Comparative performance analysis of optimization algorithms for hyperparameter tuning in LSBoost modeling of mechanical properties in FDM-printed nanocomposites

Basit Öğe Kaydı
dc.authoridSeyedzavvar, Mirsadegh/0000-0002-3324-7689
dc.authoridHashemi Soudmand, Behzad/0000-0003-3094-7185
dc.contributor.authorSeyedzavvar, Mirsadegh
dc.contributor.authorBoga, Cem
dc.contributor.authorSoudmand, Behzad Hashemi
dc.date.accessioned2026-02-27T07:33:05Z
dc.date.available2026-02-27T07:33:05Z
dc.date.issued2025
dc.description.abstractHyperparameter tuning is essential for developing accurate machine learning models, yet its role in predicting the mechanical properties of 3D-printed nanocomposites remains underexplored. This study evaluates the performance of three optimization techniques-Bayesian Optimization (BO), Simulated Annealing (SA), and Genetic Algorithm (GA)-in tuning a Least Squares Boosting (LSBoost) model for predicting the mechanical properties of fused deposition modeling (FDM) 3D-printed polylactic acid (PLA)/silica (SiO2) nanocomposites. The properties assessed include modulus of elasticity (E), yield strength (Sy), and toughness at ultimate strength (Ku), influenced by key process parameters: extrusion rate (ER), SiO2 nanoparticle concentration (SC), deposition layer thickness (LT), infill density (ID), and infill geometry (IG). Tensile specimens were produced using a Taguchi L27 orthogonal array and tested under uniaxial tension. Tuning of the LSBoost model minimized a composite objective function involving root mean square error (RMSE) and (1-R2) loss metrics. Results demonstrated that GA achieved the best performance for yield strength prediction, with an RMSE of 1.9526 MPa and R2 of 0.9713, while BO yielded the highest R2 (0.9776) for modulus of elasticity prediction with a test RMSE of 130.13 MPa. For toughness, GA produced the lowest test RMSE of 102.86 MPa and the highest R2 of 0.7953 among the optimization methods. Generally, GA consistently outperformed BO and SA in optimizing the LSBoost model across most mechanical properties, highlighting its effectiveness for hyperparameter tuning in the context of FDM-fabricated nanocomposites.
dc.description.sponsorshipResearch Council of Trkiye (TBIbull;TAK) [123M862]
dc.description.sponsorshipThis work was supported by the Scientific and Technological Research Council of Turkiye (TUEBITAK) under 1001-program with grant number 123M862.
dc.identifier.doi10.1016/j.eswa.2025.128111
dc.identifier.issn0957-4174
dc.identifier.issn1873-6793
dc.identifier.urihttp://dx.doi.org/10.1016/j.eswa.2025.128111
dc.identifier.urihttps://hdl.handle.net/20.500.14669/4447
dc.identifier.volume287
dc.identifier.wosWOS:001498346600009
dc.indekslendigikaynakWeb of Science
dc.language.isoen
dc.publisherPergamon-Elsevier Science Ltd
dc.relation.ispartofExpert Systems With Applications
dc.relation.publicationcategoryMakale - Uluslararas� Hakemli Dergi - Kurum ��retim Eleman�
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20260302
dc.subjectLeast Squares Boosting technique
dc.subjectFused deposition modeling
dc.subjectPolymer nanocomposites
dc.subjectHyperparameter optimization
dc.subject3D-printing setting
dc.subjectMechanical response
dc.titleComparative performance analysis of optimization algorithms for hyperparameter tuning in LSBoost modeling of mechanical properties in FDM-printed nanocomposites
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu