本文選題：交通流數(shù)據(jù) + 異常數(shù)據(jù)識別�。� 參考：《北京交通大學》2014年碩士論文

【摘要】：城市道路基礎(chǔ)設(shè)施的供給與交通需求之間的矛盾日益突出,交通擁堵問題日益嚴重。目前,僅僅依靠拓寬道路、增加路網(wǎng)密度等基礎(chǔ)設(shè)施已經(jīng)難以解決城市的交通擁堵問題,而智能交通系統(tǒng)的研發(fā)是一條可行的途徑。先進的交通管理系統(tǒng)是智能交通系統(tǒng)的重要組成部分,其中交通流數(shù)據(jù)的質(zhì)量識別與修正是先進的交通管理系統(tǒng)中最基礎(chǔ)和關(guān)鍵的組成部分,如何提高城市道路交通流檢測數(shù)據(jù)的精確度和實時性就變得非常重要。 論文提出單源數(shù)據(jù)修正和多源數(shù)據(jù)修正相結(jié)合的方法來提高道路交通流數(shù)據(jù)的精確度。首先對不同檢測數(shù)據(jù)進行單源數(shù)據(jù)的質(zhì)量識別與修正研究。文中基于交通流理論和閾值理論對原始數(shù)據(jù)進行異常數(shù)據(jù)識別與分類,之后應用歷史趨勢法、時間序列法和交通流局部穩(wěn)定的特性對缺失數(shù)據(jù)進行修補,并提出改進的埃特金插值算法對錯誤數(shù)據(jù)進行修正；其次,論文提出基于數(shù)值優(yōu)化的BP神經(jīng)網(wǎng)絡(luò)對多源數(shù)據(jù)進行融合修正,分別選用BFGS擬牛頓法、正切擬牛頓法、Fletcher-Reeves共軛梯度法、Polak-Ribiere共軛梯度法和Levenberg-Marquardt算法等五種數(shù)值優(yōu)化的方法對BP神經(jīng)網(wǎng)絡(luò)進行改進,并分別對其相對誤差、運行時間、迭代次數(shù)進行了對比分析；最后,論文選取北京市二環(huán)路多源檢測數(shù)據(jù)進行實例驗證。
[Abstract]:The contradiction between the supply of urban road infrastructure and traffic demand is increasingly prominent, and the traffic congestion problem is becoming more and more serious. At present, it is difficult to solve the problem of urban traffic congestion only by widening roads and increasing road network density, and the research and development of intelligent transportation system is a feasible way. Advanced traffic management system is an important part of intelligent transportation system, in which the quality identification and correction of traffic flow data is the most basic and key part of advanced traffic management system. How to improve the accuracy and real-time of urban traffic flow detection data becomes very important. In this paper, the method of single source data correction and multi-source data correction is proposed to improve the accuracy of road traffic flow data. First, the quality identification and correction of single source data for different detection data are studied. Based on the traffic flow theory and the threshold theory, the original data are identified and classified, and then the missing data are repaired by using the historical trend method, time series method and the local stability of traffic flow. An improved Etkin interpolation algorithm is proposed to correct the error data. Secondly, a BP neural network based on numerical optimization is proposed to modify the multi-source data, respectively, using BFGS quasi-Newton method. The tangent quasi Newton method, Fletcher-Reeves conjugate gradient method, Polak-Ribiere conjugate gradient method and Levenberg-Marquardt algorithm are used to improve the BP neural network, and the relative error, running time and iteration times are compared and analyzed respectively. The paper selects the Beijing second Ring Road multi-source detection data to carry on the example verification.
【學位授予單位】：北京交通大學
【學位級別】：碩士
【學位授予年份】：2014
【分類號】：U491

【參考文獻】

相關(guān)期刊論文 前10條

1 邵杰,黃山;城市道路路段車輛旅行時間檢測系統(tǒng)的研究[J];道路交通與安全;2002年05期

2 朱雷雷;張韋華;聶慶慧;;干線公路交通流數(shù)據(jù)有效性檢驗規(guī)則[J];東南大學學報(自然科學版);2011年01期

3 鄒亮;徐建閩;朱玲湘;溫惠英;;基于浮動車移動檢測與感應線圈融合技術(shù)的行程時間估計模型[J];公路交通科技;2007年06期

4 牛世峰;姜桂艷;;交通數(shù)據(jù)質(zhì)量宏觀評價與控制方法[J];公路;2012年12期

5 盛鵬;趙樹龍;宋萬忠;劉怡光;楊夢龍;;基于旅行時間檢測系統(tǒng)的交通應用研究[J];計算機應用;2007年11期

6 蔣銳;王均;;道路交通流數(shù)據(jù)檢驗與修復方法[J];交通與計算機;2006年06期

7 邵春福;趙熠;吳戈;;道路交通數(shù)據(jù)采集技術(shù)研究展望[J];現(xiàn)代交通技術(shù);2006年06期

8 譚裕安;翦俊;;城市道路交通流實時數(shù)據(jù)質(zhì)量控制技術(shù)[J];現(xiàn)代交通技術(shù);2009年01期

9 任德記,張超峰,陸付民,尚澤宇;變形控制網(wǎng)監(jiān)測數(shù)據(jù)補差方法研究[J];人民黃河;2004年11期

10 耿彥斌,于雷,趙慧;ITS數(shù)據(jù)質(zhì)量控制技術(shù)及應用研究[J];中國安全科學學報;2005年01期

，

本文編號：1798058