Article Dans Une Revue IFAC-PapersOnLine Année : 2022

Uncertainty quantification in a mechanical submodel driven by a Wasserstein-GAN

Hamza Boukraichi
Nissrine Akkari
  • Fonction : Auteur
Fabien Casenave
David Ryckelynck

Résumé

The analysis of parametric and non-parametric uncertainties of very large dynamical systems requires the construction of a stochastic model of said system. Linear approaches relying on random matrix theory Soize (2000) and principal component analysis can be used when systems undergo low-frequency vibrations. In the case of fast dynamics and wave propagation, we investigate a random generator of boundary conditions for fast submodels by using machine learning. We show that the use of non-linear techniques in machine learning and data-driven methods is highly relevant. Physics-informed neural networks Raissi et al. (2017) are a possible choice for a data-driven method to replace linear modal analysis. An architecture that supports a random component is necessary for the construction of the stochastic model of the physical system for non-parametric uncertainties, since the goal is to learn the underlying probabilistic distribution of uncertainty in the data. Generative Adversarial Networks (GANs) are suited for such applications, where the Wasserstein-GAN with gradient penalty variant Gulrajani et al. (2017) offers improved convergence results for our problem. The objective of our approach is to train a GAN on data from a finite element method code (Fenics) so as to extract stochastic boundary conditions for faster finite element predictions on a submodel. The submodel and the training data have both the same geometrical support. It is a zone of interest for uncertainty quantification and relevant to engineering purposes. In the exploitation phase, the framework can be viewed as a randomized and parametrized simulation generator on the submodel, which can be used as a Monte Carlo estimator.
Fichier principal
Vignette du fichier
2110.13680v1.pdf (1.93 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03853628 , version 1 (08-01-2025)

Identifiants

Citer

Hamza Boukraichi, Nissrine Akkari, Fabien Casenave, David Ryckelynck. Uncertainty quantification in a mechanical submodel driven by a Wasserstein-GAN. IFAC-PapersOnLine, 2022, 55 (20), pp.469-474. ⟨10.1016/j.ifacol.2022.09.139⟩. ⟨hal-03853628⟩
35 Consultations
0 Téléchargements

Altmetric

Partager

More