Free vibration analysis of annular and flat plates with sinusoidal corrugations using isogeometric analysis and machine learning-based stiffness modeling


Garg A., Shukla N. K., AVCAR M., Belarbi M., Zheng W., Raman R., ...Daha Fazla

Thin-Walled Structures, cilt.215, 2025 (SCI-Expanded, Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 215
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1016/j.tws.2025.113492
  • Dergi Adı: Thin-Walled Structures
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Communication Abstracts, Compendex, INSPEC, Metadex, Civil Engineering Abstracts
  • Anahtar Kelimeler: Bio-inspired laminates, Corrugated laminates, Isogeometric analysis, Machine learning, SHAP, Surrogate SVM
  • Süleyman Demirel Üniversitesi Adresli: Evet

Özet

This paper uses an isogeometric analysis-based shear deformation theory to present a comprehensive study on the free vibration behavior of annular and flat plates with sinusoidal corrugations, with and without holes. Inspired by helicoidal bio-inspired layup schemes, the study investigates the influence of layer orientation, hole location, and boundary conditions on the vibrational response of the plates. To address the complexities of accurately modeling the stiffness of corrugated plates, a machine learning approach based on Support Vector Machines (SVM) is utilized to predict the stiffness matrix efficiently and accurately. Furthermore, SHAP (SHapley Additive exPlanations) analysis is conducted to evaluate the relative importance of key parameters, such as layer orientation, hole location, and end conditions, on the free vibration behavior. The results reveal significant interactions between these parameters and highlight the role of helicoidal layups in enhancing the structural performance of corrugated plates. Comparative analyses are performed for plates with and without holes and the number of corrugations, demonstrating the influence of discontinuities on stiffness and vibrational characteristics. The integration of machine learning and SHAP analysis provides deeper insights into the critical design parameters governing the free vibration behavior of bio-inspired corrugated plates. This study advances the understanding of complex vibration phenomena in bio-inspired structures and offers a novel framework for designing lightweight, high-performance engineering systems with tailored vibrational properties.