NN‐mCRE: A modified constitutive relation error framework for unsupervised learning of nonlinear state laws with physics‐augmented neural networks
International Journal for Numerical Methods in Engineering · 30.04.2024 · 125 (8)
DOI: 10.1002/nme.7439 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal for Numerical Methods in Engineering, online erschienen am 25.01.2024. Verfasst von Antoine Benady und 2 weiteren Autor:innen. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: European Research Council.
Abstract (Originalsprache)
This article proposes a new approach to train physics‐augmented neural networks with observable data to represent mechanical constitutive laws. To train the neural network and learn thermodynamics potentials, the proposed method does not rely on strain‐stress or strain‐free energy pairs but needs only partial strain or displacement measurements inside the structure. The neural network is trained thanks to an unsupervised procedure in which the modified constitutive relation error (mCRE) is minimized. The mCRE functional provides a bias‐aware data assimilation framework with a rich physical sense as the constitutive relation error (CRE) part can be interpreted as a modeling error continuously defined over the structure, and can be used as a prediction quality in the inference phase. This article also extends previous works on the mCRE by introducing a new minimization procedure in the case of nonlinear state laws. As typical structural health monitoring applications may require that the neural networks should be trained online, an important focus is thus made on automatic and adaptive tuning of sensitive hyperparameters (learning rate, weighting between losses, number of epochs and initialization). It is shown that when the training database is rich enough with respect to the loading cases, the proposed method achieves remarkable performance regarding the quality of the learned model, noise robustness, and low sensitivity to user‐defined hyperparameters. The method is evaluated on two test cases: a non‐quadratic potential in the small strain regime with synthetic optic fiber measurements, and a Mooney–Rivlin model in the hyperelastic case with synthetic digital image correlation observations.
Förderung
- European Research Council
Zitieren
APA
Benady, A., Baranger, E., & Chamoin, L. (2024). NN‐mCRE: A modified constitutive relation error framework for unsupervised learning of nonlinear state laws with physics‐augmented neural networks. International Journal for Numerical Methods in Engineering, 125(8). https://doi.org/10.1002/nme.7439
Vancouver
Benady A, Baranger E, Chamoin L. NN‐mCRE: A modified constitutive relation error framework for unsupervised learning of nonlinear state laws with physics‐augmented neural networks. International Journal for Numerical Methods in Engineering. 2024;125(8). doi:10.1002/nme.7439
BibTeX
@article{Benady2024,
author = {Benady, Antoine and Baranger, Emmanuel and Chamoin, Ludovic},
title = {NN‐mCRE: A modified constitutive relation error framework for unsupervised learning of nonlinear state laws with physics‐augmented neural networks},
journal = {International Journal for Numerical Methods in Engineering},
year = {2024},
volume = {125},
number = {8},
doi = {10.1002/nme.7439}
}
EUVIMED