物流智能调度系统交通流信息处理方法综合应用研究
|
摘要
随着国民经济的高速发展和城市化进程的加快,交通拥挤阻塞以及由此导致的交通事故的增加,智能运输和智能物流相继诞生,成为是当今交通运输行业发展的热点。智能调度系统是智能物流系统的核心研究部分,针对智能物流调度系统所涉及到的城市路网,要想实现对我国大中城市的密度越来越大路网的宏观管理,就必须获得路网的绝大多数(甚至是全部)节点的交通流信息。由于我国普遍采用在各个交叉口铺设监测器来获取交通流信息,而监测器的铺设率相对较低,导致很多无监测器路口的交通流的信息很难获取。
本文依托国家自然科学基金项目“基于路网信息的港口物流智能调度系统模型和关键技术研究”基础上应用经济统计学方法和SPSS13.0软件,利用有检测器交叉口与无检测器交叉口之间的这种相关关系,并根据连接交叉口的检测器的数量的多少,利用有检测器交叉口的交通流信息分情况来预测无检测器交叉口的交通流信息。
全文共分5章。第1章为前言,提出了本论文的研究背景和意义、研究现状和研究的基本思想及内容;第2章介绍了物流智能交通流信息的采集及常见处理方法。第3章着重介绍了聚类分析法、和逐步回归分析法。其中聚类分析法是数理统计中研究“物以类聚”的一种方法,它的职能是建立一种分类方法,它是将一批样品或变量,按照它们在性质上的亲疏程度进行分类。逐步回归分析方法是一种自动地从大量可供选则的变量中,选择对建立回归方程起重要作用的变量的统计方法。本文的第4章则针对本文所要研究的问题、采用了主成分分析法。主成分分析法是把多个指标化为少数几个综合指标的一种统计方法,即找出几个综合因子来代表原来众多的变量,使这些综合因子能尽可能地反映原来变量的信息量。而第5章是全文总结,概括了本论文的主要研究成果、不足和展望。
With the fast development of domestic economy and process of civilization, traffic jam and the increasing traffic accidents have inhibited the development of economy. Intelligent logistics dispatching system which is the core component of intelligent logistics is the best way to solve the transportation problems. With the progress of modern science and the development of traffic, in allusion to the problems that exist in route network, it's necessary to gain traffic flow information of most intersections to realize the management of route network. Usually the traffic flow information is known according to detectors of intersections, it's difficult to get the information from non-detector intersecton due to scarcity of detectors.
Due to the issues above, this paper is finished in combination with the project of National Science Foundation of China(NSFC)"Research on port logistics intelligent dispatching system model and key technology based on the information of route network". In this paper, traffic flow information is divided into the normal situation and the special situation. Based on SPSS 13.0 and statistics methods, it's possible to predict the traffic flow information of non-detector intersections according to the co-relationship between the intersections in different situations.
This paper consists of five chapters. In the first chapter, the background and purpose, current research, the basic idea and content of this paper are provided. In the second chapter, the method of obtaining and dealing with traffic flow information in logistics intelligent dispatching system is introduced. Chapter 3 introduce clustering analysis and stepwise regression. The clustering analysis method can amalgamate different kinds of variables into one kind based on the co-relationship between these different kinds of variables. The stepwise regression method is a statistic method that can select several important variables to construct the regression equation. Chapter 4 introduce main-components analysis method. In these methods, The method of main-component analysis is a statistic method that can convert a lot of quotas to few synthetical quotas and these quotas have less co-relationship. Chapter 5 is the summary. The main contribution of this paper is summarized. The shortcoming and expectation of this paper appear in this chapter.
