简介:Themultipolemomentmethodnotonlyconducestotheunderstandingofthedeformationofthespace-time,butalsoservesasaneffectivetooltoapproximatelysolvetheEinsteinfieldequationwith.However,theusualmultipolemomentsarerecursivelydeterminedbyasequenceofsymmetricandtrace-freetensors,whichisinconvenientforpracticalresolution.Inthispaper,wedevelopasimplifiedproceduretogeneratetheseriessolutionstothemetricofthestationaryvacuumwithaxisymmetry,andshowitsvalidity.Inordertounderstandthefreeparametersinthesolution,weproposetotaketheSchwarzschildmetricasastandardruler,andsomewell-knownexamplesareanalysedandcomparedwiththeseriessolutionsindetail.
简介:Thepresentpaperderivedtemperaturedistributionsinpowerseriesinasteadylaminarwakebehindaslenderstreamilinedheatedbodyofrevolution.Thetemperaturedistributionofthewakebehindthebodyfromx/d=2to70werefullyexploredusingarecirculatingwaterchannel.ThethermalwakepatternsbehingthebodywerevisualizedwiththeaidofinfraredpicturesandH2bubbles.
简介:IntheresearchofusingRadialBasisFunctionNeuralNetwork(RBFNN)forecastingnonlineartimeseries,weinvestigatehowthedifferentclusteringsaffecttheprocessoflearningandforecasting.Wefindthatk-meansclusteringisverysuitable.Inordertoincreasetheprecisionweintroduceanonlinearfeedbacktermtoescapefromthelocalminimaofenergy,thenweusethemodeltoforecastthenonlineartimeserieswhichareproducedbyMackey-Glassequationandstocks.Byselectingthek-meansclusteringandthesuitablefeedbackterm,muchbetterforecastingresultsareobtained.
简介:Inthispaper,opticalpulserepetitionratemultiplicationbasedonaseries-coupleddouble-ringresonatorisproposed.First,thespectralcharacteristicoftheseries-coupleddouble-ringresonatorissimulatedandtheoptimumcouplingcoefficientstoachieveaperiodicflat-toppassbandareobtained.Then,high-qualitypulserepetitionratemultiplicationisrealizedbyperiodicallyfilteringoutspectrallinesoftheinputpulsetrain.DifferentmultiplicationfactorsN2,3,4,5canbeobtainedbyadjustingtheringradii.Inaddition,comparedwithasingle-ringresonator,themultipliedoutputpulsetrainbyaseries-coupleddouble-ringresonatorexhibitsmuchbetterpoweruniformity.
简介:Anovelmodelisproposedwhichcomprisesofabeambridgesubjectedtoanaxialloadandaninfiniteseriesofmovingloads.Themovingloads,whosedistancebetweentheneighbouringonesisthelengthofthebeambridge,coupledwiththeaxialforcecanleadthevibrationofthebeambridgetocodimension-twobifurcation.Ofparticularconcernisaparameterregimewherenon-persistencesetregionsundergoatransitiontopersistenceregions.Theboundaryofeachstriperepresentsabifurcationwhichcandrivethesystemoffakindofdynamicsandjumptoanotherone,causingdamageduetotheresultingamplitudejumps.TheGalerkinmethod,averagingmethod,invertiblelineartransformation,andnearidentitynonlineartransformationsareusedtoobtaintheuniversalunfoldingforthecodimension-twobifurcationofthemid-spandeflection.Theefficiencyofthetheoreticalanalysisobtainedinthispaperisverifiedvianumericalsimulations.
简介:<正>Someproblemsinusingv-supportvectormachine(v-SVM)forthepredictionofnonlineartimeseriesarediscussed.Theproblemsincludeselectionofvariousnetparameters,whichaffecttheperformanceofprediction,mixtureofkernels,anddecompositioncooperationlinearprogrammingv-SVMregression,whichresultinimprovementsofthealgorithm.ComputersimulationsinthepredictionofnonlineartimeseriesproducedbyMackey-GlassequationandLorenzequationprovidesomeimprovedresults.