【摘要】：隨著社會經(jīng)濟(jì)的發(fā)展,科學(xué)技術(shù)的進(jìn)步,人們交通出行的需求也不斷上升,機(jī)動車的數(shù)量更是與日俱增。機(jī)動車數(shù)量的高速增長引發(fā)交通擁堵、道路安全、環(huán)境污染、能源消耗等一系列問題日益嚴(yán)峻。大量實(shí)踐經(jīng)驗(yàn)表明,智能交通系統(tǒng)是改善城市交通狀況,提高公共交通的服務(wù)質(zhì)量最為有效的手段,不論從生態(tài)環(huán)境角度還是從社會經(jīng)濟(jì)角度來說均具有重要的意義。交通流量預(yù)測是智能交通實(shí)現(xiàn)的前提和關(guān)鍵,如何準(zhǔn)確地預(yù)測交通量信息已經(jīng)成為學(xué)者們研究的熱點(diǎn)。交通量受到多種隨機(jī)干擾因素的影響,具有一定的隨機(jī)性和動態(tài)性,因此交通量預(yù)測十分復(fù)雜,雖然很多學(xué)者已經(jīng)對此展開深入研究,取得了一定的成果,但是有關(guān)交通流預(yù)測理論的研究至今沒有形成較為成熟完備的理論體系,到底選取哪些預(yù)測模型,以及使用哪些方法進(jìn)行改進(jìn)才合理仍然是值得研究的問題。本文以智能預(yù)測理論為前提,以提高交通車流量的預(yù)測精度為目的,深入探討不同的智能方法和模型之間的有效組合形式,主要涉及以下幾個方面的研究工作。1.以灰色系統(tǒng)理論中的DGM(1,1)為基礎(chǔ),提出了DGM-GRNN和DGM-SVM兩種組合預(yù)測模型�；疑到y(tǒng)GM是在小樣本,貧信息的情況下經(jīng)常使用的一種預(yù)測模型,現(xiàn)有的灰色組合模型多采用GM(1,1)和BP神經(jīng)網(wǎng)絡(luò)進(jìn)行組合的方式。由于GM(1,1)沒有考慮未來可能加入的干擾因素對系統(tǒng)帶來的影響,因此不適合中長期預(yù)測,而DGM(1,1)模型采用離散形式對常規(guī)GM(1,1)建模進(jìn)行改進(jìn),彌補(bǔ)了傳統(tǒng)GM(1,1)模型的缺陷。另外,BP網(wǎng)絡(luò)易陷入局部極小值,并且計算結(jié)果隨機(jī)性較強(qiáng),因此本文提出了兩種殘差修正的DGM預(yù)測模型。首先使用DGM(1,1)模型對原始數(shù)據(jù)序列進(jìn)行預(yù)測,然后分別使用GRNN和SVM模型對尾段殘差序列進(jìn)行訓(xùn)練并獲取殘差的預(yù)測序列,最后合成最終的預(yù)測結(jié)果。在實(shí)際交通流預(yù)測實(shí)驗(yàn)中,通過與傳統(tǒng)的GM(1,1)和DGM(1,1)進(jìn)行對比,本文提出的組合模型在預(yù)測精度方面有了明顯提高,驗(yàn)證了組合模型的有效性。2.提出了基于粒子群算法優(yōu)化的支持向量機(jī)SVM預(yù)測模型。SVM以統(tǒng)計學(xué)理論和結(jié)構(gòu)風(fēng)險最小化原理為基礎(chǔ),能夠在小樣本學(xué)習(xí)環(huán)境下進(jìn)行分類和預(yù)測,是智能模型研究的熱點(diǎn)。本文深入探討了SVM中不同參數(shù)對系統(tǒng)預(yù)測的影響,針對SVM預(yù)測過程過參數(shù)設(shè)置不準(zhǔn)確的缺點(diǎn),分別以LSSVM和SMOSVM為基礎(chǔ),提出了兩種基于粒子群優(yōu)化的PSO-LSSVM和SMOSVM交通量預(yù)測模型。首先利用PSO算法對懲罰參數(shù)C和核寬度。進(jìn)行優(yōu)化,確定最優(yōu)的C和σ,然后分別使用SMOSVM和LSSVM通過交叉驗(yàn)證的手段進(jìn)行交通流的預(yù)測。通過與試湊法和網(wǎng)格法優(yōu)化的模型進(jìn)行對比分析實(shí)驗(yàn),本文提出的模型具有更好的預(yù)測性能,表明其能夠有效的預(yù)測實(shí)時交通流量的變化趨勢。3.提出了基于遺傳算法優(yōu)化的極限學(xué)習(xí)機(jī)預(yù)測模型GA-ELM。BP神經(jīng)網(wǎng)絡(luò)在訓(xùn)練調(diào)整各種參數(shù)的過程中,消耗了大量的時間,而極限學(xué)習(xí)機(jī)ELM在大大縮短網(wǎng)絡(luò)訓(xùn)練時間的同時并沒有降低網(wǎng)絡(luò)的收斂能力。ELM隨機(jī)設(shè)置輸入層與隱含層的連接權(quán)值和閾值,在訓(xùn)練過程中又不再重新調(diào)整這些參數(shù)的值,使得隱含層節(jié)點(diǎn)的有效性有待提高。針對這一問題,在網(wǎng)絡(luò)結(jié)構(gòu)確定的條件下,本文將遺傳算法用于極限學(xué)習(xí)機(jī)權(quán)重和閾值的選擇過程,通過目標(biāo)函數(shù)的使用,比隨機(jī)賦值獲得了更優(yōu)的權(quán)重和閾值,也使得隱含層和輸出層之間的連接權(quán)值矩陣更為合理。通過與BP模型、GA-BP模型以及標(biāo)準(zhǔn)的ELM模型實(shí)驗(yàn)對比,進(jìn)一步驗(yàn)證了本文提出的模型在預(yù)測精度和運(yùn)行時間上的優(yōu)勢。4.提出了時間序列、神經(jīng)網(wǎng)絡(luò)和灰色理論定權(quán)和不定權(quán)組合的交通流預(yù)測模型。目前,統(tǒng)計理論、非線性理論和智能理論在交通流中都有不同的應(yīng)用,各種單一模型具有一定的優(yōu)點(diǎn),但又存在一定的片面性。為了綜合利用各種預(yù)測模型所提供的信息,取長補(bǔ)短,本文以交通流預(yù)測常用的GM(1,1)、ARIMA和GRNN模型為基礎(chǔ),提出了一種固定權(quán)系數(shù)和一種變權(quán)系數(shù)的組合預(yù)測模型。在提出了準(zhǔn)預(yù)測絕對誤差的定義之后,分別建立了以相對誤差為依據(jù)的定權(quán)組合模型和Elman變權(quán)組合模型。實(shí)驗(yàn)結(jié)果表明,組合模型特別是變權(quán)系數(shù)組合模型在相對誤差、均方根誤差以及均等系數(shù)方面均優(yōu)于單一模型或兩種模型組合,從而驗(yàn)證了其有效性與可行性。5.綜合對比分析各種組合預(yù)測模型。對不同的組合預(yù)測模型使用相同的交通流量數(shù)據(jù)進(jìn)行實(shí)驗(yàn),分析和探討各種預(yù)測模型的適用性。論文的創(chuàng)新之處主要體現(xiàn)在利用智能模型的有效組合進(jìn)行交通流的預(yù)測。分別使用GRNN和SVM對DGM模型進(jìn)行殘差修正,進(jìn)一步提高了模型的預(yù)測精度；使用仿生學(xué)的粒子群算法和遺傳算法分別應(yīng)用于SVM和ELM,通過對模型參數(shù)的有效優(yōu)化,模型取得了更優(yōu)的預(yù)測效果；提出了基于GM、ARIMA和GRNN的定權(quán)組合和Elman變權(quán)組合,實(shí)驗(yàn)結(jié)果表明組合模型能夠獲得更好的性能評價指標(biāo)。綜上所述,本文的研究結(jié)果具有一定的理論和應(yīng)用價值,為更準(zhǔn)確地進(jìn)行交通流預(yù)測提供新思路和新途徑。
