【摘要】：隨著高速公路的不斷發(fā)展與建設(shè),由于其高效快速的通行能力已被越來(lái)越多的人作為日常出行方式的主要選擇。但是,隨著人們的出行需求的不斷提高,已有的路網(wǎng)通行能力早已不能滿(mǎn)足現(xiàn)有出行量,隨即產(chǎn)生越來(lái)越多的交通擁堵?tīng)顩r,而其后果是交通事故的頻發(fā)與環(huán)境污染的惡化。因此,對(duì)高速公路短時(shí)交通量預(yù)測(cè)理論和方法的研究是實(shí)現(xiàn)合理有效的交通誘導(dǎo)、緩解交通擁堵,減少交通事故的頻發(fā)以及改善環(huán)境污染的必要前提。當(dāng)今高速公路數(shù)據(jù)采集技術(shù)與設(shè)備的不斷完善,使得高速公路短時(shí)交通量的預(yù)測(cè)成為可能,本文立足于高速公路短時(shí)交通量的可預(yù)測(cè)性,建立并改進(jìn)了不同的預(yù)測(cè)模型,并對(duì)其預(yù)測(cè)結(jié)果進(jìn)行了比較。首先,本文對(duì)短時(shí)交通量預(yù)測(cè)的研究背景、意義以及國(guó)內(nèi)外研究現(xiàn)狀進(jìn)行了總結(jié),分析了各類(lèi)預(yù)測(cè)方法和模型中存在的不足,應(yīng)用有效的采集手段統(tǒng)計(jì)了蘭海高速與武罐高速兩條高速公路的短時(shí)交通流量用于后續(xù)模型的實(shí)際分析中。其次,針對(duì)高速公路短時(shí)交通量時(shí)間序列的內(nèi)部特性,介紹了混沌理論的一些基本概念和參數(shù),為了更好地分析該時(shí)間序列,重構(gòu)其相空間,通過(guò)C-C算法計(jì)算蘭海高速和武罐高速的兩組實(shí)驗(yàn)數(shù)據(jù)的延遲時(shí)間和嵌入維數(shù),重構(gòu)了原始時(shí)間序列的相空間,以此將其內(nèi)部存在的實(shí)際規(guī)律挖掘出來(lái),在此基礎(chǔ)上,利用小數(shù)據(jù)量法計(jì)算兩組數(shù)據(jù)的最大李雅普諾夫指數(shù),計(jì)算結(jié)果均大于零,表明兩組數(shù)據(jù)都可以利用混沌理論對(duì)其進(jìn)行相應(yīng)的分析與研究。然后,介紹人工神經(jīng)網(wǎng)絡(luò)的相關(guān)概念,利用小波神經(jīng)網(wǎng)絡(luò)和RBF神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)高速公路短時(shí)交通量,在此之前,分別利用重構(gòu)的兩組數(shù)據(jù)的延遲時(shí)間和嵌入維數(shù)合理設(shè)計(jì)網(wǎng)絡(luò)的輸入層與輸出層神經(jīng)元的數(shù)量,建立良好的網(wǎng)絡(luò)拓?fù)浣Y(jié)構(gòu),對(duì)蘭海高速和武罐高速采集的數(shù)據(jù)在建立的網(wǎng)絡(luò)中進(jìn)行預(yù)測(cè)實(shí)驗(yàn),通過(guò)分析計(jì)算實(shí)驗(yàn)結(jié)果可以得出,RBF神經(jīng)網(wǎng)絡(luò)的預(yù)測(cè)效果比小波神經(jīng)網(wǎng)絡(luò)更好。最后,針對(duì)兩種神經(jīng)網(wǎng)絡(luò)中存在的不足之處,使用遺傳算法對(duì)兩種網(wǎng)絡(luò)的初始參數(shù)進(jìn)行最優(yōu)選擇,以保證網(wǎng)絡(luò)的輸出結(jié)果更加良好,在對(duì)蘭海高速和武罐高速采集的兩組數(shù)據(jù)進(jìn)行預(yù)測(cè)實(shí)驗(yàn)后,可以得出改進(jìn)后的兩種神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)誤差均得到了改善,同時(shí),改進(jìn)后的RBF神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)模型也優(yōu)于改進(jìn)后的小波神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)模型,可以更好地實(shí)現(xiàn)對(duì)高速公路短時(shí)交通量的預(yù)測(cè)。
[Abstract]:With the continuous development and construction of freeway, more and more people have taken it as the main choice of daily travel mode because of its efficient and rapid traffic capacity. However, with the continuous improvement of people's travel demand, the existing road network capacity has been unable to meet the existing travel volume, resulting in more and more traffic congestion, and the consequences are the frequent occurrence of traffic accidents and the deterioration of environmental pollution. Therefore, the research on the theory and method of short-term traffic volume prediction is a necessary prerequisite for realizing reasonable and effective traffic guidance, alleviating traffic congestion, reducing frequent traffic accidents and improving environmental pollution. Nowadays, with the continuous improvement of data acquisition technology and equipment of expressway, it is possible to predict the short-term traffic volume of expressway. Based on the predictability of short-term traffic volume of expressway, different prediction models are established and improved. The predicted results are compared. First of all, this paper summarizes the research background, significance and current research situation of short-term traffic volume prediction, and analyzes the shortcomings of various forecasting methods and models. In this paper, the short time traffic flow of Lanhai high speed highway and Wucan high speed highway is analyzed by means of effective collection method. Secondly, some basic concepts and parameters of chaos theory are introduced in order to better analyze the time series and reconstruct its phase space. The delay time and embedding dimension of two groups of experimental data of Lanhai high-speed and Wu-can high-speed are calculated by C-C algorithm, and the phase space of the original time series is reconstructed. The maximum Lyapunov exponent of the two groups of data is calculated by the method of small amount of data, and the results are all greater than zero, which indicates that both groups of data can be analyzed and studied by chaos theory. Then, the related concepts of artificial neural network are introduced. Wavelet neural network and RBF neural network are used to predict the short-time traffic volume of freeway. By using the delay time and embedding dimension of the reconstructed two groups of data, the number of neurons in the input and output layers of the network is reasonably designed, and a good network topology is established. The prediction experiments of the data collected at the high speed of Lanhai and Wu-can are carried out in the established network. By analyzing and calculating the experimental results, it can be concluded that the prediction effect of RBF neural network is better than that of wavelet neural network. Finally, aiming at the shortcomings of the two neural networks, genetic algorithm is used to optimize the initial parameters of the two networks to ensure that the output of the network is better. After the two groups of data collected at the high speed of Lanhai and Wu-can are forecasted, it can be concluded that the two improved neural networks have improved the prediction error, and at the same time, The improved RBF neural network prediction model is also better than the improved wavelet neural network prediction model, which can better realize the short-term traffic volume prediction of expressway.
【學(xué)位授予單位】：蘭州交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：U491.14

