AI-driven multi-parameter optimization of high-performance epoxy composites for tribological applications

Résumé

Epoxy composites reinforced with a hybrid nanofiller consisting of paraffin oil (PO) and Al₂O₃ nanoparticles demonstrate enhanced mechanical and tribological performance for frictional applications.This study investigates the influence of Al₂O₃ NPs loading (0.5-2.0 wt.%) combined with 5 wt.%PO on hardness, compressive yield strength, elastic modulus, coefficient of friction, and wear resistance, supported by three-dimensional surface topography and scanning electron microscopy analyses of worn surfaces.The results indicate that an optimal balance between reinforcement and lubrication is achieved at low nanoparticle loading (1.0 wt.% Al₂O₃ NPs), where improved filler dispersion enhances load transfer and reduces surface damage.Significant reductions in friction and wear were observed, with decreases of approximately 43% and 34%, respectively, compared with neat epoxy.At higher loadings, (≥1.5 wt.% Al₂O₃), particle agglomeration influences deformation and frictional behavior.Furthermore, an adaptive neuro-fuzzy inference system (ANFIS) model shows strong agreement with experimental results, enabling reliable prediction of composite performance based on composition and processing variables.These findings highlight the effectiveness of combining hybrid nanofillers with AI-assisted modeling for optimizing epoxy composites in tribological applications.

Citer ce document

Accès au document

Texte intégral en lecture en ligne, réservé aux abonnés SPHAERO et aux membres de l'institution. Se connecter

Auteur(s)

Statistiques

Consultations : 1

Téléchargements : 0