本文關(guān)鍵詞： 短時(shí)船舶交通流預(yù)測(cè) 神經(jīng)網(wǎng)絡(luò) 超限學(xué)習(xí)機(jī)　出處：《大連海事大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著我國(guó)海運(yùn)事業(yè)的迅速發(fā)展,我國(guó)沿海已經(jīng)成為世界上水上交通最繁忙的區(qū)域之一。航經(jīng)我國(guó)沿海水域的船舶數(shù)量逐漸增多,海上交通事故也有增加的趨勢(shì),帶來(lái)交通安全、海洋環(huán)境污染等一系列問(wèn)題。短時(shí)交通流預(yù)測(cè)是交通流預(yù)測(cè)的重點(diǎn)研究?jī)?nèi)容之一,及時(shí)、準(zhǔn)確的短時(shí)船舶交通流預(yù)測(cè)信息是保障船舶通航安全、航道暢通、交通有效運(yùn)行的關(guān)鍵。本文在總結(jié)現(xiàn)有道路短時(shí)交通流預(yù)測(cè)和船舶交通流預(yù)測(cè)模型的基礎(chǔ)上,針對(duì)現(xiàn)有短時(shí)交通流預(yù)測(cè)算法精度低、收斂慢、性能不穩(wěn)定等問(wèn)題,對(duì)短時(shí)船舶交通流預(yù)測(cè)問(wèn)題進(jìn)行了研究,并引進(jìn)在道路短時(shí)交通流預(yù)測(cè)方面應(yīng)用廣泛的超限學(xué)習(xí)機(jī)(Extreme Learning Machine,ELM)對(duì)成山頭分道通航水域的短時(shí)船舶交通流進(jìn)行預(yù)測(cè)。本文首先簡(jiǎn)單介紹了交通流理論基礎(chǔ)知識(shí)和短時(shí)船舶交通流預(yù)測(cè)的基本概念,并對(duì)船舶交通流特征、交通流預(yù)測(cè)的基本特征和基本原則、預(yù)測(cè)方法模型要求、現(xiàn)有預(yù)測(cè)方法及各自的與缺點(diǎn)進(jìn)行了分析,并給出了短時(shí)船舶交通流預(yù)測(cè)模型的評(píng)價(jià)指標(biāo)。其次,應(yīng)用數(shù)據(jù)獲取軟件從海事局AIS網(wǎng)站獲取成山頭分道通航水域的船舶信息,并對(duì)數(shù)據(jù)進(jìn)行篩選。為減少數(shù)據(jù)波動(dòng)對(duì)基于ELM神經(jīng)網(wǎng)絡(luò)短時(shí)船舶交通流預(yù)測(cè)模型的影響,對(duì)采集到的數(shù)據(jù)進(jìn)行了標(biāo)準(zhǔn)歸一化處理,提高模型的預(yù)測(cè)精度。然后,應(yīng)用MATLAB這一數(shù)學(xué)工具建立了基于ELM神經(jīng)網(wǎng)絡(luò)的成山頭短時(shí)船舶交通流預(yù)測(cè)模型,并對(duì)編程實(shí)現(xiàn)進(jìn)行了介紹。最后,分別采用小波神經(jīng)網(wǎng)絡(luò)的時(shí)間序列預(yù)測(cè)模型、BP神經(jīng)網(wǎng)絡(luò)非線性預(yù)測(cè)模型和ELM神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)模型來(lái)對(duì)成山頭分道通航警戒區(qū)進(jìn)行短時(shí)交通流預(yù)測(cè)。研究結(jié)果表明,在一定誤差范圍內(nèi),基于小波神經(jīng)網(wǎng)絡(luò)的時(shí)間序列預(yù)測(cè)模型、BP神經(jīng)網(wǎng)絡(luò)非線性預(yù)測(cè)模型和基于ELM神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)模型均能較好的預(yù)測(cè)成山頭分道通航水域的短時(shí)船舶交通流量。對(duì)比分析上述3種預(yù)測(cè)模型的預(yù)測(cè)結(jié)果和誤差,分析結(jié)果表明ELM神經(jīng)網(wǎng)絡(luò)模型能夠有效避免傳統(tǒng)神經(jīng)網(wǎng)絡(luò)的固有缺陷,應(yīng)用ELM神經(jīng)網(wǎng)絡(luò)對(duì)短時(shí)船舶交通流預(yù)測(cè)的誤差更小、運(yùn)算時(shí)間更快、精度更高。更能滿足短時(shí)船舶交通流預(yù)測(cè)的要求。
[Abstract]:With the rapid development of marine transportation in our country, the coastal area of our country has become one of the busiest water transportation areas in the world. The number of ships passing through the coastal waters of our country is increasing gradually, and the number of maritime traffic accidents is also increasing. Short-term traffic flow forecasting is one of the key research contents of traffic flow forecasting. Timely and accurate short-term ship traffic flow forecasting information is to ensure the navigation safety of ships. On the basis of summarizing the existing short-term traffic flow forecasting and ship traffic flow forecasting models, this paper aims at the low precision and slow convergence of the existing short-term traffic flow forecasting algorithm. The prediction of short-time ship traffic flow is studied in this paper. It also introduces extreme Learning Machine, which is widely used in road short-term traffic flow prediction. In this paper, the basic knowledge of traffic flow theory and the basic concept of short-term ship traffic flow prediction are introduced. The characteristics of ship traffic flow, the basic characteristics and principles of traffic flow prediction, the requirements of forecasting method model, the existing forecasting methods and their respective shortcomings are analyzed. The evaluation index of short-term ship traffic flow prediction model is given. Secondly, the data acquisition software is used to obtain the ship information from the AIS website of MSA. In order to reduce the influence of data fluctuation on short-term ship traffic flow prediction model based on ELM neural network, the collected data are normalized. The prediction accuracy of the model is improved. Then, the prediction model of short-time ship traffic flow based on ELM neural network is established by using MATLAB, and the programming implementation is introduced. Time series prediction models based on wavelet neural network are used respectively. The nonlinear prediction model of BP neural network and the ELM neural network prediction model are used to predict the traffic flow in the navigational warning area of Chengshan Mountain head. The results show that the traffic flow is within a certain error range. Time series prediction model based on wavelet neural network. Both the BP neural network nonlinear prediction model and the ELM neural network prediction model can be used to predict the short-time ship traffic flow in the Shantou and navigable waters. The prediction results of the above three forecasting models are compared and analyzed. And errors. The analysis results show that the ELM neural network model can effectively avoid the inherent defects of the traditional neural network, the application of ELM neural network to short-term ship traffic flow prediction error is smaller, faster operation time. The accuracy is higher and can meet the demand of short-time ship traffic flow forecast.
【學(xué)位授予單位】：大連海事大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：U692

