Towards DIC-Subset-Independent Machine Learning Models for Constitutive Parameter Identification in Sheet Metal Forming

Article Preview

Abstract:

Machine learning (ML) algorithms have been studied in literature as an inverse method to predict material constitutive parameters. However, these approaches are often dependent on the mesh discretisation settings applied during numerical simulations, and then difficulty model adaptation to experimental digital image correlation (DIC) subsets. Although a recent study explores the use of an interpolation-based approach to achieve experimental adaptation from numerically-based trained ML models, the proposed methodology lacks evaluation using experimental data. As a follow-up, this study proposes a new evaluation approach. Numerical data is DIC-levelled via MatchID software and then submitted to interpolation. An XGBoost algorithm is then trained on interpolated DIC data and evaluated for parameter prediction, comparing the obtained results with those obtained from the model trained on interpolated numerical data. Overall, the proposed DIC-levelling and interpolation pipeline yields an excellent predictive performance, with results comparable to those obtained when training on interpolated numerical data. The largest deviations are observed for the hardening exponent, while the remaining parameters are predicted with consistently high accuracy. These findings validate the practical applicability of the interpolation-based strategy to reduce the subset scheme dependency of ML models trained on real experimental data.

You have full access to the following eBook

Info:

* - Corresponding Author

[1] P. Böhringer et al., "A strategy to train machine learning material models for finite element simulations on data acquirable from physical experiments," Computer Methods in Applied Mechanics and Engineering, vol. 406, p.115894, Mar. 2023, doi: doi.org/.

DOI: 10.1016/j.cma.2023.115894

Google Scholar

[2] J. Kim, A. S. Ebrahim, B. L. Kinsey, and J. Ha, "Identification of Yld2000–2d anisotropic yield function parameters from single hole expansion test using machine learning," CIRP Annals, vol. 73, no. 1, p.233–236, Jan. 2024, doi: doi.org/.

DOI: 10.1016/j.cirp.2024.04.026

Google Scholar

[3] N. Bastos, P. A. Prates, and A. Andrade-Campos, "Material Parameter Identification of Elastoplastic Constitutive Models Using Machine Learning Approaches," Key Engineering Materials, vol. 926, p.2193–2200, Jul. 2022, doi: doi.org/.

DOI: 10.4028/p-zr575d

Google Scholar

[4] D. Mitreiro, P. A. Prates, and A. Andrade-Campos, "Reducing mesh dependency in dataset generation for machine learning prediction of constitutive parameters in sheet metal forming," Metals, vol. 15, no. 5, p.534, 2025.

DOI: 10.3390/met15050534

Google Scholar

[5] Dassault Systèmes. Abaqus 2016 Analysis User's Guide (Vols. 1–5). Providence, RI: Dassault Systèmes Simulia Corp., 2016.

Google Scholar

[6] R. Hill, E. Orowan, "A theory of the yielding and plastic flow of anisotropic metals," Proc. R. Soc. Lond. Ser. A, vol. 193, no. 1033, p.281–297, 1948.

DOI: 10.1098/rspa.1948.0045

Google Scholar

[7] H. W. Swift, "Plastic instability under plane stress," Journal of the Mechanics and Physics of Solids, vol. 1, no. 1, p.1–18, Oct. 1952.

DOI: 10.1016/0022-5096(52)90002-1

Google Scholar