Rapidly predicting the effect of tool geometry on the wrinkling of biaxial NCFs during composites manufacturing using a deep learning surrogate model

Viisainen, J.V.; Yu, F.; Codolini, A.; Chen, S.; Harper, L.T.; Sutcliffe, M.P.F.

Abstract

A deep learning surrogate model is developed to rapidly predict the wrinkling patterns of a biaxial non-crimp fabric (NCF) layup for any given tool geometry during forming. The underlying dataset of finite element simulations is used to investigate the effect of tool geometry on wrinkling severity. The trained surrogate model is able to make reliable predictions of wrinkling patterns at a very low computational cost, suitable for tool design optimisation. Results indicate that certain geometrical features have a greater impact on wrinkling than others. In particular, forming NCFs over geometries with greater draft angles tends to result in smaller wrinkles.

Citation

Viisainen, J., Yu, F., Codolini, A., Chen, S., Harper, L., & Sutcliffe, M. (2023). Rapidly predicting the effect of tool geometry on the wrinkling of biaxial NCFs during composites manufacturing using a deep learning surrogate model. Composites Part B: Engineering, 253, Article 110536. https://doi.org/10.1016/j.compositesb.2023.110536

• Journal Article Type: Article
• Acceptance Date: Jan 18, 2023
• Online Publication Date: Jan 21, 2023
• Publication Date: Mar 15, 2023
• Deposit Date: Jan 31, 2023
• Publicly Available Date: Feb 2, 2023
• Journal: Composites Part B: Engineering
• Print ISSN: 1359-8368
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 253
• Article Number: 110536
• DOI: https://doi.org/10.1016/j.compositesb.2023.110536
• Keywords: Industrial and Manufacturing Engineering; Mechanical Engineering; Mechanics of Materials; Ceramics and Composites
• Public URL: https://nottingham-repository.worktribe.com/output/16506980
• Publisher URL: https://www.sciencedirect.com/science/article/pii/S1359836823000392?via%3Dihub