發(fā)布時(shí)間：2018-06-14 22:54

  本文選題：軌道交通 + 客流預(yù)測　； 參考：《北京交通大學(xué)》2012年碩士論文

【摘要】：隨著城市規(guī)模的不斷擴(kuò)大、人口的不斷增加、私人小汽車的逐漸普及,交通擁堵、環(huán)境污染、能源消耗等問題日趨嚴(yán)重,這與人們自由出行的愿望背道而馳,城市面臨巨大的交通壓力。準(zhǔn)時(shí)、環(huán)保、舒適、運(yùn)量大、效益好的城市軌道交通已經(jīng)成為解決交通問題的主要發(fā)展方向�？土髁渴浅鞘熊壍澜煌肪W(wǎng)規(guī)劃與設(shè)計(jì)的基礎(chǔ),而前期的客流預(yù)測是城市軌道交通工程建設(shè)的關(guān)鍵技術(shù)。 圍繞城市軌道交通客流的短期預(yù)測問題,本文主要進(jìn)行了如下的研究工作： 1、對北京市軌道交通清明節(jié)假期的客流數(shù)據(jù)進(jìn)行統(tǒng)計(jì)和分析,得到了其時(shí)序特征、周期規(guī)律及主要影響因素。此外,對線路流量和進(jìn)站量數(shù)據(jù)進(jìn)行聚類分析,有效劃分?jǐn)?shù)據(jù)樣本類型,為模型改進(jìn)及案例分析提供可靠的數(shù)據(jù)支持。 2、針對RBF神經(jīng)網(wǎng)絡(luò)單一模型結(jié)構(gòu)的局限性現(xiàn)狀,構(gòu)建基于時(shí)序特征的多模塊加權(quán)神經(jīng)網(wǎng)絡(luò)預(yù)測模型,通過軌道交通線路流量的預(yù)測實(shí)例,驗(yàn)證改進(jìn)后預(yù)測模型具有更高的預(yù)測精度。 3、針對支持向量機(jī)單一核函數(shù)的不足,構(gòu)建改進(jìn)的基于混合核函數(shù)的支持向量機(jī)預(yù)測模型,通過對進(jìn)站量預(yù)測的實(shí)例分析,證明改進(jìn)后支持向量機(jī)模型更好的擬合效果及在城市軌道交通短期客流預(yù)測領(lǐng)域的可行性。 4、考慮RBF神經(jīng)網(wǎng)絡(luò)和支持向量機(jī)兩種單項(xiàng)預(yù)測方法在學(xué)習(xí)方法、建模方式及結(jié)構(gòu)特征等方面的優(yōu)勢,將這兩種預(yù)測方法有機(jī)的融合在一起,構(gòu)建基于灰色關(guān)聯(lián)度最大化的組合預(yù)測模型。通過清明節(jié)線路流量的預(yù)測實(shí)例,得到了組合預(yù)測方法比單項(xiàng)預(yù)測方法更大的關(guān)聯(lián)度,證明組合預(yù)測模型優(yōu)于單項(xiàng)預(yù)測模型。
[Abstract]:With the continuous expansion of the city scale, the increasing population, the gradual popularization of private cars, traffic congestion, environmental pollution, energy consumption and other problems are increasingly serious, which runs counter to people's desire to travel freely. The city is facing great traffic pressure. Punctuality, environmental protection, comfort, large volume and good efficiency of urban rail transit have become the main development direction of solving traffic problems. Passenger flow is the basis of urban rail transit network planning and design, and the prediction of early passenger flow is the key technology of urban rail transit engineering construction. Focusing on the short-term prediction of urban rail transit passenger flow, this paper mainly carries out the following research work: 1. The statistics and analysis of the passenger flow data of Ching Ming Festival holiday in Beijing rail transit are carried out, and the time series characteristics are obtained. Periodic law and main influencing factors. In addition, cluster analysis of line flow and incoming data is carried out, and data sample types are divided effectively, which provides reliable data support for model improvement and case analysis. 2. In view of the limitations of single model structure of RBF neural network, The prediction model of multi-module weighted neural network based on time series feature is constructed, and the forecasting example of rail transit line flow is given. It is verified that the improved prediction model has higher prediction accuracy. 3. Aiming at the deficiency of single kernel function of support vector machine, an improved support vector machine prediction model based on hybrid kernel function is constructed. It is proved that the improved support vector machine model has better fitting effect and the feasibility in the field of short-term passenger flow prediction of urban rail transit. 4. Two single forecasting methods, RBF neural network and support vector machine, are considered in this paper. Based on the advantages of modeling and structural features, the two prediction methods are combined together to construct a combined prediction model based on the maximization of grey correlation degree. Through the example of Ching Ming Festival line flow forecasting, the combined forecasting method is better than the single forecasting method, and it is proved that the combined forecasting model is superior to the single prediction model.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2012
【分類號】：U239.5;U293.13

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 董景榮,楊秀苔;基于模糊邏輯系統(tǒng)的非線性組合預(yù)測方法研究[J];管理科學(xué)學(xué)報(bào);1999年03期

2 徐小力,徐洪安,曹愛東;旋轉(zhuǎn)機(jī)組的基于變權(quán)重神經(jīng)網(wǎng)絡(luò)組合預(yù)測模型[J];中國機(jī)械工程;2003年04期

3 王進(jìn);史其信;;短時(shí)交通流預(yù)測模型綜述[J];中國公共安全;2005年01期

4 王碩,張有富,金菊良;基于BP-AGA的非線性組合預(yù)測方法研究[J];中國工程科學(xué);2005年04期

5 趙建玉;賈磊;楊立才;朱文興;;基于粒子群優(yōu)化的RBF神經(jīng)網(wǎng)絡(luò)交通流預(yù)測[J];公路交通科技;2006年07期

6 王玉敏;;基于改進(jìn)BP神經(jīng)網(wǎng)絡(luò)的組合預(yù)測模型設(shè)計(jì)[J];數(shù)學(xué)的實(shí)踐與認(rèn)識;2006年04期

7 謝開貴,李春燕,俞集輝;基于遺傳算法的短期負(fù)荷組合預(yù)測模型[J];電網(wǎng)技術(shù);2001年08期

8 譚國真,丁浩;廣義神經(jīng)網(wǎng)絡(luò)的研究及其在交通流預(yù)測中的應(yīng)用[J];控制與決策;2002年S1期

9 王宏杰,林良明,徐大淦,顏國正;基于改進(jìn)BP網(wǎng)交通流動態(tài)時(shí)序預(yù)測算法的研究[J];交通與計(jì)算機(jī);2001年03期

10 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(bào)(自然科學(xué)版);2004年01期

相關(guān)博士學(xué)位論文 前1條

1 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)測理論與方法研究[D];北京交通大學(xué);2007年

相關(guān)碩士學(xué)位論文 前3條

1 唐明;短時(shí)交通流特性及其預(yù)測方法的研究[D];長沙理工大學(xué);2004年

2 王樹盛;都市圈軌道交通客流預(yù)測理論及方法研究[D];東南大學(xué);2004年

3 屠小娥;基于神經(jīng)網(wǎng)絡(luò)的非線性預(yù)測控制研究[D];蘭州理工大學(xué);2007年

，

本文編號：2019296