本文依托国家自然科学基金项目“基于路网信息的港口物流智能调度系统模型和关键技术研究”基础上应用经济统计学方法和SPSS13.0软件,利用有检测器交叉口与无检测器交叉口之间的这种相关关系,并根据连接交叉口的检测器的数量的多少,利用有检测器交叉口的交通流信息分情况来预测无检测器交叉口的交通流信息。
全文共分5章。第1章为前言,提出了本论文的研究背景和意义、研究现状和研究的基本思想及内容;第2章介绍了物流智能交通流信息的采集及常见处理方法。第3章着重介绍了聚类分析法、和逐步回归分析法。其中聚类分析法是数理统计中研究“物以类聚”的一种方法,它的职能是建立一种分类方法,它是将一批样品或变量,按照它们在性质上的亲疏程度进行分类。逐步回归分析方法是一种自动地从大量可供选则的变量中,选择对建立回归方程起重要作用的变量的统计方法。本文的第4章则针对本文所要研究的问题、采用了主成分分析法。主成分分析法是把多个指标化为少数几个综合指标的一种统计方法,即找出几个综合因子来代表原来众多的变量,使这些综合因子能尽可能地反映原来变量的信息量。而第5章是全文总结,概括了本论文的主要研究成果、不足和展望。
With the fast development of domestic economy and process of civilization, traffic jam and the increasing traffic accidents have inhibited the development of economy. Intelligent logistics dispatching system which is the core component of intelligent logistics is the best way to solve the transportation problems. With the progress of modern science and the development of traffic, in allusion to the problems that exist in route network, it's necessary to gain traffic flow information of most intersections to realize the management of route network. Usually the traffic flow information is known according to detectors of intersections, it's difficult to get the information from non-detector intersecton due to scarcity of detectors.
Due to the issues above, this paper is finished in combination with the project of National Science Foundation of China(NSFC)"Research on port logistics intelligent dispatching system model and key technology based on the information of route network". In this paper, traffic flow information is divided into the normal situation and the special situation. Based on SPSS 13.0 and statistics methods, it's possible to predict the traffic flow information of non-detector intersections according to the co-relationship between the intersections in different situations.
This paper consists of five chapters. In the first chapter, the background and purpose, current research, the basic idea and content of this paper are provided. In the second chapter, the method of obtaining and dealing with traffic flow information in logistics intelligent dispatching system is introduced. Chapter 3 introduce clustering analysis and stepwise regression. The clustering analysis method can amalgamate different kinds of variables into one kind based on the co-relationship between these different kinds of variables. The stepwise regression method is a statistic method that can select several important variables to construct the regression equation. Chapter 4 introduce main-components analysis method. In these methods, The method of main-component analysis is a statistic method that can convert a lot of quotas to few synthetical quotas and these quotas have less co-relationship. Chapter 5 is the summary. The main contribution of this paper is summarized. The shortcoming and expectation of this paper appear in this chapter.
引文
[1]杨兆升主编.智能运输系统概论.人民交通出版社,2003.
[2]李志鹏.交通流建模及城市路网交通状态分析.上海交通大学博士论文,2007.
[3]陆化普编著.智能运输系统.北京:人民交通出版社,2002.
[4]杨兆升.论智能运输系统.中国公路学报,1995,4(8):30-34.
[5]丁江宁.加快建设我国环渤海地区智能交通系统的必要性.交通运输,2007,12:50-52.
[6]张赫.基于路网信息的港口物流智能调度系统模型和关键技术研究.国家自然基金申请书,2006.
[7]赵立权.智能物流及其支撑技术.情报杂志2005,12:49-53.
[8]张赫,杨兆升,李贻武.无检测器交叉口交通流量预测方法综合研究.公路交通科技,2002.2(19),93-97.
[9]李军,郭耀煌.物流配送车辆优化调度M.北京:中国物资出版社,2002.
[10]张赫,杨兆升,王炜.基于实时交通流信息的中心式动态路径诱导系统行车路线优化技术研究.公路交通科技,2004.
[11]唐丽娜,张卫华.短时交通流预测方法比较.交通科技与经济,2008.
[12]谷远利.交通流诱导系统中的实时动态交通流预测研究.吉林工业大学硕士毕业论文,1999.
[13]邓志龙,李全,陈茜.基于灰色系统理论的短时交通流预测.公里交通技术,2006.2(1).
[14]周小鹏,冯奇,孙立军.基于最近邻法的短时交通流预测.同济大学学报(自然科学版)2006,11(34).
[15]朱顺应,王红,李光寿.道段上短时间区段内交通量预测ARIMA模型.2003,1.
[16]高慧,赵建玉,贾磊.短时交通流预测方法综述.济南大学学报(自然科学版),2008,22(1).
[17]王雷,许晗,郑山水.ITS中交通流预测方法的研究.中国科技信息,2008.
[18]雷胜.城市交通流量智能组合预测方法研究.西华大学学报(自然科学版),2006,2(25).