[Abstract]:With the development of the social economy and the progress of science and technology, the demand for traffic travel is increasing, the number of motor vehicles is increasing. The rapid growth of motor vehicles leads to traffic congestion, road safety, environmental pollution, energy consumption and so on. A large number of practical experiences show that the intelligent transportation system is changed. The traffic condition of the city and the most effective means to improve the service quality of the public transportation are of great significance both in the ecological environment and from the socioeconomic point of view. Traffic flow forecast is the precondition and key of the realization of intelligent traffic. How to accurately predict the traffic information has become a hot spot of research by the scholars. The quantity is influenced by a variety of random interference factors and has a certain randomness and dynamics, so the traffic volume prediction is very complicated. Although many scholars have studied it in depth and achieved some results, the research on traffic flow prediction theory has not formed a more mature and complete theoretical system, which is to be selected in the end. Some prediction models and which methods to be improved is still a problem that is still worth studying. In this paper, based on the intelligent prediction theory, in order to improve the prediction accuracy of traffic traffic, the effective combination form between different intelligent methods and models is discussed, and the research work of.1. is mainly involved in the following aspects. On the basis of DGM (1,1) in grey system theory, two combination forecasting models of DGM-GRNN and DGM-SVM are proposed. The grey system GM is a prediction model often used in the case of small sample and poor information. The existing grey combination models are mostly composed of GM (1,1) and BP neural network. Because GM (1,1) does not consider the possible future The influence of the interfering factors on the system is not suitable for medium and long term prediction, and the DGM (1,1) model improves the conventional GM (1,1) model in discrete form, and makes up for the defects of the traditional GM (1,1) model. In addition, the BP network is easy to fall into the local minimum, and the result of the calculation is more random. So two kinds of residual correction are proposed in this paper. The DGM model is used to predict the original data sequence using the DGM (1,1) model. Then, the GRNN and SVM models are used to train the residual sequence of the tail section and obtain the prediction sequence of the residual difference. Finally, the final prediction results are synthesized. In the actual traffic flow prediction experiment, the comparison with the traditional GM (1,1) and DGM (1,1) is made. The combined model proposed in this paper has improved the accuracy of prediction, and validates the effectiveness of the combined model.2.. The support vector machine SVM prediction model based on particle swarm optimization (PSO) optimization is based on the statistical theory and the principle of structural risk minimization, which can be classified and predicted in a small sample learning environment. It is an intelligent model, which is an intelligent model. In this paper, the influence of different parameters on the system prediction in SVM is discussed, and two kinds of PSO-LSSVM and SMOSVM traffic prediction models based on particle swarm optimization are proposed based on LSSVM and SMOSVM, which are based on LSSVM and SMOSVM. Firstly, the C and kernel width of penalty parameters are applied to the C and kernel width of the penalty parameters. Optimization, determine the optimal C and sigma, and then use SMOSVM and LSSVM to predict traffic