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 商強(qiáng);楊兆升;張偉;邴其春;周熙陽(yáng);;基于奇異譜分析和CKF-LSSVM的短時(shí)交通流量預(yù)測(cè)[J];吉林大學(xué)學(xué)報(bào)(工學(xué)版);2016年06期

2 傅成紅;張陽(yáng);;基于參數(shù)優(yōu)化的SVR城市群交通需求預(yù)測(cè)方法[J];系統(tǒng)工程;2016年02期

3 李曼;;小波分析實(shí)現(xiàn)圖像去噪[J];電腦知識(shí)與技術(shù);2015年05期

4 李巧茹;趙蓉;陳亮;;基于SVM與自適應(yīng)時(shí)空數(shù)據(jù)融合的短時(shí)交通流量預(yù)測(cè)模型[J];北京工業(yè)大學(xué)學(xué)報(bào);2015年04期

5 王珂;田瑞;王菲菲;;基于灰色遺傳支持向量機(jī)的短時(shí)交通流預(yù)測(cè)[J];武漢理工大學(xué)學(xué)報(bào)(交通科學(xué)與工程版);2014年05期

6 賈顯超;陳旭梅;弓晉麗;張溪;郭淑霞;;基于混沌理論的短期交通流量多步預(yù)測(cè)[J];交通信息與安全;2013年06期

7 孫棣華;李超;廖孝勇;;高速公路短時(shí)交通流量預(yù)測(cè)的改進(jìn)非參數(shù)回歸算法[J];公路交通科技;2013年11期

8 侯越;;DE優(yōu)化T-S模糊神經(jīng)網(wǎng)絡(luò)的交通流量預(yù)測(cè)[J];計(jì)算機(jī)工程與設(shè)計(jì);2013年09期

9 傅貴;韓國(guó)強(qiáng);逯峰;許子鑫;;基于支持向量機(jī)回歸的短時(shí)交通流預(yù)測(cè)模型[J];華南理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年09期

10 張玉梅;吳曉軍;白樹(shù)林;;交通流量序列混沌特性分析及DFPSOVF預(yù)測(cè)模型[J];物理學(xué)報(bào);2013年19期

相關(guān)博士學(xué)位論文 前4條

1 吳華穩(wěn);混沌時(shí)間序列分析及在鐵路貨運(yùn)量預(yù)測(cè)中的應(yīng)用研究[D];中國(guó)鐵道科學(xué)研究院;2014年

2 馬慶祿;基于混沌理論的交通狀態(tài)預(yù)測(cè)研究[D];重慶大學(xué);2012年

3 王義康;高爐冶煉復(fù)雜性分析及支持向量機(jī)擴(kuò)展建模預(yù)測(cè)研究[D];浙江大學(xué);2012年

4 韓曉霞;混沌與支持向量機(jī)結(jié)合的多相催化建模與優(yōu)化研究[D];太原理工大學(xué);2010年

相關(guān)碩士學(xué)位論文 前5條

1 肖凡;基于改進(jìn)的RBF神經(jīng)網(wǎng)絡(luò)對(duì)股市混沌效應(yīng)預(yù)測(cè)[D];中國(guó)海洋大學(xué);2014年

2 李騰飛;復(fù)雜光照條件下光伏發(fā)電系統(tǒng)輸出特性及最大功率點(diǎn)跟蹤研究[D];太原理工大學(xué);2014年

3 劉士劍;基于GA-BPNN的光伏最大功率點(diǎn)跟蹤控制研究[D];南京理工大學(xué);2013年

4 鄭令;基于小波神經(jīng)網(wǎng)絡(luò)的機(jī)械故障診斷方法的研究[D];大連交通大學(xué);2009年

5 孔明;基于神經(jīng)網(wǎng)絡(luò)和模糊系統(tǒng)的非線性隨機(jī)控制[D];華中科技大學(xué);2005年

，

本文編號(hào)：2227228