資源描述：
《基于非等時(shí)距加權(quán)灰色模型與神經(jīng)網(wǎng)絡(luò)的軌道不平順預(yù)測(cè)-論文.pdf》由會(huì)員上傳分享，免費(fèi)在線閱讀，更多相關(guān)內(nèi)容在行業(yè)資料-天天文庫。
1、第36卷第1期鐵道學(xué)報(bào)Vol_36NO．12014年1月JOURNALOFTHECHINARAILWAYSOCIETYJanuary2014文章編號(hào)：10018361(2014)01—0081一O7基于非等時(shí)距加權(quán)灰色模型與神經(jīng)網(wǎng)絡(luò)的軌道不平順預(yù)測(cè)韓晉，楊岳，陳峰，吳湘華(中南大學(xué)交通運(yùn)輸工程學(xué)院，湖南長(zhǎng)沙41O075)摘要：對(duì)軌道不平順的發(fā)展趨勢(shì)進(jìn)行有效預(yù)測(cè)，可以提高鐵路線路養(yǎng)護(hù)的維修效率，保障行車安全。根據(jù)軌道不平順的發(fā)展特性，提出一種基于非等時(shí)距加權(quán)灰色理論和神經(jīng)網(wǎng)絡(luò)法的組合預(yù)測(cè)方法。該方法通過構(gòu)建非等時(shí)距加權(quán)灰色預(yù)測(cè)模型，將原始TQI序列的平
2、均值作為累加序列初值，將連續(xù)累積函數(shù)的積分面積作為背景值，對(duì)累加序列進(jìn)行加權(quán)處理，較好地反映了時(shí)間序列對(duì)軌道不平順預(yù)測(cè)結(jié)果的貢獻(xiàn)。在此基礎(chǔ)上，引入BP神經(jīng)網(wǎng)絡(luò)模型對(duì)TQI預(yù)測(cè)的殘差序列進(jìn)行修正，較好地克服了單一模型預(yù)測(cè)精度偏低的不足。分別對(duì)滬昆線上行兩段線路的軌道不平順進(jìn)行預(yù)測(cè)，結(jié)果表明該預(yù)測(cè)方法相對(duì)誤差平均值分別為2．76和2．O8，預(yù)測(cè)結(jié)果的后驗(yàn)差比值分別為0．121和0．151，精度等級(jí)達(dá)到l級(jí)。關(guān)鍵詞：軌道不平順；神經(jīng)網(wǎng)絡(luò)；非等時(shí)距；灰色模型．力口權(quán)；殘差修正中圖分類號(hào)：U212．24+6文獻(xiàn)標(biāo)志碼：Adoi：10．3969／j．issn．1
3、001—8360．2014．01．013PredictionofTrackIrregularityBasedonNon。。equalIntervalWeightedGreyModelandNeuralNetworkHANJin，YANGYue，CHENFeng，WUXiang—hua(SchoolofTrafficandTransportati0nEngineering，CentralSouthUniversity，Changsha410075，China)Abstract：Effectivepredictionofthetrackirregular
4、itydevelopmenttrendcanimprovetheefficiencyofrailwaylinemaintenance&repairsandSOensuretrafficsafety．Accordingtotrackirregularitydevelopmentcharacter—istics，thecombinationpredictionmethodbasedonthenon—equalintervalweightedgreytheoryandneuralnet—workmethodwasproposed．Withthismetho
5、d，byconstructingthenon—equalintervalweightedgreypredictionmodel，theaverageoftheoriginalTQIsequencewasregardedasthecumulativesequenceinitialvalue，theinte—gralareaofthecontinuousaccumulationfunctionwasusedasthebackgroundvalue，thecumulativesequencewasprocessedbyweighting．Therefore
6、，thecontributionofthetimesequencetothetrackirregularitypredic—tionresultswasbetterreflected．Onthisbasis，theBPneuralnetworkmodelwasintroducedtoamendtheTQIpredictionresidualssequenceandtoovercomethedrawbackoflowpredictionaccuracybyasinglemode1．ThetrackirregularitiesoftWOup—direct
7、ionsectionsoftheShanghai—KunmingLinewerepredictedrespectively．Thepredictionresultsindicatethatthemeansoftherelativeerrorsare2．76and2．08respectively，theposteri—orerrorratiosare0．121and0．151respectively，andtheaccuracylevelreachesA．Keywords：trackirregularity；neuralnetwork；non—equa
8、linterval；greymodel；weight；residualmodification利用軌道不平順
