基于神经网络的城市群客运交通需求预测研究
|
摘要
城市群的形成和发展已成为全球范围内的典型社会经济现象,这种趋势带来了城市群内人口的增长和区域范围的大幅膨胀,带来的是城市及区域之间的人员流动和交通联系愈加频繁,城市群内的完善而合理的交通网络是城市群健康快速发展的物质基础,因此有必要进行针对性的城市群交通规划,确定城市群交通的发展方向和网络的合理规模。作为规划的主要组成部分,交通需求预测是确定交通网络规模的重要技术手段。根据城市群客流具有的特殊性,找出相对应的客流模型是有其现实意义的。
本文分析了城市群问题的研究现状,在此基础上,首先,对城市群的定义和形成做出了归纳,描述了空间分布形式,叙述了城市群客流产生机理,在此基础上,描述和总结了城市群客运需求的特点,并归纳出影响城市群客运交通需求的主要因素。
在城市群城际客运交通生成预测,列举了常规的时间序列法、回归分析法及弹性系数法,以及对这三种方法进行组合的预测方法,并指出了它们存在的不足。在此基础上,提出了根据神经网络,利用各种相关因素的预测方法。
最后,论文运用交通组合模型将交通方式划分与交通分布两阶段进行组合,简化了四阶段法的预测流程,提高预测精度,并将此模型仿照传统的双约束重力模型进行改进,在引入调整系数,进一步提高结果的准确性。
The formation and development of urban agglomeration has become a global typical socio-economic phenomenon,this trend brought population growth and substantial expansion of the regional scope within it, directly result the traffic contact between urban and regional become more frequent, reasonable transportation network is the material basis of healthy and rapid development of urban agglomeration, it is necessary to make targeted urban transportation planning, determine the direction of development and the reasonable scale of traffic network. As a major component, transportation demand forecasting is a important technique to determine it. Combined with the characteristics of urban agglomeration, a reasonable model for traffic demand forecasting is very important.
With analysis and summary of existing studies, built traffic demand forecasting model according to characteristics of urban agglomeration. Firstly, elaborate the definition, the formation and spatial distribution patterns, describe the passenger mechanism of urban agglomeration. On this basis, describes and summarizes the characteristics of demand for urban transport demand, summed up the major factors impact the transport demand.
In the urban agglomeration passenger trip generation forecast,listing the time series method,regression analysis and elasticity coefficient method,and the combined model of them. And pointed out their shortcomings. On this basis, proposed a model using a variety of related factors based on neural network.
Finally,suggest a combine model of traffic distribution and mode split,simplified four-stage method of forecasting process, improve the accuracy, and modeled after the traditional double-constrained gravity model to improved, the introduction of the adjustment factor further improve the accuracy of the results.
本文分析了城市群问题的研究现状,在此基础上,首先,对城市群的定义和形成做出了归纳,描述了空间分布形式,叙述了城市群客流产生机理,在此基础上,描述和总结了城市群客运需求的特点,并归纳出影响城市群客运交通需求的主要因素。
在城市群城际客运交通生成预测,列举了常规的时间序列法、回归分析法及弹性系数法,以及对这三种方法进行组合的预测方法,并指出了它们存在的不足。在此基础上,提出了根据神经网络,利用各种相关因素的预测方法。
最后,论文运用交通组合模型将交通方式划分与交通分布两阶段进行组合,简化了四阶段法的预测流程,提高预测精度,并将此模型仿照传统的双约束重力模型进行改进,在引入调整系数,进一步提高结果的准确性。
The formation and development of urban agglomeration has become a global typical socio-economic phenomenon,this trend brought population growth and substantial expansion of the regional scope within it, directly result the traffic contact between urban and regional become more frequent, reasonable transportation network is the material basis of healthy and rapid development of urban agglomeration, it is necessary to make targeted urban transportation planning, determine the direction of development and the reasonable scale of traffic network. As a major component, transportation demand forecasting is a important technique to determine it. Combined with the characteristics of urban agglomeration, a reasonable model for traffic demand forecasting is very important.
