Artificial Neural Network Application to the Friction Stir Welding of Al 6061 Alloy to Stainless Steel 304

(整期优先)网络出版时间:2008-01-11
/ 1
Thejoiningofa6-mmthicknessAl6061toStainlesssteel304hasbeenperformedbysolidstatewelding.Aselectionmethodofoptimumfrictionweldingconditionusingneuralnetworksisproposed.Thedatausedforanalysesarethefrictionstirweldingcondition,theinputparametersofthemodelconsistofweldingspeedandtoolrotationspeed.TheoutputsoftheANN(ArtificialNeuralNetwork)modelincludesresultingparameters,namely,maximumreachedtemperature,andheatingrateforbothaluminumalloy6061andstainlesssteel304duringfrictionstirweldingprocess.Theresultsofanalysissuggestthattheproposedmethodisaneffectiveonetoselectanoptimumweldingcondition.GoodperformanceoftheANNmodelwasachieved.Thecombinedinfluenceofweldingspeedandtoolrotationspeedonthemaximumreachedtemperatureandheatingrateforbothaluminumalloy6061andstainlesssteel304frictionstirweldingwassimulated.AcomparisonwasmadebetweentheoutputoftheANNprogramandfiniteelementmodel.Thecalculatedresultswereingoodagreementwiththatoffiniteelementmodel.