Enhancing Predictive Capabilities: Machine Learning Approaches for Predicting Mechanical Behavior in Friction Stir Welded Aluminum Alloys

Basit Öğe Kaydı
dc.authoridSun, Ying/0000-0001-6703-4270
dc.authoridDorbane, Abdelhakim/0000-0001-8294-7895
dc.authorwosidSun, Ying/N-2009-2017
dc.authorwosidDorbane, Abdelhakim/M-6993-2016
dc.contributor.authorDorbane, Abdelhakim
dc.contributor.authorHarrou, Fouzi
dc.contributor.authorDursun, Bekir
dc.contributor.authorSun, Ying
dc.date.accessioned2024-06-12T10:51:20Z
dc.date.available2024-06-12T10:51:20Z
dc.date.issued2024
dc.departmentTrakya Üniversitesien_US
dc.description.abstractAccurate prediction of friction stir welding (FSW) joint behavior is crucial for optimizing welding processes and ensuring structural integrity. This study exploits machine learning to predict the mechanical behavior of aluminum alloy FSW joints under varying temperatures. It involves a comparison of predictive performance across 18 models, including support vector regression (SVR), Gaussian process regression (GPR), ensemble models, and five distinct types of neural networks (NN). The assessment used Al6061-T6 aluminum alloy with the FSW joining method at temperatures of 25, 100, 200, and 300 degrees C. To ensure robustness, the machine learning models were developed using a fivefold cross-validation approach, with Bayesian optimization applied for fine-tuning during training. Results revealed the ability of machine learning to precisely predict the mechanical behavior of FSW joints. Specifically, GPR and the triple NN model outperformed other models, achieving average R2 values of 0.9879 and 0.9703, respectively.en_US
dc.description.sponsorshipKing Abdullah University of Science and Technology (KAUST)en_US
dc.description.sponsorshipThe authors (Fouzi Harrou and Ying Sun) would like to acknowledge the support of the King Abdullah University of Science and Technology (KAUST) in conducting this research.en_US
dc.identifier.doi10.1007/s11665-024-09345-2
dc.identifier.issn1059-9495
dc.identifier.issn1544-1024
dc.identifier.scopus2-s2.0-85189769515en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.urihttps://doi.org/10.1007/s11665-024-09345-2
dc.identifier.urihttps://hdl.handle.net/20.500.14551/18330
dc.identifier.wosWOS:001198566400002en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringeren_US
dc.relation.ispartofJournal Of Materials Engineering And Performanceen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectAluminum Sheetsen_US
dc.subjectFriction Stir Weldingen_US
dc.subjectFSWen_US
dc.subjectMachine Learningen_US
dc.subjectMechanical Behavioren_US
dc.subjectOptimizationen_US
dc.subjectPredictive Modelsen_US
dc.subjectProcess Parametersen_US
dc.subjectWelded Jointsen_US
dc.subjectMicrostructureen_US
dc.subjectModelen_US
dc.subjectTransformationen_US
dc.subjectTemperatureen_US
dc.subjectParametersen_US
dc.subjectEvolutionen_US
dc.subjectStrengthen_US
dc.subjectFractureen_US
dc.subjectSpeeden_US
dc.titleEnhancing Predictive Capabilities: Machine Learning Approaches for Predicting Mechanical Behavior in Friction Stir Welded Aluminum Alloysen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu