【摘要】：高速公路收費(fèi)數(shù)據(jù)作為高速公路聯(lián)網(wǎng)收費(fèi)管理系統(tǒng)的最直接產(chǎn)物,具有字段豐富、內(nèi)容充實(shí)、數(shù)據(jù)量大、更新及時(shí)等特點(diǎn)。對(duì)收費(fèi)數(shù)據(jù)進(jìn)行深入分析及挖掘,能夠得到許多隱藏在基礎(chǔ)數(shù)據(jù)下的信息。本文基于高速公路收費(fèi)流水?dāng)?shù)據(jù)的特征分析,從算法優(yōu)化、模型建立、實(shí)例分析、應(yīng)用對(duì)比等方面,對(duì)高速公路車輛旅行路徑、斷面車流量以及路段旅行時(shí)間進(jìn)行預(yù)測(cè)研究,一方面改善出行者的出行選擇,另一方面也能提高高速公路管理部門的管理水平。針對(duì)國(guó)內(nèi)外相關(guān)預(yù)測(cè)研究中只注重單一方面,而缺乏完善且系統(tǒng)的綜合預(yù)測(cè)挖掘研究的現(xiàn)狀,本文主要完成了以下工作:首先,提出一種高速公路原始收費(fèi)數(shù)據(jù)的預(yù)處理方法。針對(duì)收費(fèi)數(shù)據(jù)中較大比例的異常數(shù)據(jù),為最大程度減少異常數(shù)據(jù)的干擾,提出將異常數(shù)據(jù)分為冗余數(shù)據(jù)、缺失數(shù)據(jù)以及噪聲數(shù)據(jù)這3類數(shù)據(jù),分別進(jìn)行處理方法說(shuō)明,并通過(guò)實(shí)例對(duì)比,驗(yàn)證該處理方法的可行性。其次,基于馬爾可夫預(yù)測(cè)法建立車輛旅行路徑預(yù)測(cè)模型。分車型進(jìn)行模型的建立以提高預(yù)測(cè)精度。針對(duì)預(yù)測(cè)法中狀態(tài)轉(zhuǎn)移概率矩陣的求解,選取統(tǒng)計(jì)法及線性方程組法分別進(jìn)行求解并對(duì)比分析,采用實(shí)例進(jìn)行驗(yàn)證,結(jié)果表明:統(tǒng)計(jì)法更適合于收費(fèi)數(shù)據(jù)的預(yù)測(cè)特征。再次,在路徑預(yù)測(cè)的基礎(chǔ)上,針對(duì)高速公路路段交通狀態(tài)的預(yù)測(cè)進(jìn)行研究。選取路段斷面車流量及車輛旅行時(shí)間作為路段交通狀態(tài)的預(yù)測(cè)指標(biāo)。提出一種基于收費(fèi)數(shù)據(jù)的斷面車流量統(tǒng)計(jì)法,以此為數(shù)據(jù)基礎(chǔ)進(jìn)行車流量預(yù)測(cè)。實(shí)例分析表明:基于自適應(yīng)卡爾曼濾波算法的斷面車流量預(yù)測(cè),能避免卡爾曼濾波算法的缺陷,并提高預(yù)測(cè)精度。然后,論證路段旅行時(shí)間與斷面車流量的相關(guān)性,提出基于密度的路段旅行時(shí)間估計(jì)方法并進(jìn)行算法修正,通過(guò)MATLAB實(shí)例分析,驗(yàn)證該算法的可行性及準(zhǔn)確性。最后,基于以上預(yù)測(cè)研究成果,提出高速公路收費(fèi)數(shù)據(jù)的預(yù)測(cè)應(yīng)用場(chǎng)景。分實(shí)時(shí)與非實(shí)時(shí)預(yù)測(cè)進(jìn)行對(duì)比分析,并分別針對(duì)工作日、周末及節(jié)假日的不同交通特性進(jìn)行交通預(yù)測(cè),研究結(jié)果可得若干結(jié)論,用于相關(guān)領(lǐng)域的研究。
[Abstract]:As the most direct product of expressway network toll management system, expressway toll collection data has the characteristics of rich fields, substantial content, large amount of data, timely updating, and so on. A lot of information hidden under the basic data can be obtained by analyzing and mining the charging data in depth. In this paper, based on the characteristic analysis of expressway toll flow data, from the aspects of algorithm optimization, model establishment, case analysis and application comparison, the prediction of expressway vehicle travel path, cross-section traffic flow and section travel time are studied. On the one hand, it can improve the traveler's travel choice, on the other hand, it can also improve the management level of highway management department. In view of the fact that the related prediction research at home and abroad only pays attention to a single aspect, but lacks the perfect and systematic comprehensive prediction mining research, this paper mainly completes the following work: first, a preprocessing method of the original toll data of expressway is proposed. Aiming at the large proportion of abnormal data in charge data, in order to minimize the interference of abnormal data, the paper puts forward that the abnormal data can be divided into redundant data, missing data and noise data. The feasibility of the method is verified by an example. Secondly, the vehicle travel path prediction model is established based on Markov prediction method. The models are built to improve the prediction accuracy. In order to solve the state transition probability matrix in the forecasting method, the statistical method and the linear equation group method are selected to solve and analyze respectively. The results show that the statistical method is more suitable for the forecasting characteristics of the charging data. Thirdly, on the basis of path prediction, the traffic state prediction of expressway section is studied. The section traffic flow and vehicle travel time are selected as the predictors of road traffic state. A cross-section traffic flow statistic method based on toll data is proposed to predict the traffic flow on the basis of the data. The analysis of examples shows that the prediction of cross-section traffic flow based on adaptive Kalman filter algorithm can avoid the defects of Kalman filter algorithm and improve the prediction accuracy. Then, the correlation between section travel time and cross-section traffic flow is demonstrated, and a density-based road travel time estimation method is proposed, and the algorithm is modified. The feasibility and accuracy of the algorithm are verified by an MATLAB example. Finally, based on the above research results, the forecast application scenario of highway toll data is put forward. The traffic prediction is carried out according to the different traffic characteristics of weekdays weekends and holidays. Some conclusions can be drawn and used in the research of related fields.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：U495

