A new design method to account for interlaminar stresses in laminated composites using machine learning

Gadinger M, Deutschmann T, Krause D, Wartzack S (2025)


Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2025

Publisher: Cambridge University Press

Book Volume: 5

Pages Range: 209 - 218

Conference Proceedings Title: Proceedings of the Design Society: Volume 5: ICED25

DOI: 10.1017/pds.2025.10035

Open Access Link: https://doi.org/10.1017/pds.2025.10035

Abstract

Lightweight design is critical for improving the efficiency and sustainability of engineering applications. Laminated composites, with their high strength-to-weight ratio and tailored material properties, play a key role but introduce interlaminar stresses, particularly near free edges where delamination failures often occur. Addressing these stresses typically requires computationally expensive 3D finite element simulations, limiting their use in early design stages. This study presents a machine learning approach using Gaussian process regression and artificial neural networks to efficiently predict interlaminar stresses based on in-plane stress data from shell FE simulations. Achieving high predictive accuracy, this method enables cost-effective, early-stage composite design optimization under complex loading scenarios.

Authors with CRIS profile

How to cite

APA:

Gadinger, M., Deutschmann, T., Krause, D., & Wartzack, S. (2025). A new design method to account for interlaminar stresses in laminated composites using machine learning. In Proceedings of the Design Society: Volume 5: ICED25 (pp. 209 - 218). Cambridge University Press.

MLA:

Gadinger, Marc, et al. "A new design method to account for interlaminar stresses in laminated composites using machine learning." Proceedings of the Proceedings of the Design Society: Volume 5: ICED25 Cambridge University Press, 2025. 209 - 218.

BibTeX: Download