简介:Inthispaper,theweldpoolshapecontrolbyintelligentstrategywasstudied.Aneuronself-learningPSDcontrollerforbacksidewidthofweldpoolinpulsedGTAWwithwirefillerwasdesigned.ThePSDcontrolarithmeticwasanalyzed,simulatingexperimentbyMATLABsoftwarewasdone,andthevalidatingexperimentsonvariedheatsinkworkpieceandvariedgapworkpieceweresuccessfullyimplemented.Thestudyresultsshowthattheneuronself-learningPSDcontrolmethodcanattainaperfectcontroleffectunderdifferentsetvaluesandconditions,andissuitablefortheweldingprocesswiththevariedstructureandcoefficientsofcontrolmodel.
简介:AnewtypeofDZ9000EOxygenGaseousHVOFsystem(GHVOF)isdevelopedwhichcanreducethecostofcoatingsandincreasethein-situremovabilitytoadaptvariousworkingconditions.Thewholesystemiseconomical,whichenablesthesystemtomeettherequirementofsprayingmediumorlowcostHighVelocityOxy-Fuel(HVOF)coatingsformediumandsmalljobshops.ThedepositedcermetscoatingsbytheDZ9000EsystemhavegoodperformancewithaveragemicrohardnessHV0.2ofmorethan1000andthebondstrengthbetweencoatingandsubstrateofgreaterthan50MPa.
简介:Basedonthemethodofartificialneuralnetwork,anewapproachhasbeendevisedtopredictthemechanicalpropertyofE4303electrode.Theoutlinedpredicationmodelfordeterminingthemechanicalpropertyofelectrodewasbuiltupontheproductiondata.Theresearchleveragesabackpropagationalgorithmastheneuralnetwork'slearningrule.Theresultindicatesthattherearepositivecorrelationsbetweenthepredictedresultsandthepracticalproductiondata.Hence,usingtheneuralnetwork,predicationofelectrodepropertycanberealized.Forthefirsttime,thisresearchprovidesamorescientificmethodfordesigningelectrode.