【摘要】：在智能交通系統(tǒng)中,交通流預(yù)測(cè)是一個(gè)重要的組成部分。實(shí)施交通信號(hào)控制、路徑誘導(dǎo)、事故檢測(cè)等的重要前提是快速而準(zhǔn)確的短時(shí)交通流預(yù)測(cè)。但是,交通系統(tǒng)具有高度的復(fù)雜性、非線性和不確定性等特征,其是由人、車(chē)、路等多種客體組成的復(fù)雜系統(tǒng),對(duì)交通流做出實(shí)時(shí)、準(zhǔn)確地預(yù)測(cè)是目前智能交通領(lǐng)域研究的熱點(diǎn)和難點(diǎn)之一。然而,由于短時(shí)交通流信息量大,不確定性噪聲信號(hào)干擾強(qiáng),加之城市道路網(wǎng)絡(luò)的拓?fù)浣Y(jié)構(gòu)復(fù)雜,致使怎樣實(shí)現(xiàn)城市道路短時(shí)交通流預(yù)測(cè)一直阻礙著智能交通的長(zhǎng)遠(yuǎn)發(fā)展。為了解決上述問(wèn)題,已經(jīng)提出了許多預(yù)測(cè)方法,但因未考慮不確定干擾信號(hào)或城市路網(wǎng)復(fù)雜性對(duì)短時(shí)交通流所造成的影響,導(dǎo)致預(yù)測(cè)結(jié)果的實(shí)時(shí)性與準(zhǔn)確性都不盡理想。本文采用Mallat算法,對(duì)短時(shí)交通流信號(hào)進(jìn)行小波分解與重構(gòu),旨在濾掉短時(shí)交通流的強(qiáng)干擾噪聲信號(hào),此法可以提高短時(shí)交通流信息預(yù)處理速度及精度。針對(duì)交通流數(shù)據(jù)的復(fù)雜性和非線性特性,本文引入神經(jīng)網(wǎng)絡(luò)理論,利用其對(duì)非線性問(wèn)題的良好處理能力來(lái)進(jìn)行短時(shí)交通流的預(yù)測(cè),是交通流預(yù)測(cè)的有效方法。綜上,針對(duì)城市道路交通流量的時(shí)變性、復(fù)雜性以及非線性特點(diǎn),為提高短時(shí)交通流預(yù)測(cè)的精準(zhǔn)度,該文提出了一種基于小波去噪和自適應(yīng)遺傳算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的短時(shí)交通流組合預(yù)測(cè)模型。利用小波變換可以將交通流分解成具有不同頻率的多個(gè)平滑子序列,然后對(duì)各個(gè)子序列分別進(jìn)行預(yù)測(cè),此種方式能有效解決被預(yù)測(cè)交通流的時(shí)變性、復(fù)雜性以及非線性問(wèn)題,同時(shí)自適應(yīng)遺傳算法具有全局搜索能力,能夠很好的解決神經(jīng)網(wǎng)絡(luò)的缺陷——易陷入局部極小值。并將預(yù)測(cè)結(jié)果與小波神經(jīng)網(wǎng)絡(luò)方法以及遺傳神經(jīng)網(wǎng)絡(luò)方法的預(yù)測(cè)結(jié)果進(jìn)行了比較。結(jié)果表明,本文所建立模型的平均絕對(duì)誤差、平均絕對(duì)百分比誤差以及均方根誤差均較小,且擬合度EC值較大,由此較好地說(shuō)明了該模型在短時(shí)交通流預(yù)測(cè)上的有效性、精確性。
[Abstract]:Traffic flow prediction is an important part of intelligent transportation system. The important premise of traffic signal control, route guidance and accident detection is fast and accurate short-time traffic flow prediction. However, the traffic system has the characteristics of high complexity, nonlinearity and uncertainty. It is a complex system composed of people, cars, roads and other objects, making real-time traffic flow. Accurate prediction is one of the hotspots and difficulties in the field of intelligent transportation. However, because of the large amount of traffic flow information, the strong disturbance of uncertain noise signal and the complex topology of urban road network, how to realize the short-term traffic flow prediction of urban road has been hindering the long-term development of intelligent transportation. In order to solve these problems, many forecasting methods have been put forward, but the real-time and accuracy of the prediction results are not ideal because of not considering the influence of uncertain interference signals or the complexity of urban road network on the short-term traffic flow. In this paper, Mallat algorithm is used to decompose and reconstruct the short time traffic flow signal with wavelet transform in order to filter out the strong interference noise signal of the short time traffic flow. This method can improve the speed and precision of the short time traffic flow information preprocessing. In view of the complexity and nonlinear characteristics of traffic flow data, the neural network theory is introduced in this paper. It is an effective method to predict traffic flow in short time by using its good ability to deal with nonlinear problems. In summary, in order to improve the accuracy of short-term traffic flow prediction, in view of the time-varying, complex and nonlinear characteristics of urban road traffic flow, This paper presents a short-term traffic flow combination prediction model based on wavelet denoising and adaptive genetic algorithm to optimize BP neural network. Using wavelet transform, traffic flow can be decomposed into multiple smooth subsequences with different frequencies, and each subsequence can be predicted separately. This method can effectively solve the time-varying, complex and nonlinear problems of the predicted traffic flow. At the same time, the adaptive genetic algorithm has the ability of global searching, and it can solve the defect of neural network, which is easy to fall into the local minimum. The prediction results are compared with those of wavelet neural network method and genetic neural network method. The results show that the average absolute error, mean absolute percentage error and root mean square error of the model are small, and the EC value of the fitting degree is large, which shows the validity of the model in the short-term traffic flow prediction. Accuracy.
【學(xué)位授予單位】：華東交通大學(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 沈國(guó)江;王嘯虎;孔祥杰;;短時(shí)交通流量智能組合預(yù)測(cè)模型及應(yīng)用[J];系統(tǒng)工程理論與實(shí)踐;2011年03期