flow through cross validation respectively. Through comparison and analysis experiments with the model optimized by the trial and the grid method, the proposed model has better prediction performance, which shows that it can effectively predict the change of real-time traffic flow. The potential.3. proposed the limit learning machine prediction model based on the genetic algorithm optimization GA-ELM.BP neural network consumed a lot of time in the process of training and adjusting the various parameters, while the limit learning machine ELM greatly shortened the network training time and did not reduce the convergence energy of the network.ELM randomly set the input layer and the hidden layer. In the training process, the values of these parameters are no longer adjusted in the training process, so the validity of the hidden layer nodes should be improved. Under the condition of the network structure, the genetic algorithm is applied to the selection of the weight and threshold of the limit learning machine, and the use of the target function is obtained. Better weights and thresholds make the connection weight matrix between the hidden layer and the output layer more reasonable. By comparing with the BP model, the GA-BP model and the standard ELM model experiment, it is further verified that the advantages of the model proposed in this paper are time series, neural network and grey theory in the prediction accuracy and running time. Traffic flow forecasting model of combination of fixed weight and indefinite right. At present, statistical theory, nonlinear theory and intelligent theory have different applications in traffic flow. All kinds of single models have certain advantages, but there are some one-sided. In order to make use of the information provided by all kinds of prediction models, this paper is based on traffic flow prediction. Based on the commonly used GM (1,1), ARIMA and GRNN models, a combination prediction model of the fixed weight coefficient and a variable weight coefficient is proposed. After the definition of the quasi prediction absolute error is put forward, the fixed weight combination model and the Elman variable weight combination model based on the relative error are established respectively. The experimental results show that the combined model is especially variable. The weight coefficient combination model is superior to the single model or two model combinations in relative error, root mean square error and equal coefficient, thus validates its effectiveness and feasibility.5. comprehensive comparison and analysis of various combination forecasting models. The innovation of this model is mainly embodied in the use of the effective combination of intelligent models to predict the traffic flow. The residual correction of the DGM model by using GRNN and SVM is used to further improve the prediction accuracy of the model. The bionics particle swarm optimization and genetic algorithm are used for SVM and ELM respectively. The model parameters are optimized effectively, and the model has better prediction effect. The combination of weight and Elman based on GM, ARIMA and GRNN is proposed. The experimental results show that the combined model can obtain better performance evaluation index. In summary, the results of this paper have a definite theoretical and application value for more accurate delivery. Flow prediction provides new ideas and new ways.
【學(xué)位授予單位】：東北師范大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2016
【分類號】：U491.14

