泵毕业设计外文文献资料下载.pdf
- 文档编号:16120544
- 上传时间:2022-11-20
- 格式:PDF
- 页数:16
- 大小:304.74KB
泵毕业设计外文文献资料下载.pdf
《泵毕业设计外文文献资料下载.pdf》由会员分享,可在线阅读,更多相关《泵毕业设计外文文献资料下载.pdf(16页珍藏版)》请在冰豆网上搜索。
PredictingaxialpistonpumpperformanceusingneuralnetworksMansourA.Karkouba,OsamaE.Gada,MahmoudG.RabiebaCollegeofEngineeringandPetroleum,KuwaitUniversity,KuwaitbMilitaryTechnicalCollege,Cairo,EgyptReceived15October1996;@#@receivedinrevisedform25March1998;@#@accepted23April1998AbstractAneuralnetworkmodelforanaxialpistonpump(bent-axisdesign)isderivedinthispaper.Themodelusesdataobtainedfromanexperimentalsetup.Thepurposeofthisongoingstudyisthereductionofthepowerlossathighpressures.However,atthebeginning,astudyisbeingdonetopredictthebehaviorofthecurrentdesignofthepump.TheneuralnetworkmodelhasafeedforwardarchitectureandusestheLevenbergMarquardtoptimizationtechniqueinthetrainingprocess.Themodelwasabletopredictthebehaviorofthepumpaccurately.#1998ElsevierScienceLtd.Allrightsreserved.1.IntroductionVariable-displacementaxialpistonpumpsareimportantdevicesthatarecommonlyusedinfluidpowersystems,suchascontrolledhydraulicpowersuppliesandcontrolledhydrostatictransmissiondrives.Thedisplacementvaryingmechanismandthepower-to-weightratioofthisdevicemakeitmostsuitableforcontrolofhighpowerlevels.Thedesignofaxialpistonpumpsboastsdependabilityandsimplicity;@#@however,theirmostimportantcharacteristicisthatofvariableoutputdisplacement.Alotofworkhasbeendoneintheareaofaxialpistonpumps;@#@however,onlyafewcontributionswillbediscussedhere.KaliafetisandCostopoulos5studiedthestaticanddynamiccharacteristicsofanaxialpistonvariabledisplacementpumpwithpressureregulator.Theaccuracyoftheproposedmodelisdependentonthedynamicoperatingcurvesofthemanufacturersdata.Theauthorsconcludedthattheoperatingconditionsareverycrucialforthepumpdynamicbehaviorwhichcanbeimprovedbydecreasingthesetpressure.Harrisetal.4simulatedandmeasuredthecylinderpressureandsuctionflowrippleforanaxialpistonMechanismandMachineTheory34(1999)121112260094-114X/99/$-seefrontmatter#1998ElsevierScienceLtd.Allrightsreserved.PII:
@#@S0094-114X(98)00086-XandMasakasu7studiedtheexperimentalandtheoreticalstaticanddynamiccharacteristicsoftheoperatingmomentofaswash-platetype,variabledelivery,axialpistonpump.Anewpredictionmethodoftheoperatingmomentwasproposed.Thevalidityofthenewmethodwasverifiedexperimentallyforthepumpcharacteristicsinwhichaportplatewithwide,shortanddeepnotcheswasused.EdgeandDarling2,studiedthecylinderpressureandflowinanoilhydraulicaxialpistonpump.Theproposedmodelwascheckedexperimentally.Theinfluenceoftheportplateandreliefgroovedesignonthecylinderpressureandpumpflowripplewasdiscussed.Analternativemodelingtechnique,neuralnetworks(NN),hasbeenproventogivegoodresults,especiallywhenthesystemishighlynonlinear.Thistechniquetriestoemulatetheworkofthehumanbraininrecognizinginformation.KarkoubandElkamel6usedaneuralnetworkmodeltopredictthepressuredistributioninarectangulargasbearing.Thedesignedmodelpredictedthepressuredistributionaswellastheload-carryingcapacitymoreaccuratelythantheotheravailabletools.Gharbietal.3predictedthebreakthroughoilrecoveryusingneuralnetworks.TheNNmodelperformedmuchbetterthanthecommonregressionorfinitedi?
@#@erencemethods.Lietal.8usedNNsalongwiththePowellsoptimizationtechniquetomodelandcontrolsingleanddoublelinkinvertedpendulums.Theauthorswereabletoachievegoodresults.Pandaetal.9appliedNNstomodelfluidcontactsinPrudhoeBayoilfields.Theresultantmodelestimatedthefluiddistributionattargetoilwellsmoreaccuratelythantheconventionalregression-basedtechniques.Aoyamaetal.1havederivedanNNmodeltopredicttheresponseofnon-minimumphasesystems.ThedevelopedmodelwasappliedtotheVandeVussreactorandacontinuousstirredtankbioreactorandtheresultswerepromising.Thispaperdealswiththemodelingofcertainpressuresinanaxialpistonpump(bent-axisdesign)usingneuralnetworks.Adescriptionoftheexperimentalsetupusedtocollectthetrainingdatawillbegivenfirst,then,abriefintroductiontotheneuralnetworkmodelingprocedurewillfollow.2.ExperimentalsetupThetrainingdatawasobtainedfromanexperimentalsetupwhichwillbediscussedinthissection.Themaincomponentofthesetupistheaxialpistonpump.Inthefollowingsection,wewillgiveadescriptionofhowthepumpworks,thenadescriptionofhowthetrainingdatawascollectedwillfollow.2.1.Bent-axispumpTheschematicdiagramshowninFig.2describesthebasiccomponentsoftheaxialpistonpumpusedintheexperimentwhilethecontrollerforthispumpisshowninFig.3.Thepumpconsistsoftwomaingroups.Thefirstgroupistherotarygroup,whichcontainsthedriveshaft(31),pistons(32),cylinderblocks(33),andcontrollens(34).Sevenpisto
- 配套讲稿:
如PPT文件的首页显示word图标,表示该PPT已包含配套word讲稿。双击word图标可打开word文档。
- 特殊限制:
部分文档作品中含有的国旗、国徽等图片,仅作为作品整体效果示例展示,禁止商用。设计者仅对作品中独创性部分享有著作权。
- 关 键 词:
- 毕业设计 外文 文献