Paper Titles
AI-Driven Design and Optimization of Bending Processes
p.65
Hybrid Numerical and Data-Driven Modelling for Defect Prediction in Screw Press Hot Bulk Forging of the En AW-6060 Part
p.75
Machine Learning Algorithms Applied to the Identification of CPB06 Yield Criterion Parameters
p.89
Geometry-Based Concept for Automatic Cut Planning and Flattening of Sheet Metal Components
p.99
Towards Single-Test Anisotropy Calibration: Sensitivity, Identifiability and Validation of YLD2000-2d
p.107
Towards DIC-Subset-Independent Machine Learning Models for Constitutive Parameter Identification in Sheet Metal Forming
p.115
Application of Reference-Free Strain Measurement to Assess the Deformation Level of Pre-Deformed Components
p.123
Improving FEMU Calibration from a Single Heterogeneous Test through a Data-Driven Approach: An Exploratory Study
p.131
Robust Performance Optimization Using Bayesian Optimization and Extreme Value Theory
p.141

Improving FEMU Calibration from a Single Heterogeneous Test through a Data-Driven Approach: An Exploratory Study

Article Preview
View Pdf By email

Abstract:

Inverse identification of material parameters from experimental data is a long-standing challenge, especially when calibrating complex constitutive models characterized by a large number of parameters. Heterogeneous mechanical tests combined with full-field measurements provide a large amount of information for material parameter identification but lead to high computational costs when used within a Finite Element Model Updating (FEMU) framework. This work presents an exploratory study on the use of surrogate-assisted Bayesian optimization to assess its potential for reducing the number of simulations required for FEMU-based calibration using data from a single notched tensile test. FEMU cost function is applied based on the discrepancy between experimental and numerical strain fields. A Gaussian Process surrogate model is iteratively constructed, and new sets of material parameters are selected using an Expected Improvement criterion. The results are discussed in terms of convergence behaviour and optimization efficiency, providing insight into the suitability of Bayesian optimization for solving inverse identification problems.

You have full access to the following eBook
Lionel Fourment on: Optimization, AI and Inverse Analysis in Forming Read eBook

Info:

Periodical:

Key Engineering Materials (Volume 1049)

Pages:

131-139

DOI:

https://doi.org/10.4028/p-QE9aTP

Citation:

Cite this paper

Online since:

April 2026

Authors:

Mafalda Gonçalves*, Rui Amaral, Sandrine Thuillier, António Andrade-Campos

Keywords:

Data-Driven, FEMU, Heterogeneous Test, Material Testing 2.0

Export:

RIS, BibTeX

Permissions:

Creative Commons CC BY 4.0

Share:

Citation:

* - Corresponding Author

References

[1] M. Gonçalves, S. Thuillier, A. Andrade-Campos, Assessing the potential of heterogeneous mechanical tests for sheet metals through experimentally measured full-fields, Exp. Mech. 65 (2025) 757–774.

DOI: 10.1007/s11340-025-01168-z

Google Scholar

[2] M. Gonçalves, S. Thuillier, A. Andrade-Campos, Inverse identification of anisotropic plasticity model parameters using FEMU and a heterogeneous test, Mater. Res. Proc. 54 (2025) 1548–1557.

DOI: 10.21741/9781644903599-167

Google Scholar

[3] L. Germain, M. Gonçalves, T. Barret, A. Andrade-Campos, S. Thuillier, Virtual forming based on model calibration from heterogeneous tests, Mater. Res. Proc. 54 (2025) 1568–1576.

DOI: 10.21741/9781644903599-169

Google Scholar

[4] J.M.P. Martins, A. Andrade-Campos, S. Thuillier, Comparison of inverse identification strategies for constitutive mechanical models using full-field measurements, Int. J. Mech. Sci. 145 (2018) 330–345.

DOI: 10.1016/j.ijmecsci.2018.07.013

Google Scholar

[5] A.E. Marques, T.G. Parreira, A.F.G. Pereira, Machine learning application to the identification of sheet metal constitutive model parameters, Mach. Learn. Comput. Sci. Eng. 1 (2025) 10.

DOI: 10.1007/s44379-024-00006-8

Google Scholar

[6] T.G. Parreira, A.E. Marques, N.A. Sakharova, P.A. Prates, A.F.G. Pereira, Identification of sheet metal constitutive parameters using metamodeling of the biaxial tensile test on a cruciform specimen, Metals 14 (2024) 212.

DOI: 10.3390/met14020212

Google Scholar

[7] R.P. Cardoso Coelho, A.F.C. Alves, F.M. Andrade Pires, Efficient constitutive parameter identification through optimisation-based techniques: A comparative analysis and novel composite Bayesian optimisation strategy, Comput. Methods Appl. Mech. Eng. 427 (2024) 117039.

DOI: 10.1016/j.cma.2024.117039

Google Scholar

[8] J. Kuhn, J. Spitz, P. Sonnweber-Ribic, et al., Identifying material parameters in crystal plasticity by Bayesian optimization, Optim. Eng. 23 (2022) 1489–1523.

DOI: 10.1007/s11081-021-09663-7

Google Scholar

[9] T. Long, L. Wang, C. Kan, J.D. Lee, A Novel Approach for Modelling Strain Hardening in Plasticity and Its Material Parameter Identification by Bayesian Optimization for Automotive Structural Steels Application. Applied Math 5 (2025), 104.

DOI: 10.3390/appliedmath5030104

Google Scholar

[10] A. Vlachas, E. Chatzi, J.F. Unger, A Bayesian framework for constitutive model identification via use of full field measurements, with application to heterogeneous materials, Comp. Methods in Appl. Mech. Eng. 433 (2025), 117489.

DOI: 10.1016/j.cma.2024.117489

Google Scholar

[11] M. Rossi, F. Pierron, and M. Štamborská, Application of the virtual fields method to large strain anisotropic plasticity, Int. J. Solids Struct., 97-98, (2016) 322–335.

DOI: 10.1016/j.ijsolstr.2016.07.015

Google Scholar

[12] Y. Wang, T.-Y. Chen, and D.G. Vlachos, NEXTorch: A Design and Bayesian Optimization Toolkit for Chemical Sciences and Engineering, J. Chem. Inf. Model. 61 (2021) 5312-5319.

DOI: 10.1021/acs.jcim.1c00637

Google Scholar