With analysis and summary of existing studies, built traffic demand forecasting model according to characteristics of urban agglomeration. Firstly, elaborate the definition, the formation and spatial distribution patterns, describe the passenger mechanism of urban agglomeration. On this basis, describes and summarizes the characteristics of demand for urban transport demand, summed up the major factors impact the transport demand.
In the urban agglomeration passenger trip generation forecast,listing the time series method,regression analysis and elasticity coefficient method,and the combined model of them. And pointed out their shortcomings. On this basis, proposed a model using a variety of related factors based on neural network.
Finally,suggest a combine model of traffic distribution and mode split,simplified four-stage method of forecasting process, improve the accuracy, and modeled after the traditional double-constrained gravity model to improved, the introduction of the adjustment factor further improve the accuracy of the results.
引文
[1] Hall P.The World Cities Morison&Gibb Ltd.U.K,1997
[2] Enjian YAO,Takayuki MORIKAWA.A Study on Integrated Intercity Travel Demand Model.10th International Conference on Travel Behaviour Research,Lucerne,2003:1-25
[3]李志,许传忠.日本城市交通现代化与城市发展的关系.国外城市规划:2003,18(2):50-51
[4] Thomas F.Golob.A simultaneous model of house hold actlilvlilty participation and trip chain generation.Transportation Research Part B,2000:34
[5]吕从高.城际客运专线客运量预测理论与方法研究[硕士学位论文].成都:西南交通大学,2008
[6] H Murat Celik.Modeling freight distribution using artificial neural networks. Journal of Transport Geography,2004,12:141–148
[7] Giulio Erberto Cantarella,Stefano de Luca.Multilayer feedforward networks for transportation mode choice analysis:An analysis and a comparison with random utility models.Transportation Research Part C,2005,13:121–155
[8] Hilmi Berk Celikoglua,Hikmet Kerem Cigizoglu.Modelling public transport trips by radial basis function neural networks.Mathematical and Computer Modelling, 2007,45:480–489
[9] Hilmi Berk Celikoglu,Hikmet Kerem Cigizoglu.Public transportation trip flow modeling with generalized regression neural networks.Advances in Engineering Software,2007,38:71–79
[10]王建伟,姜丽丽.都市圈及都市带的客流特性及发展趋势.长安大学学报(社会科学版),2004,6(2):39-43
[11]康学东,王长钊.关于建设环渤海京津冀地区城际铁路网的探讨.铁道建筑,2005,(2):89-91
[12]徐正和.长江三角洲区域轨道交通的探讨.现代城市轨道交通. 2004,(4):1-4
[13] YAO Liya,GUAN Hongzhi,YAN Hai.Trip Generation Model Based on Destination Attractiveness.TSINGHUA SCIENCE AND TECHNOLOGY,2008,5(13):632-635
[14]陆化普,王建伟.城际快速轨道交通客流预测方法研究.土木工程学报,2003,(7):41-45