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 文軍;蔣由輝;方文清;;航空貨運(yùn)量的優(yōu)化組合預(yù)測模型[J];計算機(jī)工程與應(yīng)用;2010年15期

2 黃元生;黎特;皮薇;;非平均權(quán)重條件下電力負(fù)荷組合預(yù)測模型研究[J];山東電力高等�？茖W(xué)校學(xué)報;2013年03期

3 丁岳維;組合預(yù)測模型的研究[J];西安公路交通大學(xué)學(xué)報;1997年04期

4 朱章;對組合預(yù)測模型預(yù)測精度的分析[J];黃石高等�？茖W(xué)校學(xué)報;1997年01期

5 邢棉;能源發(fā)展趨勢的非線性優(yōu)化組合預(yù)測模型研究[J];華北電力大學(xué)學(xué)報;2002年03期

6 陳華友,趙佳寶,劉春林;基于灰色關(guān)聯(lián)度的組合預(yù)測模型的性質(zhì)[J];東南大學(xué)學(xué)報(自然科學(xué)版);2004年01期

7 李眉眉;丁晶;衡彤;覃光華;;電力月負(fù)荷的混沌趨勢組合模型預(yù)測[J];四川電力技術(shù);2006年03期

8 張欣;;組合預(yù)測模型在上海內(nèi)河港口吞吐量預(yù)測中的應(yīng)用[J];水運(yùn)工程;2007年04期

9 王斌;張金隆;;航線流量組合預(yù)測模型研究[J];武漢理工大學(xué)學(xué)報(信息與管理工程版);2008年03期

10 趙海青,楊秀岐;灰色加法組合預(yù)測模型及其應(yīng)用[J];保定師范�？茖W(xué)校學(xué)報;2002年04期

相關(guān)會議論文 前10條

1 謝如賢;成盛超;程仕軍;陳思華;;變結(jié)構(gòu)組合預(yù)測模型的建立與應(yīng)用[A];全國青年管理科學(xué)與系統(tǒng)科學(xué)論文集（第2卷）[C];1993年

2 董景榮;;基于遺傳輔助設(shè)計的匯率組合預(yù)測模型研究[A];面向復(fù)雜系統(tǒng)的管理理論與信息系統(tǒng)技術(shù)學(xué)術(shù)會議專輯[C];2000年

3 馬永開;唐小我;;組合預(yù)測模型研究[A];管理科學(xué)與系統(tǒng)科學(xué)進(jìn)展——全國青年管理科學(xué)與系統(tǒng)科學(xué)論文集（第4卷）[C];1997年

