway with five segments, an on-ramp and an off-ramp is simulated. BP and RBF neural networks are chosen in contrast to the Elman network. The results show that the Elman network has the fewest training epochs, the smallest error and the best generalization ability.
2. Nonlinear feedback methods are proposed for freeway on-ramp metering. The freeway traffic flow dynamic model is built. Based on the model and in conjunction with advanced PID control, three nonlinear feedback ramp controllers are designed: artificial immune controller, single neuron network self-adaptation controller, and fuzzy-immune controller. The above controllers are simulated seperately in MATLAB software. Simulation results show that nonlinear feedback is effective to the on-ramp control.
3. The hierarchical structure and CMAC (Cerebellar Model Articulation Controller) are used for freeway ramp metering. The macroscopic model to describe the evolution of freeway traffic flow is first established. The algorithm of the composition controller of PID and CMAC is then studied. There are two layers in this control architecture: the coordinated control layer is responsible for computing the desired state of each segment, and the direct control layer is in charge of the ramp metering rate via the composition controller of PID and CMAC. Finally, the control system is simulated in MATLAB software and fuzzy logic control is also chosen in contrast to the composition control. The result shows that the composition controller improves evidently on the aspects of response speed and dynamic performance. The method can effectively eliminate traffic jams, andmake vehicles travel more efficiently and safely.
引文
[1]刘智勇.智能交通控制理论及其应用.北京:科学出版社,2003.
[2]史忠科,黄辉先,曲仕茹等.交通控制系统导论.北京:科学出版社,2003.
[3]J.X.Xu and Y.F.Xing.A learning approach for freeway traffic control.International Conference on Control and Automation,2005,887-892.
[4]王殿海.交通流理论.北京:人民交通出版社,2002.
[5]Kinzer,J.P.Application of the theory of probability to problem of highway traffic.B.C.E.thesis,Politech.Inst.Brooklyn,1933.
[6]Adams,W.F.Road traffic considered as a random series.J.Inst.Civil Eng,1936,4:121-130.
[7]Greenshields,B.D.A study of traffic capacity.Proc.Highway Res.Board,1934,14:448-477.
[8]Lighthill M.J.Whitham G.B.On kinematic waves:Pt I Flow movement in long rivers;Ⅱ.A theory of traffic flow on long crouded road.Proc Roy Soc A,1955,229:281-316.
[9]王雷.一维交通流元胞自动机模型中自组织临界性及其相变行为的研究.中国科学技术大学博士学位论文,2004.
[10]Ho F,Ioannou P.Traffic flow modeling and control using artificial neural networks.IEEE Control System,1996,16-26.
[11]Shinya K,Partha C.Car-following model based on fuzzy inference system.TRB,1365.1992,99-111.
[12]张智勇,荣建,任福田.跟车模型研究综述.公路交通科技,2004,21(8):108-113.
[13]欧海涛,张文渊,杨煌普等.高速公路交通流的RBF神经网络建模.上海交通大学学报(自然科学版),2000,34(5):665-668.
[14]罗赞文,吴志坚,韩曾晋.RBF网络在交通流模型辨识中的应用.清华大学学报(自然科学版),2001,41(9):106-110.
[15]撒元功,胡郁葱,徐建闽.高速公路动态交通流的神经网络模型.华南理工大学学报(自然科学版),2002,30(8):91-94.
[16]肖健梅.RBF神经网络在高速公路交通流建模中的应用.第五届全球智能控制与自动化大会,2004,5208-5211.
[17]顾国庆等.交通系统的元胞自动机模型.系统工程理论方法应用,1995,4(1):12-17.
[18]梁新荣.高速公路智能控制方法研究.华南理工大学博士论文,2005.
[19]王亦兵,罗赞文,韩曾晋.城市高速公路交通中的控制问题.中国公路学报,1997,10(3):89-93.
[20]王亦兵,韩曾晋,贺国光.城市高速公路交通控制综述.自动化学报,1998,24(4):484-493.
[21]黄小原,樊治平,张文江.高速公路入口交通控制问题的研究.系统工程,1989,(11):36-41.
[22]Papageorigiou M.Kotsialos,A.Freeway ramp metering:an overview.Intelligent Transportation Systems.2000,Proceedings IEEE.Oct,2000:228-239.
