Free axial vibration of short-fiber-reinforced nanorods: A hybrid semi-analytical and machine learning solution based on strain gradient theory


Kafkas U., AKPINAR M., UZUN B., YAYLI M. Ö.

MECHANICS BASED DESIGN OF STRUCTURES AND MACHINES, cilt.54, sa.1, 2026 (SCI-Expanded, Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 54 Sayı: 1
  • Basım Tarihi: 2026
  • Doi Numarası: 10.1080/15397734.2026.2677845
  • Dergi Adı: MECHANICS BASED DESIGN OF STRUCTURES AND MACHINES
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, DIALNET, Academic Search Ultimate (EBSCO), Engineering Source (EBSCO)
  • Bursa Uludağ Üniversitesi Adresli: Evet

Özet

This study investigates the free axial vibration of short-fiber-reinforced (SFR) nanorods under strain gradient theory by combining a Fourier-based semi-analytical model with an explainable machine learning surrogate. Five regression models were trained on a 5000-sample synthetic dataset, with Radial-Basis-Function Support Vector Regression (RBF-SVR) delivering the highest accuracy (R2=0.997, MAPE=1.0%). Mode-wise SHAP analysis revealed a clear physical regime transition: lower vibration modes are governed mainly by fiber-to-matrix density, stiffness, and volume fraction, whereas higher modes are dominated by strain-gradient and slenderness effects. The surrogate enables fast, accurate parametric studies.