Influence of data filtering and noise on the calibration of constitutive models using machine learning techniques

–

Influence of data filtering and noise on the calibration of constitutive models using machine learning techniques

PRATES Pedro, PINTO José, MARQUES João, HENRIQUES João, PEREIRA André, ANDRADE-CAMPOS António

Abstract. This work focuses on predicting material parameters that describe the plastic behaviour of metallic sheets using the XGBoost machine learning algorithm, with a dual focus on the influence of data filtering and data noise. A dataset was populated with finite element simulation results of cruciform tensile tests, including strain field data during the test. Different noise levels were added to the strain-related features of the dataset; additionally, a feature importance study was carried out to identify and select the most relevant features of the dataset. A systematic analysis shows how feature noise and selection individually and simultaneously influence the predictive performance of machine learning models. The results show that feature selection will greatly accelerate model training, without losing its predictive performance. Also, adding noise to the features does not have significant impact on model performance, highlighting the robustness of the models.

Keywords
Parameter Identification, Machine Learning, Feature Analysis, Noise, Sheet Metal Forming

Published online 4/24/2024, 10 pages
Copyright © 2024 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA

Citation: PRATES Pedro, PINTO José, MARQUES João, HENRIQUES João, PEREIRA André, ANDRADE-CAMPOS António, Influence of data filtering and noise on the calibration of constitutive models using machine learning techniques, Materials Research Proceedings, Vol. 41, pp 1807-1816, 2024

DOI: https://doi.org/10.21741/9781644903131-200

The article was published as article 200 of the book Material Forming

Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.

References
[1] A. Andrade-Campos, N. Bastos, M. Conde, M. Gonçalves, J. Henriques, R. Lourenço, J.M.P. Martins, M.G. Oliveira, P. Prates, L. Rumor, On the inverse identification methods for forming plasticity models using full-field measurements, IOP Conf. Ser. Mater. Sci. Eng. 1238 (2022) 012059. https://doi.org/10.1088/1757-899X/1238/1/012059
[2] P.A. Prates, J.D. Henriques, J. Pinto, N. Bastos, A. Andrade-Campos, Coupling machine learning and synthetic image DIC-based techniques for the calibration of elastoplastic constitutive models, Mater. Res. Proc. 28 (2023) 1193-1202. https://doi.org/10.21741/9781644902479-130
[3] J. Martins, A. Andrade-Campos, and S. Thuillier, Calibration of anisotropic plasticity models using a biaxial test and the virtual fields method, Int. J. Solids Struct. 172 (2019) 21–37. https://doi.org/10.1016/j.ijsolstr.2019.05.019
[4] Dassault Systèmes. Abaqus 2017 documentation, 2017.
[5] T. Chen and C. Guestrin, XGBoost: A scalable tree boosting system, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016) 785–794. https://doi.org/10.1145/2939672.2939785
[6] S. Lundberg and S. Lee, “A Unified Approach to Interpreting Model Predictions”, 2017.