[23]Kotsialos,A.,and Papageorgiou,M.The importance of traffic flow modeling for motorway traffic control.Networks and Spatial Economics,2001,76(1):179-203.
[24]罗赞文,吴志坚,韩曾晋.RBF网络在交通流模型辨识中的应用.清华大学学报(自然科学版),2001,41(9):106-110.
[25]欧海涛,张文渊,杨煜普等.高速公路交通流的RBF神经网络建模.上海交通大学学报(自然科学版),2000,34(5):665-668.
[26]撒元功,胡郁葱,徐建闽.高速公路动态交通流的神经网络模型.华南理工大学学报(自然科学版),2002,30(8):91-94.
[27]撒元功.高速公路交通流模型与控制方法研究.华南理工大学博士论文,2002.
[28]Xiao,J.M.Application of RBF neural network to freeway traffic flow modeling.Proceedings of the 5th World Congress on Intelligent Control and Automation,Hangzhou,China,2004,5208-5211.
[29]Abdalla,M.I.Digital tection techniques via Elman neural network.Journal of Engineering and Applied Science,2002,49(6):1197-1208.
[30]M.Papageorgiou.ALINEA:A local feedback control law for on-ramp metering.In Transportation Research Record 1320,1991.
[31]M.Papageorgiou.ALINEA local ramp metering:Summary of field results.In Transportation Research Record 1603,1997.
[32]梁新荣,刘智勇,毛宗源.高速公路非线性反馈模糊逻辑匝道控制器.控制理论与应用,2006,23(1):99-102.
[33]杜启亮,高向军,莫鸿强.人工免疫PI控制器在窑头温度控制中的应用.第六届全球智能控制与自动化大会论文集,2006,3533-3537.
[34]付冬梅,郑德玲,位耀光.人工免疫控制器的设计及其控制效果的仿真.北京科技大学学报,2004,26(4):442-445.
[35]刘金琨.先进PID控制MATLAB仿真(第2版),电子工业出版社,北京,2004.
[36]H.M.Zhang,S.G.Ritchie,R.Jayakrishnan.Coordinated traffic responsive ramp control via nonlinear state feedback.Transportation Research,Series C,2001,(9):337-352.
[37]梁新荣,刘智勇,毛宗源.高速公路匝道非线性反馈控制器的设计与仿真.计算机工程与应用,2005,41(20):111-113.
[38]贺敬凯,徐建闽.基于BP神经网络的入口匝道控制器的设计.华南理工大学学报,2002,30(7):24-27.
[39]陈德望,王飞跃,陈龙.基于模糊神经网络的城市高速公路入口匝道控制算法.交通运输工程学报,2003,3(2):100-105.
[40]王青,曲仕茹,史忠科.高速公路交通流密度控制器设计.西北工业大学学报,2001,19(3):451-455.
[41]梁新荣,刘智勇,徐建闽.高速公路多匝道协调控制系统设计与仿真.信息与控制,2005,34(3):308-311.
[42]J.X.Xu and Y.F.Xing.A learning approach for freeway traffic control.International Conference on Control and Automation,2005,887-892.
[43]A.Kotsialos and M.Papageorgiou.Nonlinear optimal control applied to coordinated ramp metering.IEEE Trans.on Control Systems Technology,2004,12(6):920-933.
[44]A.D.Febbraro,T.Parisini,S.Sacone.Neural approximations for feedback optimal control of freeway system.IEEE Trans.On Vehicular Technology,2001,50(1):302-313.
[45]Kachroo P,Krishen K.System dynamics and feedback control design formulations for real time ramp metering.Transactions of the SDPS,Journal of Integrated Desigh and Process Science,2000,4(1):37-54.
[46]Zhang H M,Ritchie S G,Jayakrishnan R.Coordinated traffic responsive ramp control via nonlinear state feedback.Transportation Research,2001,9C(9):337-352.
[47]Bogenberger K,Keller H,Vukanovic S.A neuro-fuzzy algorithm for coordinated traffic responsive ramp metering.Proceedings of the IEEE Intelligent TransportationSystems Conference,Oakland,USA,2001,94-99.
[48]梁新荣,刘智勇,徐建闽,毛宗源.高速公路多路段的模糊逻辑协调控制.华南理工大学学报,2005,33(9):35-40.