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 崔翔鵬;黃洪瓊;;基于GA優(yōu)化ELM的船舶交通流預(yù)測(cè)模型[J];微型機(jī)與應(yīng)用;2017年09期

2 梁小春;陳曉云;;基于奇異值分解的極限學(xué)習(xí)機(jī)多變量時(shí)間序列預(yù)測(cè)模型[J];福州大學(xué)學(xué)報(bào)(自然科學(xué)版);2017年01期

3 劉虎;李偉峰;;基于AIS數(shù)據(jù)的海上交通流區(qū)域自動(dòng)識(shí)別[J];中國(guó)航海;2016年04期

4 余丹;吳小俊;;一種卷積神經(jīng)網(wǎng)絡(luò)和極限學(xué)習(xí)機(jī)相結(jié)合的人臉識(shí)別方法[J];數(shù)據(jù)采集與處理;2016年05期

5 芮蘭蘭;李欽銘;;基于組合模型的短時(shí)交通流量預(yù)測(cè)算法[J];電子與信息學(xué)報(bào);2016年05期

6 羅來(lái)鵬;;基于BP神經(jīng)網(wǎng)絡(luò)的城市占道交通擁堵預(yù)測(cè)[J];黑龍江工程學(xué)院學(xué)報(bào);2016年01期

7 季雪美;高軍偉;劉新;張彬;;基于ELM算法的短時(shí)交通流預(yù)測(cè)研究[J];青島大學(xué)學(xué)報(bào)(工程技術(shù)版);2015年04期

8 何雅玲;;大型海港進(jìn)港主航道通過(guò)能力及組織模式研究[J];中國(guó)水運(yùn);2015年11期

9 李紅祥;方遜;;基于AIS的船舶交通流量統(tǒng)計(jì)方法研究[J];武漢理工大學(xué)學(xué)報(bào)(交通科學(xué)與工程版);2011年04期

10 劉敬賢;劉振東;周鋒;;基于廣義回歸神經(jīng)網(wǎng)絡(luò)的船舶交通量預(yù)測(cè)模型[J];中國(guó)航海;2011年02期

相關(guān)碩士學(xué)位論文 前10條

1 呂磊;短時(shí)交通流預(yù)測(cè)與線路推薦研究[D];山東大學(xué);2016年

2 于亞男;基于神經(jīng)網(wǎng)絡(luò)模型的短時(shí)交通流預(yù)測(cè)及應(yīng)用研究[D];太原理工大學(xué);2015年

3 陳會(huì)茹;高速公路基本路段實(shí)時(shí)交通狀態(tài)判別方法的研究及應(yīng)用[D];長(zhǎng)安大學(xué);2015年

4 邱世崇;基于時(shí)空特性的城市道路短時(shí)交通流預(yù)測(cè)研究[D];重慶交通大學(xué);2015年

5 李軍;海上交通信息發(fā)布體系的構(gòu)建[D];大連海事大學(xué);2014年

6 楊元元;基于時(shí)間序列模型的短時(shí)交通流預(yù)測(cè)的研究與應(yīng)用[D];西安電子科技大學(xué);2014年

7 周鋒;基于元胞自動(dòng)機(jī)的沿海港口水域船舶交通流演化仿真研究[D];武漢理工大學(xué);2012年

8 王茂清;基于船舶行為特征的港口航道通過(guò)能力研究[D];武漢理工大學(xué);2012年

9 董宇;航道通過(guò)能力及服務(wù)水平研究[D];河海大學(xué);2006年

10 甘明星;基于Lattice Boltzmann方法的交通流模型研究[D];武漢理工大學(xué);2004年

，

本文編號(hào)：1473229