本文選題：鐵路運(yùn)輸 + RBF神經(jīng)網(wǎng)絡(luò)　； 參考：《鐵道科學(xué)與工程學(xué)報(bào)》2014年04期

【摘要】：根據(jù)徑向基神經(jīng)網(wǎng)絡(luò)具有分析非線性動態(tài)系統(tǒng)的混沌特性的特點(diǎn),對鐵路客貨運(yùn)發(fā)送量相關(guān)時(shí)間序列進(jìn)行分析和研究,在Takens相空間重構(gòu)的基礎(chǔ)上,利用互信息方法求嵌入時(shí)延、偽鄰域方法求嵌入維數(shù);應(yīng)用G-P方法和最大Lyapunov指數(shù)方法對鐵路客貨運(yùn)量時(shí)間序列進(jìn)行混沌識別;根據(jù)RBF神經(jīng)網(wǎng)絡(luò)的學(xué)習(xí)算法和辨識原理,對鐵路客貨運(yùn)量預(yù)測流程進(jìn)行分析。應(yīng)用徑向基神經(jīng)網(wǎng)絡(luò)對鐵路客貨運(yùn)量自1999-01-01~2012-08-27共4 988 d的發(fā)送量為基礎(chǔ)進(jìn)行徑向基神經(jīng)網(wǎng)絡(luò)預(yù)測;并對預(yù)測誤差進(jìn)行檢驗(yàn)及對預(yù)測結(jié)果進(jìn)行分析。研究結(jié)果表明:基于徑向基神經(jīng)網(wǎng)絡(luò)預(yù)測值能很好地與實(shí)際值相吻合,因而在鐵路客貨運(yùn)量相關(guān)時(shí)間序列中預(yù)測有廣泛的實(shí)用價(jià)值。
[Abstract]:According to the characteristic of the radial basis function neural network (RBF) which has the characteristic of analyzing the chaos characteristic of the nonlinear dynamic system, the correlation time series of railway passenger and freight transport quantity is analyzed and studied. Based on the reconstruction of Takens phase space, the embedded time delay is solved by mutual information method. The pseudo-neighborhood method is used to calculate the embedding dimension, the G-P method and the maximum Lyapunov exponent method are used to identify the time series of railway passenger and cargo traffic, and the prediction flow of railway passenger and freight volume is analyzed according to the learning algorithm and identification principle of RBF neural network. The radial basis function neural network (RBF) was applied to forecast the passenger and cargo transport volume from 1999-01-01g to 2012-08-27. The radial basis function neural network was used to forecast the railway passenger and cargo transport volume from 1999-01-01g to 2012-08-27, and the prediction error was tested and the prediction results were analyzed. The results show that the predicted value based on radial basis function neural network is in good agreement with the actual value, so it has a wide range of practical value in the correlation time series of railway passenger and cargo traffic.
【作者單位】： 中國鐵道科學(xué)研究院電子計(jì)算技術(shù)研究所;鐵道部信息技術(shù)中心;中國鐵路總公司計(jì)劃統(tǒng)計(jì)部;
【基金】：鐵道部科技研究計(jì)劃資助項(xiàng)目(2007X008-G,2008X015-H)
【分類號】：U293.13;U294.13;TP183

【相似文獻(xiàn)】

相關(guān)期刊論文 前3條

1 李曉俊;呂曉艷;劉軍;;基于徑向基神經(jīng)網(wǎng)絡(luò)的鐵路短期客流預(yù)測[J];鐵道運(yùn)輸與經(jīng)濟(jì);2011年06期

2 李志勇;文睿;危韌勇;;基于徑向基神經(jīng)網(wǎng)絡(luò)的機(jī)車牽引能耗計(jì)算模型[J];鐵道學(xué)報(bào);2011年09期

3 丁彥闖;兆文忠;;考慮疲勞損傷約束的車輛焊接結(jié)構(gòu)輕量化設(shè)計(jì)[J];鐵道學(xué)報(bào);2008年05期

相關(guān)碩士學(xué)位論文 前3條

1 文睿;機(jī)車牽引能耗計(jì)算方法的研究[D];中南大學(xué);2011年

2 朱佼佼;基于改進(jìn)智能算法的電力機(jī)車牽引變壓器故障診斷技術(shù)研究[D];中南大學(xué);2011年

3 張明磊;鐵路旅客運(yùn)輸產(chǎn)品生命周期識別研究[D];中南大學(xué);2013年

，

本文編號：1988449