Predictive modeling of buckling in composite tubes: Integrating artificial neural networks for damage detection

Abstract

Tubular structural composites are widely used in applications where high stiffness and low weight are required. This work proposes the study and evaluation of the influence of damage on the structural responses of thin-walled structures made of composite materials, as well as the development of a buckling prediction model using artificial intelligence. The methodology is approached on a few main fronts, namely: i) numerical modeling of the direct problem of the structure in finite elements, ii) modeling and parameterization of delamination in the elliptical shell model; iii) obtaining a database through finite element updating and iv) formulation and construction of the regression and prediction model using artificial neural networks. The numerical results showed that, as expected, the presence of delamination has a significant impact on the occurrence of buckling. The study also showed that it is possible to predict buckling values, with extremely satisfactory results - an error of around 1%, provided that more complex regression methods are used, such as regression by artificial neural networks, since the relationship between damage and buckling values is not trivial.

Keywords:

• Structural damage
• finite elements
• buckling
• artificial intelligence
• composite material

Acknowledgments

The authors would like to acknowledge the financial support from the Brazilian agency CNPq (Conselho Nacional de Desenvolvimento Científico e Tecnológico - 405598/2022-0), CAPES (Coordenacão de Aperfeicoamento de Pessoal de Nível Superior) and FAPEMIG (Fundação de Amparo à Pesquisa do Estado de Minas Gerais - APQ-00062-24).

Data availability

The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.

Disclosure statement

The authors declare that they have no conflict of interest.