تقرير
Uncertainty quantification in a mechanical submodel driven by a Wasserstein-GAN
| العنوان: | Uncertainty quantification in a mechanical submodel driven by a Wasserstein-GAN |
|---|---|
| المؤلفون: | Boukraichi, Hamza, Akkari, Nissrine, Casenave, Fabien, Ryckelynck, David |
| المصدر: | IFAC PAPERSONLINE, 55(20), 469-474, (2022) |
| سنة النشر: | 2021 |
| المجموعة: | Computer Science Statistics |
| مصطلحات موضوعية: | Statistics - Machine Learning, Computer Science - Machine Learning, 68T07 (Primary) 35L05 (Secondary), G.3, G.1.8 |
| الوصف: | 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 and principal componant 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 is a possible choice for a data-driven method to replace linear modal analysis. An architecture that support 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 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. |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1016/j.ifacol.2022.09.139 |
| URL الوصول: | http://arxiv.org/abs/2110.13680 |
| رقم الأكسشن: | edsarx.2110.13680 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1016/j.ifacol.2022.09.139 |
|---|