[19]张毅,罗元.基于人工神经网络城市交通流量智能预测的研究.重庆邮电学院,2005.
[20]杨胜,李莉,胡福乔,施鹏飞.基于决策树的城市短时交通流预测.计算机工程2005,8(31).
[21]王晓原,刘海红.基于投影寻踪自回归的短时交通流预测.系统工程,2006,3(24).
[22]王进,史其.基于非线性理论的短期交通流预测研究.西安建筑科技大学学报(自然科学 版),2006,38(2).
[23]杨兆升,朱中.交通流诱导的信息系统研究.公路交通科技,1999.
[24]杨兆升.城市交通流诱导系统理论与模型.人民交通出版社,2000.
[25]吉林大学智能运输系统研究与开发中心.城市交通流诱导系统理论模型和方法研究论文汇编,2001.
[26]杨兆升,姜桂艳.城市交通流诱导系统结构框架研究.公路交通科技,1997,14(3):6-10.
[27]Nancy Lnihan,Kjello Holmesland.Use of the Box and Jenkins Time Series Technique in Traffic Forecasting[J].Transportation,1988:125-143.
[28]杨兆升,朱中.基于卡尔曼滤波理论的交通流量实时预测模型.中国公路学报,1999,12(3).
[29]刘静,关伟.交通流预测方法综述[J].公路交通科技,2004:82-85.
[30]Wang Yisheng,Wang Feng,Jiang Dali.A study of identifying the core competences for virtual logistics organization based on fuzzy clustering algorithm[J].Man and Cybernetics,2003,5(3):235-238.
[31]徐启华,丁兆奎,毕训银.一种基于动态递归神经网络的交通流量实时预测方法.淮海工学院学报,2003,12(4).
[32]王宏杰,林良明,徐大淦等.基于改进BP网交通流动态时序预测算法的研究[J].交通与计算机,2001.
[33]Smith Brian L,Michael J.Demetsky Short-term Traffic Flow Prediction:Neural Network Approach.Transportation Research Record 1453:98-104.
[34]史其信,郑为中.道路网短期交通流预测方法比较.交通运输工程学报.2004,4(4).
[35]贺国强,李宇,马寿峰.基于数学模型的短时交通流量预测方法探讨[J].系统工程理论与实践,2000,12:51-561.
[36]许玮珑,马林才,王巍.BP神经网络在交通流量预测中的应用.交通标准化.2005,11.
[37]罗积玉,邢瑛.经济统计分析方法及预测.清华大学出版社,1987.
[38]He Zhang,Wei Wang,Huai Zhonggu.Application of Cluster Analysis and Stepwise Regression in Predicting the Traffic Volume of Lanes.Journal of Southeast University(English Edition),2005:359-362.
[39]Michael Kyte.Capacity Analysis of Unsignalized Intersections.Transportation Research Part A 33(1999):157-160.
[40]张文波,陈红艳.实用数据统计分析及SPSS12.0应用.人民邮电出版社,2006.
[41]张赫,杨兆升.逐步回归分析法在无检测器交叉口交通流量预测中的应用.吉林大学学报.(工学版,学术榜),2002,12(108):16-19.
[42]Yang Zhaosheng,Zhang He,Damachi B.B.U.Research on the Method Used in Predicting the Traffic Volume of Non-detector Intersections,9~(th) ITS 2000.U.S.A.
[2]李志鹏.交通流建模及城市路网交通状态分析.上海交通大学博士论文,2007.
[3]陆化普编著.智能运输系统.北京:人民交通出版社,2002.
[4]杨兆升.论智能运输系统.中国公路学报,1995,4(8):30-34.
[5]丁江宁.加快建设我国环渤海地区智能交通系统的必要性.交通运输,2007,12:50-52.
[6]张赫.基于路网信息的港口物流智能调度系统模型和关键技术研究.国家自然基金申请书,2006.
[7]赵立权.智能物流及其支撑技术.情报杂志2005,12:49-53.
[8]张赫,杨兆升,李贻武.无检测器交叉口交通流量预测方法综合研究.公路交通科技,2002.2(19),93-97.
[9]李军,郭耀煌.物流配送车辆优化调度M.北京:中国物资出版社,2002.
[10]张赫,杨兆升,王炜.基于实时交通流信息的中心式动态路径诱导系统行车路线优化技术研究.公路交通科技,2004.
