简介：ＷｅｌｄｑｕａｌｉｔｙｃｏｎｔｒｏｌｂｙｎｅｕｒａｌｎｅｔｗｏｒｋＨｕａｎｇＳｈｉｓｈｅｎｇ；ＬｉＤｉａｎｄＳｏｎｇＹｏｎｇｌｕｎ（ＳｏｕｔｈＣｈｉｎａＵｎｉｖｅｒｓｉｔｙｏｆＴｅｃｈｎｏｌｏｇｙ）Ａｂｓｔｒａｃｔ：Ａｒｔｉｆｉｃｉａｌｎｅｕｒａｌｎ...

简介：

简介：

简介：Inthepresentpaper,thegraphicalmethoddeterminationofoptimalweldingparametersofGMAWisdescribed.Somequalitycomplexcriteriathataretheratioofweldsizeshavebeenproposed.Thesecriteriaallowoptimizingtheshapeoftheweldmetalzone,reducingthelikelihoodofhotcracksformation,andreducingthestressconcentrationoftheweldatthetoe.Intheproposedmethodology,theearlierdescribedequationsconnectingtheweldingparametersandthewelddimensionsofmildandlow-alloysteelsareexplored.Determinationoftheoptimalweldingparametersiscarriedoutgraphicallytakingintoaccountthevarianceoftheweldingparameters.Anexampleofusingtheproposedmethoddestinedtodeterminetheoptimumweldingparametersisprovided.Itisshownthatitsaccuracyissufficientlygoodforapracticalapplication.

简介：

简介：

简介：Amethodwasdevelopedtorealizequalityevaluationoneveryweld-spotinresistancespotweldingbasedoninformationprocessingofartificialintelligent.Firstly,thesignalsofweldingcurrentandweldingvoltage,asinformationsource,weresynchronouslycollected.Inputpoweranddynamicresistancewereselectedasmonitoringwaveforms.Eightcharacteristicparametersrelatingtoweldqualitywereextractedfromthemonitoringwaveforms.Secondly,tensile-shearstrengthofthespot-weldedjointwasemployedasevaluatingtargetofweldquality.Throughcorrelationanalysisbetweeneverytwoparametersofcharacteristicvector,fivecharacteristicparameterswerereasonablyselectedtofoundamappingmodelofweldqualityestimation.Atlast,themodelwasrealizedbymeansofthealgorithmsofRadialBasicFunctionneuralnetworkandsamplematrixes.Theresultsshowedvalidationsbyasatisfactioninevaluatingweldqualityofmildsteeljointon-lineinspotweldingprocess.

简介：

简介：

简介：Laserblankweldingisbecomingmoreandmoreimportantintheautomotiveindustryandthequalityoftheweldiscriticalforasuccessfulapplication.Afullyautomatedsolutionisrequiredtoinspectthequalityoftheblanks.ThispaperpresentsavisioninspectionsystemwithaCMOScamerawhichusesART2networktoinspectthedefectson-linetoobtainthegeometryandthequalityoftheweldseam.TheneuralnetworkART2hasthecapabilityofself-learningfromtheenvironment.Itcandistinguishthedefectsthathavebeenlearnedbeforeandgivenewoutputsfornewdefects.SoART2networkissuitableforweldqualityinspectioninlaserblankwelding.Additionally,aCO_2laserisusedfortheblankbutt-welding.

简介：Basedonalargeamountofdissectionatweldedinterfaceandquantitativemicroscopicexaminationofweldedrate,thesuitablelimitgreyscalevaluewasdetermined,andtheweldedrateofsuperplasticsolid-stateweldinginterfaceofheterogeneoussteelwassystematicallystudiedbymeansofself-madeultrasonicC-scanningimaginginspectionsystem.Theexperimentalresultsshow:theweldedstateofsuperplasticsolid-stateweldinginterfaceofheterogeneoussteelcanbeconductedtobemoreaccurately,reliablyandquicklyinspectedbymeansofthissystem,andtheultrasonictestingresultsaregoodconsistentwithactualexaminationresultsoftheinterfacedefectivedistribution.Withintheextentofthesuitbleweldedrate,theweldedratein40Cr/T10Asuperplasticweldingprocesstestedbythissystemislinearwithitstensilestrengthofjoint.

简介：