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 趙建東;徐菲菲;張琨;白繼根;;融合多源數(shù)據(jù)預(yù)測(cè)高速公路站間旅行時(shí)間[J];交通運(yùn)輸系統(tǒng)工程與信息;2016年01期

2 肖潤(rùn)謀;李彬;陳蔭三;;基于大數(shù)據(jù)的高速公路運(yùn)輸趨勢(shì)分析[J];交通運(yùn)輸工程學(xué)報(bào);2015年05期

3 符方睿;羅方;;廣東省高速公路ETC/MTC混合車道實(shí)施方案[J];中國(guó)交通信息化;2015年04期

4 李卉;申孟宜;展國(guó)殿;;大數(shù)據(jù)在我國(guó)高速公路超限問(wèn)題研究中的應(yīng)用初探[J];統(tǒng)計(jì)研究;2014年10期

5 薛文婷;張波;李署堅(jiān);;組合導(dǎo)航中一種新息自適應(yīng)卡爾曼濾波算法[J];全球定位系統(tǒng);2014年04期

6 宋子房;;公路短時(shí)車流量預(yù)測(cè)模型研究[J];科學(xué)決策;2014年04期

7 李慧兵;楊曉光;;面向行程時(shí)間預(yù)測(cè)準(zhǔn)確度評(píng)價(jià)的數(shù)據(jù)融合方法[J];同濟(jì)大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年01期

8 蔣亞平;郭俊亮;;基于馬爾柯夫過(guò)程的交叉路口車流量預(yù)測(cè)模型研究[J];鄭州輕工業(yè)學(xué)院學(xué)報(bào)(自然科學(xué)版);2012年06期

9 沈強(qiáng);;基于高速公路收費(fèi)數(shù)據(jù)的路網(wǎng)運(yùn)行狀態(tài)評(píng)價(jià)[J];公路交通科技;2012年08期

10 劉擁華;孫靜怡;何民;賈利民;莊文君;;高速公路貨物運(yùn)輸量統(tǒng)計(jì)方法[J];公路交通科技;2012年04期

相關(guān)碩士學(xué)位論文 前7條

1 周悅;基于預(yù)測(cè)控制的道路交通生態(tài)控制方法研究[D];浙江工業(yè)大學(xué);2015年

2 孫會(huì);基于壓縮感知理論的重建算法研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2014年

3 楊春霞;海峽西岸經(jīng)濟(jì)區(qū)高速公路貨物運(yùn)輸發(fā)展研究[D];長(zhǎng)安大學(xué);2014年

4 王浩;基于收費(fèi)數(shù)據(jù)的高速公路旅行時(shí)間自適應(yīng)插值卡爾曼濾波預(yù)測(cè)研究[D];北京交通大學(xué);2014年

5 李敏;基于高速公路聯(lián)網(wǎng)收費(fèi)數(shù)據(jù)的路徑交通量求解方法研究[D];華南理工大學(xué);2012年

6 王延鈞;治理超限超載運(yùn)輸存在的問(wèn)題及其主要對(duì)策[D];吉林大學(xué);2011年

7 常濤;改進(jìn)型MapReduce框架的研究與設(shè)計(jì)[D];北京郵電大學(xué);2011年

，

本文編號(hào)：2301156