2 張國(guó)強(qiáng);彭曉明;;自適應(yīng)遺傳算法的改進(jìn)與應(yīng)用[J];艦船電子工程;2010年01期

3 陳岳明;蕭德云;;基于動(dòng)態(tài)交通分配的路網(wǎng)應(yīng)急疏散模型[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);2009年08期

4 孫湘海;劉潭秋;;基于神經(jīng)網(wǎng)絡(luò)和SARIMA組合模型的短期交通流預(yù)測(cè)[J];交通運(yùn)輸系統(tǒng)工程與信息;2008年05期

5 聶佩林;余志;何兆成;;基于約束卡爾曼濾波的短時(shí)交通流量組合預(yù)測(cè)模型[J];交通運(yùn)輸工程學(xué)報(bào);2008年05期

6 張玉梅;曲仕茹;溫凱歌;;基于混沌和RBF神經(jīng)網(wǎng)絡(luò)的短時(shí)交通流量預(yù)測(cè)[J];系統(tǒng)工程;2007年11期

7 張梁斌;周必水;奚李峰;;自適應(yīng)遺傳算法與分形圖像壓縮結(jié)合的新方法[J];計(jì)算機(jī)應(yīng)用研究;2006年07期

8 劉學(xué)鋒;劉聯(lián)會(huì);;圖像Mallat算法邊界延拓問(wèn)題的研究[J];現(xiàn)代電子技術(shù);2006年09期

9 王曉原;劉海紅;;基于投影尋蹤自回歸的短時(shí)交通流預(yù)測(cè)[J];系統(tǒng)工程;2006年03期

10 任子武;傘冶;;自適應(yīng)遺傳算法的改進(jìn)及在系統(tǒng)辨識(shí)中應(yīng)用研究[J];系統(tǒng)仿真學(xué)報(bào);2006年01期

相關(guān)博士學(xué)位論文 前4條

1 許小可;基于非線性分析的海雜波處理與目標(biāo)檢測(cè)[D];大連海事大學(xué);2008年

2 姚智勝;基于實(shí)時(shí)數(shù)據(jù)的道路網(wǎng)短時(shí)交通流預(yù)測(cè)理論與方法研究[D];北京交通大學(xué);2007年

3 李星毅;基于相似性的交通流分析方法[D];北京交通大學(xué);2010年

4 陳柳;小波分析和神經(jīng)網(wǎng)絡(luò)應(yīng)用于大氣污染預(yù)測(cè)的研究[D];西安建筑科技大學(xué);2006年

相關(guān)碩士學(xué)位論文 前4條

1 胡楓;基于馬爾科夫模型的短時(shí)交通流預(yù)測(cè)研究[D];南京郵電大學(xué);2013年

2 雷旭東;基于自適應(yīng)神經(jīng)網(wǎng)絡(luò)的車(chē)室噪聲主動(dòng)控制系統(tǒng)研究[D];重慶交通大學(xué);2012年

3 丁蕾;面向城市交通控制的短時(shí)交通流預(yù)測(cè)方法研究[D];大連理工大學(xué);2009年

4 吳浩勇;城市快速路交通參數(shù)預(yù)測(cè)方法研究[D];吉林大學(xué);2005年

，

本文編號(hào)：2201840