Title of article
ResidualstresspredictionofdissimilarmetalsweldingatNPPsusingsupportvectorregressionOriginalResearchArticle
Author/Authors
ManGyunNa، نويسنده , , JinWeonKim، نويسنده , , DongHyukLim، نويسنده , , Young-JuneKang، نويسنده ,
Issue Information
روزنامه با شماره پیاپی سال 2008
Pages
8
From page
1503
To page
1510
Abstract
Residualstressesareanimportantfactorinthecomponentintegrityandlifeassessmentofweldedstructures.Inthispaper,asupportvectorregression(SVR)methodispresentedtopredicttheresidualstressfordissimilarmetalweldingaccordingtovariousweldingconditions.DissimilarweldingjointbetweennozzleandpipeisregardedintheanalysessinceithasbeenknowntobehighlysusceptibletoPrimaryWaterStressCorrosionCracking(PWSCC)intheprimarysystemofanuclearpowerplant(NPP).Theresidualstressdistributionsarepredictedalongtwostraightpathsofaweldzone:apipeflowpathontheinnerweldsurfaceandapathconnectingtwocentersoftheinnerandoutersurfacesofaweldzoneofapipe.FourSVRmodelsaredevelopedforfournumericaldatagroupswhicharesplitaccordingtothetwoendsectionconstraintsandthetwopredictionpathsandtheSVRmodelsareoptimizedbyageneticalgorithm.TheSVRmodelsaretrainedbyusingadatasetpreparedfortraining,optimizedbyusinganoptimizationdataset,andverifiedbyusingatestdatasetindependentofthetrainingdataandtheoptimizationdata.ItisknownthattheSVRmodelsaresufficientlyaccuratetobeusedintheintegrityevaluationbypredictingtheresidualstressofdissimilarmetalweldingzones.
Journal title
Nuclear Engineering and Design Eslah
Serial Year
2008
Journal title
Nuclear Engineering and Design Eslah
Record number
895107
Link To Document