[15]王树盛.都市圈轨道交通客流预测方法研究.城市轨道交通客流预测方法研究.2004(1):40-43
[16]王树盛.都市圈轨道交通客流预测理论及方法研究[硕士学位论文].南京:东南大学,2004
[17]毛敏.广州至珠海城际快速轨道交通客流预测.西南交通大学学报.2004,(4):39-42
[18]朱照宏、杨东援、吴兵.城市群交通规划.上海.同济大学出版社,2007.84-87
[19]冯垒.城市群理论与都市圈理论比较.理论探索,2006,(3):96-98
[20]刘有军.城市群一体化交通网络设计方法研究.2009年华中科技大学自主创新基金
[21]年富华等.试论城市群区域内的网络化组织地理科学.地理科学,2002,(5):568-571
[22]袁婧.城市群城际公路客运交通生成与分布预测研究[硕士学位论文].成都:西南交通大学,2007
[23]刘帅.基于非集计模型的都市圈客流交通方式划分应用研究[硕士学位论文] .重庆交通,2008
[24]高麒.我国发展区域城际快速铁路的相关问题研究[硕士学位论文].成都:西南交通大学,2006
[25]汪恒.武汉城市圈道路客运需求研究[硕士学位论文].武汉:武汉理工大学,2006
[26]郑璐.公路客运与城际铁路协同发展研究[硕士学位论文].吉林:吉林大学.2008
[27]邵春福.交通规划原理.北京:中国铁道出版社,2004.112-144
[28]陆化普.交通规划理论与方法.北京.清华大学出版社,2006.80-90
[29]王银华.区域公路网发展规模的预测与优化方法研究[硕士学位论文].北京:北京交通大学,2008
[30] Sheffi Y.Urban transportation networks equilibrium analysis with mathematical programming methods.New Jersey:Prentice2Hall,1989.165-180
[31]邓卫.新型交通组合需求预测方法的研究.东南大学学报,1997,5:42-45
[32] M Vrtic,P Frohlich,N Schussler.Two-dimensionally constrained disaggregate trip generation,distribution and mode choice model:Theory and application for a Swiss national model.Transportation Research Part A,2007,41
[33] Mark Dougherty.A review of neural networks applied to transport.Transportation Research C,1995,3(4):247-260
[34]焦李成.神经网络系统理论.西安:西安电子科技大学出版社,1995
[35] FiSter B.Neural network forecastion of short,noisy time series.TIMS/ORSA Nations Meeting,1991.
[36] Nussbaum M.Fundamentals of Artificial Neural Networks.Journal of Biomechanics,1994,29(10)
[37]阎平凡.对多层前向神经网络研究的进一步看法.电子学报,1999,5:82-85
[38]陆化普,周钱,徐薇.交通出行预测的神经网络模型.交通运输工程与信息学报,2008,6(2):6-11
[39]王海强,马国忠,刘开元.基于重要度的城际轨道交通空间出行分布预测的研究.交通标准化,2004,9:94-95
[40]田志立,周海涛.交通分布修正引力模型的应用.公路交通科技,1996(1):48-53
[41]凡蓉荣.武汉城市圈经济一体化发展[硕士学位论文].上海:华东师范大学,2006
[42]武汉市人民政府课题组:“武汉城市经济圈建设问题研究报告”.《长江论坛》2003(4)
[43]武汉经济圈资源要素的互动研究课题组:“武汉经济圈资源要素的互动研究”.《长江论坛》2005(4)
[2] Enjian YAO,Takayuki MORIKAWA.A Study on Integrated Intercity Travel Demand Model.10th International Conference on Travel Behaviour Research,Lucerne,2003:1-25
[3]李志,许传忠.日本城市交通现代化与城市发展的关系.国外城市规划:2003,18(2):50-51
[4] Thomas F.Golob.A simultaneous model of house hold actlilvlilty participation and trip chain generation.Transportation Research Part B,2000:34
[5]吕从高.城际客运专线客运量预测理论与方法研究[硕士学位论文].成都:西南交通大学,2008
[6] H Murat Celik.Modeling freight distribution using artificial neural networks. Journal of Transport Geography,2004,12:141–148
[7] Giulio Erberto Cantarella,Stefano de Luca.Multilayer feedforward networks for transportation mode choice analysis:An analysis and a comparison with random utility models.Transportation Research Part C,2005,13:121–155
