基于神經(jīng)網(wǎng)絡(luò)的卡鉆預(yù)測(cè)方法研究.pdf

1、學(xué)位論文創(chuàng)新性聲明本人聲明所呈交的學(xué)位論文是我個(gè)人在導(dǎo)師指導(dǎo)下進(jìn)行的研究工作及取得的研究成果。盡我所知，除了文中特別加以標(biāo)注和致謝中所羅列的內(nèi)容以外，論文中不包含其他人已經(jīng)發(fā)表或撰寫過的研究成果；也不包含為獲得西安石油大學(xué)或其它教育機(jī)構(gòu)的學(xué)位或證書而使用過的材料。與我一同工作的同志對(duì)本研究所做的任何貢獻(xiàn)均已在論文中做了明確的說明并表示了謝意。申請(qǐng)學(xué)位論文與資料若有不實(shí)之處，本人承擔(dān)一切相關(guān)責(zé)任。論文作者簽名：壘墨日期：211查：女!!]

2、學(xué)位論文使用授權(quán)的說明本人完全了解西安石油大學(xué)有關(guān)保留和使用學(xué)位論文的規(guī)定，即：研究生在校攻讀學(xué)位期間論文工作的知識(shí)產(chǎn)權(quán)單位屬西安石油大學(xué)。學(xué)校享有以任何方法發(fā)表、復(fù)制、公開閱覽、借閱以及申請(qǐng)專利等權(quán)利。本人離校后發(fā)表或使用學(xué)位論文或與該論文直接相關(guān)的學(xué)術(shù)論文或成果時(shí)，署名單位仍然為西安石油大學(xué)。論文作者簽名：蘭虬導(dǎo)師簽名：日期：z出!』：17日期：竺!!!墨：9注：如本論文涉密，請(qǐng)?jiān)谑褂檬跈?quán)的說明中指出(含解密年限等)。Suhiect

3、：Speciality：Name：Instructor：TheStudyofPredictingPipeStickingBasedonNeuralNetworkPowerElectronicsandElectricalDrivesZhuDan(signatu舊叢叢ZhangQizhi(signatureAbstractPipestickingaccidenthasagreatprobabilityofoccurrenceandittak

4、esalongtimetounfreezingAfterstatisticsfromadrillingcompany，Timetodealwithstickingaccidentsisover60％ofthetotaldrillingaccidenttreatmenttimeSowiththepurposeofimprovingthedrillingefficiency，reducingstickingaccident，thispape

5、rstudiedthepredictingpipestickinkindepthFirstly，BPneuralnetworkwhichhasastrongnonlinearmappingabilitytoforecastthestickingWasselectedbasedontheanalysisofalargenumberofdrillingdata，andsummingupdifferentkindsoffactorsinflu

6、encingstickingaccidentcauses，symptomsandsolutionThispaperanalysedmechanismofstickingdeeply，andestablishedstickingpredictionmodelbasedonBPneuralnetworkAtthesametime，alargenumberofdrillingdatahasbeencollected，andcomposedof

7、trainingsampleandtestingsampleoftheneuralnetworkThenWainthestickingpredictionandverifythestickingpredictionabilityValidationresultsshowthatthetrainingerrorandtestingerrorofthestickingpredictionmodelwithinthescopeoftheper

8、mitIntheviewofthedefectsofBPlearningalgorithm，whichincludelowlearningefficiencyandslowconvergencespeed，thispaperimproveslearningalgorithmofthenetworkbyusingadaptiveleamingrate，SOastoimprovethepredictionprecisionofthenetw

9、ork，andreducethetrainingtimeByverifyingthemodel’SpredictionaccuracyhasbeenraisedandthetimeoftraininghasbeenreducedLastly，thiSPapersetsuploopstickingpredictionmodelinordertopredicthigll■一一C，一frequencyloopsticking，andverif

10、iesthepredictiveandgeneralizationabilityoftheloopstickingpredictionmodelTheverificationresultshowsthatthemodelCanpredictloopstickingaccidentsforregionalareaexactly，andalsohasgoodgeneralizationabilityaswellKeywords：Pipest