[11]唐丽娜,张卫华.短时交通流预测方法比较.交通科技与经济,2008.
[12]谷远利.交通流诱导系统中的实时动态交通流预测研究.吉林工业大学硕士毕业论文,1999.
[13]邓志龙,李全,陈茜.基于灰色系统理论的短时交通流预测.公里交通技术,2006.2(1).
[14]周小鹏,冯奇,孙立军.基于最近邻法的短时交通流预测.同济大学学报(自然科学版)2006,11(34).
[15]朱顺应,王红,李光寿.道段上短时间区段内交通量预测ARIMA模型.2003,1.
[16]高慧,赵建玉,贾磊.短时交通流预测方法综述.济南大学学报(自然科学版),2008,22(1).
[17]王雷,许晗,郑山水.ITS中交通流预测方法的研究.中国科技信息,2008.
[18]雷胜.城市交通流量智能组合预测方法研究.西华大学学报(自然科学版),2006,2(25).
[19]张毅,罗元.基于人工神经网络城市交通流量智能预测的研究.重庆邮电学院,2005.
[20]杨胜,李莉,胡福乔,施鹏飞.基于决策树的城市短时交通流预测.计算机工程2005,8(31).
[21]王晓原,刘海红.基于投影寻踪自回归的短时交通流预测.系统工程,2006,3(24).
[22]王进,史其.基于非线性理论的短期交通流预测研究.西安建筑科技大学学报(自然科学 版),2006,38(2).
[23]杨兆升,朱中.交通流诱导的信息系统研究.公路交通科技,1999.
[24]杨兆升.城市交通流诱导系统理论与模型.人民交通出版社,2000.
[25]吉林大学智能运输系统研究与开发中心.城市交通流诱导系统理论模型和方法研究论文汇编,2001.
[26]杨兆升,姜桂艳.城市交通流诱导系统结构框架研究.公路交通科技,1997,14(3):6-10.
[27]Nancy Lnihan,Kjello Holmesland.Use of the Box and Jenkins Time Series Technique in Traffic Forecasting[J].Transportation,1988:125-143.
[28]杨兆升,朱中.基于卡尔曼滤波理论的交通流量实时预测模型.中国公路学报,1999,12(3).
[29]刘静,关伟.交通流预测方法综述[J].公路交通科技,2004:82-85.
[30]Wang Yisheng,Wang Feng,Jiang Dali.A study of identifying the core competences for virtual logistics organization based on fuzzy clustering algorithm[J].Man and Cybernetics,2003,5(3):235-238.
[31]徐启华,丁兆奎,毕训银.一种基于动态递归神经网络的交通流量实时预测方法.淮海工学院学报,2003,12(4).
[32]王宏杰,林良明,徐大淦等.基于改进BP网交通流动态时序预测算法的研究[J].交通与计算机,2001.
[33]Smith Brian L,Michael J.Demetsky Short-term Traffic Flow Prediction:Neural Network Approach.Transportation Research Record 1453:98-104.
[34]史其信,郑为中.道路网短期交通流预测方法比较.交通运输工程学报.2004,4(4).
[35]贺国强,李宇,马寿峰.基于数学模型的短时交通流量预测方法探讨[J].系统工程理论与实践,2000,12:51-561.
[36]许玮珑,马林才,王巍.BP神经网络在交通流量预测中的应用.交通标准化.2005,11.
[37]罗积玉,邢瑛.经济统计分析方法及预测.清华大学出版社,1987.
[38]He Zhang,Wei Wang,Huai Zhonggu.Application of Cluster Analysis and Stepwise Regression in Predicting the Traffic Volume of Lanes.Journal of Southeast University(English Edition),2005:359-362.
[39]Michael Kyte.Capacity Analysis of Unsignalized Intersections.Transportation Research Part A 33(1999):157-160.
[40]张文波,陈红艳.实用数据统计分析及SPSS12.0应用.人民邮电出版社,2006.
[41]张赫,杨兆升.逐步回归分析法在无检测器交叉口交通流量预测中的应用.吉林大学学报.(工学版,学术榜),2002,12(108):16-19.
[42]Yang Zhaosheng,Zhang He,Damachi B.B.U.Research on the Method Used in Predicting the Traffic Volume of Non-detector Intersections,9~(th) ITS 2000.U.S.A.