[49]Singh M G,Title A.Systems:decomposition,optimization and control.Pergamon press,oxford,England,1978.
[50]Papageorigiou M.Multiplayer control system design applied to freeway traffic.IEEE Transactions on Automatic Control,1984,29(6):482-490.
[51]刘智勇,吴今培,万百五.高速公路智能交通控制系统的建模及多层描述.公路交通科技,1998,15(1):39-44.
[52]撒元功,徐建闽.基于神经网络预测模型的高速公路递阶控制.暨南大学学报,2002,23(5):31-34.
[53]谭满春.基于多车道交通流动态离散模型的递阶优化控制问题与算法.控制理论与应用,2003,20(6):855-858.
[2]史忠科,黄辉先,曲仕茹等.交通控制系统导论.北京:科学出版社,2003.
[3]J.X.Xu and Y.F.Xing.A learning approach for freeway traffic control.International Conference on Control and Automation,2005,887-892.
[4]王殿海.交通流理论.北京:人民交通出版社,2002.
[5]Kinzer,J.P.Application of the theory of probability to problem of highway traffic.B.C.E.thesis,Politech.Inst.Brooklyn,1933.
[6]Adams,W.F.Road traffic considered as a random series.J.Inst.Civil Eng,1936,4:121-130.
[7]Greenshields,B.D.A study of traffic capacity.Proc.Highway Res.Board,1934,14:448-477.
[8]Lighthill M.J.Whitham G.B.On kinematic waves:Pt I Flow movement in long rivers;Ⅱ.A theory of traffic flow on long crouded road.Proc Roy Soc A,1955,229:281-316.
[9]王雷.一维交通流元胞自动机模型中自组织临界性及其相变行为的研究.中国科学技术大学博士学位论文,2004.
[10]Ho F,Ioannou P.Traffic flow modeling and control using artificial neural networks.IEEE Control System,1996,16-26.
[11]Shinya K,Partha C.Car-following model based on fuzzy inference system.TRB,1365.1992,99-111.
[12]张智勇,荣建,任福田.跟车模型研究综述.公路交通科技,2004,21(8):108-113.
[13]欧海涛,张文渊,杨煌普等.高速公路交通流的RBF神经网络建模.上海交通大学学报(自然科学版),2000,34(5):665-668.
[14]罗赞文,吴志坚,韩曾晋.RBF网络在交通流模型辨识中的应用.清华大学学报(自然科学版),2001,41(9):106-110.
[15]撒元功,胡郁葱,徐建闽.高速公路动态交通流的神经网络模型.华南理工大学学报(自然科学版),2002,30(8):91-94.
[16]肖健梅.RBF神经网络在高速公路交通流建模中的应用.第五届全球智能控制与自动化大会,2004,5208-5211.
[17]顾国庆等.交通系统的元胞自动机模型.系统工程理论方法应用,1995,4(1):12-17.
[18]梁新荣.高速公路智能控制方法研究.华南理工大学博士论文,2005.
[19]王亦兵,罗赞文,韩曾晋.城市高速公路交通中的控制问题.中国公路学报,1997,10(3):89-93.
[20]王亦兵,韩曾晋,贺国光.城市高速公路交通控制综述.自动化学报,1998,24(4):484-493.
[21]黄小原,樊治平,张文江.高速公路入口交通控制问题的研究.系统工程,1989,(11):36-41.
[22]Papageorigiou M.Kotsialos,A.Freeway ramp metering:an overview.Intelligent Transportation Systems.2000,Proceedings IEEE.Oct,2000:228-239.
[23]Kotsialos,A.,and Papageorgiou,M.The importance of traffic flow modeling for motorway traffic control.Networks and Spatial Economics,2001,76(1):179-203.
[24]罗赞文,吴志坚,韩曾晋.RBF网络在交通流模型辨识中的应用.清华大学学报(自然科学版),2001,41(9):106-110.
[25]欧海涛,张文渊,杨煜普等.高速公路交通流的RBF神经网络建模.上海交通大学学报(自然科学版),2000,34(5):665-668.
[26]撒元功,胡郁葱,徐建闽.高速公路动态交通流的神经网络模型.华南理工大学学报(自然科学版),2002,30(8):91-94.
