Free vibration behaviour of curved Miura-folded bio-inspired helicoidal laminated composite cylindrical shells using HSDT assisted by machine learning-based IGA
Composite Structures, cilt.357, 2025 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 357
- Basım Tarihi: 2025
- Doi Numarası: 10.1016/j.compstruct.2025.118933
- Dergi Adı: Composite Structures
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Chimica, Communication Abstracts, Compendex, INSPEC, Metadex, Civil Engineering Abstracts
- Anahtar Kelimeler: Bio-inspired shells, Free vibration, Isogeometric analysis, Machine learning, Miura-fold, Origami-inspired structures
- Süleyman Demirel Üniversitesi Adresli: Evet
Özet
Deployable structures, which can be compacted into small spaces and later deployed into their desired configurations, have gained significant attention due to their versatility. Origami-inspired structures, in particular, leverage the principles of origami to achieve compactness and deploy ability. This study focuses on predicting the free vibration behaviour of Miura-folded laminated composite cylindrical shells, which are modelled using bio-inspired helicoidal schemes. The analysis is conducted through isogeometric analysis (IGA) based on higher-order shear deformation theory (HSDT). A Gaussian Process Regression (GPR) machine learning surrogate is employed to predict the IGA parameters, specifically the knot vectors, which are used to accurately model the geometry of the shells. The performance of the proposed approach is validated by comparing the results with those obtained without the surrogate model. The findings of this study serve as a benchmark for future research on the free vibration behaviour of origami-inspired cylindrical shells and highlight the potential of using machine learning surrogates in structural analysis.