4 成樞;劉國林;高放;;最優(yōu)組合預(yù)測模型及其在變形預(yù)測中的應(yīng)用[A];《測繪通報》測繪科學(xué)前沿技術(shù)論壇摘要集[C];2008年

5 何迎東;吳婉瑩;郭u&;陳華友;;基于離消度的組合預(yù)測模型及其應(yīng)用[A];第十屆中國不確定系統(tǒng)年會、第十四屆中國青年信息與管理學(xué)者大會論文集[C];2012年

6 陳華友;程蕾;張倩;;基于相關(guān)系數(shù)的IOWA算子最優(yōu)組合預(yù)測模型[A];第四屆中國不確定系統(tǒng)年會論文集[C];2006年

7 陳華友;;IOWA算子的組合預(yù)測模型及在所得稅預(yù)測中的應(yīng)用[A];第三屆不確定系統(tǒng)年會論文集[C];2005年

8 謝正文;孔凡玉;胡毅夫;;基于熵權(quán)的沉降組合預(yù)測模型及應(yīng)用[A];第一屆中國水利水電巖土力學(xué)與工程學(xué)術(shù)討論會論文集（下冊）[C];2006年

9 王永光;趙國浩;;變權(quán)組合預(yù)測模型在中國煤炭需求預(yù)測中的應(yīng)用[A];2007中國可持續(xù)發(fā)展論壇暨中國可持續(xù)發(fā)展學(xué)術(shù)年會論文集（4）[C];2007年

10 王尚俊;吳剛;陳華友;周禮剛;;基于廣義10WA算子的組合預(yù)測模型及在卷煙消費(fèi)需求中應(yīng)用[A];第十一屆中國不確定系統(tǒng)年會、第十五屆中國青年信息與管理學(xué)者大會論文集[C];2013年

相關(guān)博士學(xué)位論文 前5條

1 趙川;重載交通對高速公路橋梁的疲勞影響研究[D];河北工業(yè)大學(xué);2015年

2 于志恒;基于智能理論的交通流量組合預(yù)測模型研究[D];東北師范大學(xué);2016年

3 向昌盛;基于支持向量機(jī)的時間序列組合預(yù)測模型[D];湖南農(nóng)業(yè)大學(xué);2011年

4 萬玉成;基于未確知性的預(yù)測與決策方法及其應(yīng)用研究[D];東南大學(xué);2004年

5 南曉強(qiáng);風(fēng)電預(yù)測技術(shù)及其運(yùn)行分析[D];西南交通大學(xué);2013年

相關(guān)碩士學(xué)位論文 前10條

1 秦成;我國城市生活垃圾處理現(xiàn)狀及清運(yùn)量預(yù)測研究[D];天津財經(jīng)大學(xué);2015年

2 王海軍;基于組合預(yù)測模型的我國石油供需預(yù)測研究[D];中國石油大學(xué)(華東);2014年

3 劉源;EMD組合預(yù)測模型IMF分量選取的改進(jìn)[D];太原理工大學(xué);2016年

4 吳少華;組合預(yù)測模型及其在變形分析中的應(yīng)用研究[D];東華理工大學(xué);2016年

5 朱家明;幾種基于模糊信息集成算子的組合預(yù)測模型及其應(yīng)用[D];安徽大學(xué);2016年

6 孟玲玲;基于支持向量機(jī)的組合預(yù)測模型及其應(yīng)用研究[D];河南理工大學(xué);2015年

7 潘志剛;基于深度學(xué)習(xí)網(wǎng)絡(luò)的風(fēng)電場功率預(yù)測研究及應(yīng)用[D];上海電機(jī)學(xué)院;2016年

8 周發(fā)仁;多方法組合預(yù)測模型應(yīng)用研究[D];中國地震局地震預(yù)測研究所;2016年

9 尤志敏;組合預(yù)測方法在上市公司財務(wù)風(fēng)險預(yù)警中的研究與應(yīng)用[D];東北大學(xué);2011年

10 靳運(yùn)章;我國煤礦事故特征規(guī)律及組合預(yù)測模型研究[D];西安科技大學(xué);2016年

，

本文編號：2155670