[27]撒元功.高速公路交通流模型与控制方法研究.华南理工大学博士论文,2002.
[28]Xiao,J.M.Application of RBF neural network to freeway traffic flow modeling.Proceedings of the 5th World Congress on Intelligent Control and Automation,Hangzhou,China,2004,5208-5211.
[29]Abdalla,M.I.Digital tection techniques via Elman neural network.Journal of Engineering and Applied Science,2002,49(6):1197-1208.
[30]M.Papageorgiou.ALINEA:A local feedback control law for on-ramp metering.In Transportation Research Record 1320,1991.
[31]M.Papageorgiou.ALINEA local ramp metering:Summary of field results.In Transportation Research Record 1603,1997.
[32]梁新荣,刘智勇,毛宗源.高速公路非线性反馈模糊逻辑匝道控制器.控制理论与应用,2006,23(1):99-102.
[33]杜启亮,高向军,莫鸿强.人工免疫PI控制器在窑头温度控制中的应用.第六届全球智能控制与自动化大会论文集,2006,3533-3537.
[34]付冬梅,郑德玲,位耀光.人工免疫控制器的设计及其控制效果的仿真.北京科技大学学报,2004,26(4):442-445.
[35]刘金琨.先进PID控制MATLAB仿真(第2版),电子工业出版社,北京,2004.
[36]H.M.Zhang,S.G.Ritchie,R.Jayakrishnan.Coordinated traffic responsive ramp control via nonlinear state feedback.Transportation Research,Series C,2001,(9):337-352.
[37]梁新荣,刘智勇,毛宗源.高速公路匝道非线性反馈控制器的设计与仿真.计算机工程与应用,2005,41(20):111-113.
[38]贺敬凯,徐建闽.基于BP神经网络的入口匝道控制器的设计.华南理工大学学报,2002,30(7):24-27.
[39]陈德望,王飞跃,陈龙.基于模糊神经网络的城市高速公路入口匝道控制算法.交通运输工程学报,2003,3(2):100-105.
[40]王青,曲仕茹,史忠科.高速公路交通流密度控制器设计.西北工业大学学报,2001,19(3):451-455.
[41]梁新荣,刘智勇,徐建闽.高速公路多匝道协调控制系统设计与仿真.信息与控制,2005,34(3):308-311.
[42]J.X.Xu and Y.F.Xing.A learning approach for freeway traffic control.International Conference on Control and Automation,2005,887-892.
[43]A.Kotsialos and M.Papageorgiou.Nonlinear optimal control applied to coordinated ramp metering.IEEE Trans.on Control Systems Technology,2004,12(6):920-933.
[44]A.D.Febbraro,T.Parisini,S.Sacone.Neural approximations for feedback optimal control of freeway system.IEEE Trans.On Vehicular Technology,2001,50(1):302-313.
[45]Kachroo P,Krishen K.System dynamics and feedback control design formulations for real time ramp metering.Transactions of the SDPS,Journal of Integrated Desigh and Process Science,2000,4(1):37-54.
[46]Zhang H M,Ritchie S G,Jayakrishnan R.Coordinated traffic responsive ramp control via nonlinear state feedback.Transportation Research,2001,9C(9):337-352.
[47]Bogenberger K,Keller H,Vukanovic S.A neuro-fuzzy algorithm for coordinated traffic responsive ramp metering.Proceedings of the IEEE Intelligent TransportationSystems Conference,Oakland,USA,2001,94-99.
[48]梁新荣,刘智勇,徐建闽,毛宗源.高速公路多路段的模糊逻辑协调控制.华南理工大学学报,2005,33(9):35-40.
[49]Singh M G,Title A.Systems:decomposition,optimization and control.Pergamon press,oxford,England,1978.
[50]Papageorigiou M.Multiplayer control system design applied to freeway traffic.IEEE Transactions on Automatic Control,1984,29(6):482-490.
[51]刘智勇,吴今培,万百五.高速公路智能交通控制系统的建模及多层描述.公路交通科技,1998,15(1):39-44.
[52]撒元功,徐建闽.基于神经网络预测模型的高速公路递阶控制.暨南大学学报,2002,23(5):31-34.
[53]谭满春.基于多车道交通流动态离散模型的递阶优化控制问题与算法.控制理论与应用,2003,20(6):855-858.