[8] Hilmi Berk Celikoglua,Hikmet Kerem Cigizoglu.Modelling public transport trips by radial basis function neural networks.Mathematical and Computer Modelling, 2007,45:480–489
[9] Hilmi Berk Celikoglu,Hikmet Kerem Cigizoglu.Public transportation trip flow modeling with generalized regression neural networks.Advances in Engineering Software,2007,38:71–79
[10]王建伟,姜丽丽.都市圈及都市带的客流特性及发展趋势.长安大学学报(社会科学版),2004,6(2):39-43
[11]康学东,王长钊.关于建设环渤海京津冀地区城际铁路网的探讨.铁道建筑,2005,(2):89-91
[12]徐正和.长江三角洲区域轨道交通的探讨.现代城市轨道交通. 2004,(4):1-4
[13] YAO Liya,GUAN Hongzhi,YAN Hai.Trip Generation Model Based on Destination Attractiveness.TSINGHUA SCIENCE AND TECHNOLOGY,2008,5(13):632-635
[14]陆化普,王建伟.城际快速轨道交通客流预测方法研究.土木工程学报,2003,(7):41-45
[15]王树盛.都市圈轨道交通客流预测方法研究.城市轨道交通客流预测方法研究.2004(1):40-43
[16]王树盛.都市圈轨道交通客流预测理论及方法研究[硕士学位论文].南京:东南大学,2004
[17]毛敏.广州至珠海城际快速轨道交通客流预测.西南交通大学学报.2004,(4):39-42
[18]朱照宏、杨东援、吴兵.城市群交通规划.上海.同济大学出版社,2007.84-87
[19]冯垒.城市群理论与都市圈理论比较.理论探索,2006,(3):96-98
[20]刘有军.城市群一体化交通网络设计方法研究.2009年华中科技大学自主创新基金
[21]年富华等.试论城市群区域内的网络化组织地理科学.地理科学,2002,(5):568-571
[22]袁婧.城市群城际公路客运交通生成与分布预测研究[硕士学位论文].成都:西南交通大学,2007
[23]刘帅.基于非集计模型的都市圈客流交通方式划分应用研究[硕士学位论文] .重庆交通,2008
[24]高麒.我国发展区域城际快速铁路的相关问题研究[硕士学位论文].成都:西南交通大学,2006
[25]汪恒.武汉城市圈道路客运需求研究[硕士学位论文].武汉:武汉理工大学,2006
[26]郑璐.公路客运与城际铁路协同发展研究[硕士学位论文].吉林:吉林大学.2008
[27]邵春福.交通规划原理.北京:中国铁道出版社,2004.112-144
[28]陆化普.交通规划理论与方法.北京.清华大学出版社,2006.80-90
[29]王银华.区域公路网发展规模的预测与优化方法研究[硕士学位论文].北京:北京交通大学,2008
[30] Sheffi Y.Urban transportation networks equilibrium analysis with mathematical programming methods.New Jersey:Prentice2Hall,1989.165-180
[31]邓卫.新型交通组合需求预测方法的研究.东南大学学报,1997,5:42-45
[32] M Vrtic,P Frohlich,N Schussler.Two-dimensionally constrained disaggregate trip generation,distribution and mode choice model:Theory and application for a Swiss national model.Transportation Research Part A,2007,41
[33] Mark Dougherty.A review of neural networks applied to transport.Transportation Research C,1995,3(4):247-260
[34]焦李成.神经网络系统理论.西安:西安电子科技大学出版社,1995
[35] FiSter B.Neural network forecastion of short,noisy time series.TIMS/ORSA Nations Meeting,1991.
[36] Nussbaum M.Fundamentals of Artificial Neural Networks.Journal of Biomechanics,1994,29(10)
[37]阎平凡.对多层前向神经网络研究的进一步看法.电子学报,1999,5:82-85
[38]陆化普,周钱,徐薇.交通出行预测的神经网络模型.交通运输工程与信息学报,2008,6(2):6-11
[39]王海强,马国忠,刘开元.基于重要度的城际轨道交通空间出行分布预测的研究.交通标准化,2004,9:94-95
[40]田志立,周海涛.交通分布修正引力模型的应用.公路交通科技,1996(1):48-53
[41]凡蓉荣.武汉城市圈经济一体化发展[硕士学位论文].上海:华东师范大学,2006
[42]武汉市人民政府课题组:“武汉城市经济圈建设问题研究报告”.《长江论坛》2003(4)
[43]武汉经济圈资源要素的互动研究课题组:“武汉经济圈资源要素的互动研究”.《长江论坛》2005(4)
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |