Prediction of the buckling mode of cylindrical composite shells with imperfections using FEM-based deep learning approach

Abstract

This study introduces a new method for predicting buckling modes in cylindrical composite shells using a deep learning approach based on finite element method (FEM). The study used carbon fiber woven prepreg material and collected 520 data sets through an Abaqus-Python program. A deep neural network was trained using FEM results to accurately predict the buckling mode of cylindrical composite shells with imperfections. The study employed a generative adversarial network and the pix2pix deep learning algorithm in the prediction process. The deep learning model achieved a similar level of prediction accuracy as traditional FEM, but was much more efficient. The study also utilized logistic regression to examine the relationship between input variables and buckling modes. The research shows the potential of the FEM-based deep learning approach to improve the efficiency of buckling mode prediction in cylindrical composite shells, which is critical for their design and safety.

Keywords:

• Cylindrical composite shell
• imperfections
• finite element analysis
• deep learning: generative adversarial network

Acknowledgements

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2022R1I1A2055690). This paper was also supported by Konkuk University Researcher Fund in 2022. The authors are grateful for the financial support.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Correction Statement

This article has been republished with minor changes. These changes do not impact the academic content of the article.

Additional information

Funding

The work was supported by the National Research Foundation of Korea [NRF-2022R1I1A2055690]. This paper was also supported by Konkuk University Researcher Fund in 2022.