Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209243383> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W3209243383 endingPage "474" @default.
- W3209243383 startingPage "469" @default.
- W3209243383 abstract "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." @default.
- W3209243383 created "2021-11-08" @default.
- W3209243383 creator A5056477280 @default.
- W3209243383 creator A5063653501 @default.
- W3209243383 creator A5066019849 @default.
- W3209243383 creator A5086924340 @default.
- W3209243383 date "2022-01-01" @default.
- W3209243383 modified "2023-09-30" @default.
- W3209243383 title "Uncertainty quantification in a mechanical submodel driven by a Wasserstein-GAN" @default.
- W3209243383 cites W1988859494 @default.
- W3209243383 cites W2003028731 @default.
- W3209243383 cites W2054261748 @default.
- W3209243383 cites W2120270890 @default.
- W3209243383 cites W2563263390 @default.
- W3209243383 cites W2899283552 @default.
- W3209243383 cites W2900369848 @default.
- W3209243383 cites W3006111637 @default.
- W3209243383 cites W3040708241 @default.
- W3209243383 doi "https://doi.org/10.1016/j.ifacol.2022.09.139" @default.
- W3209243383 hasPublicationYear "2022" @default.
- W3209243383 type Work @default.
- W3209243383 sameAs 3209243383 @default.
- W3209243383 citedByCount "1" @default.
- W3209243383 countsByYear W32092433832023 @default.
- W3209243383 crossrefType "journal-article" @default.
- W3209243383 hasAuthorship W3209243383A5056477280 @default.
- W3209243383 hasAuthorship W3209243383A5063653501 @default.
- W3209243383 hasAuthorship W3209243383A5066019849 @default.
- W3209243383 hasAuthorship W3209243383A5086924340 @default.
- W3209243383 hasBestOaLocation W32092433831 @default.
- W3209243383 hasConcept C105795698 @default.
- W3209243383 hasConcept C11413529 @default.
- W3209243383 hasConcept C117251300 @default.
- W3209243383 hasConcept C119857082 @default.
- W3209243383 hasConcept C121332964 @default.
- W3209243383 hasConcept C126255220 @default.
- W3209243383 hasConcept C127413603 @default.
- W3209243383 hasConcept C135628077 @default.
- W3209243383 hasConcept C154945302 @default.
- W3209243383 hasConcept C158693339 @default.
- W3209243383 hasConcept C163258240 @default.
- W3209243383 hasConcept C168167062 @default.
- W3209243383 hasConcept C2780992000 @default.
- W3209243383 hasConcept C32230216 @default.
- W3209243383 hasConcept C33923547 @default.
- W3209243383 hasConcept C41008148 @default.
- W3209243383 hasConcept C49937458 @default.
- W3209243383 hasConcept C62520636 @default.
- W3209243383 hasConcept C66938386 @default.
- W3209243383 hasConcept C97355855 @default.
- W3209243383 hasConceptScore W3209243383C105795698 @default.
- W3209243383 hasConceptScore W3209243383C11413529 @default.
- W3209243383 hasConceptScore W3209243383C117251300 @default.
- W3209243383 hasConceptScore W3209243383C119857082 @default.
- W3209243383 hasConceptScore W3209243383C121332964 @default.
- W3209243383 hasConceptScore W3209243383C126255220 @default.
- W3209243383 hasConceptScore W3209243383C127413603 @default.
- W3209243383 hasConceptScore W3209243383C135628077 @default.
- W3209243383 hasConceptScore W3209243383C154945302 @default.
- W3209243383 hasConceptScore W3209243383C158693339 @default.
- W3209243383 hasConceptScore W3209243383C163258240 @default.
- W3209243383 hasConceptScore W3209243383C168167062 @default.
- W3209243383 hasConceptScore W3209243383C2780992000 @default.
- W3209243383 hasConceptScore W3209243383C32230216 @default.
- W3209243383 hasConceptScore W3209243383C33923547 @default.
- W3209243383 hasConceptScore W3209243383C41008148 @default.
- W3209243383 hasConceptScore W3209243383C49937458 @default.
- W3209243383 hasConceptScore W3209243383C62520636 @default.
- W3209243383 hasConceptScore W3209243383C66938386 @default.
- W3209243383 hasConceptScore W3209243383C97355855 @default.
- W3209243383 hasIssue "20" @default.
- W3209243383 hasLocation W32092433831 @default.
- W3209243383 hasLocation W32092433832 @default.
- W3209243383 hasLocation W32092433833 @default.
- W3209243383 hasLocation W32092433834 @default.
- W3209243383 hasOpenAccess W3209243383 @default.
- W3209243383 hasPrimaryLocation W32092433831 @default.
- W3209243383 hasRelatedWork W1966994088 @default.
- W3209243383 hasRelatedWork W2102319274 @default.
- W3209243383 hasRelatedWork W2116008045 @default.
- W3209243383 hasRelatedWork W2359118882 @default.
- W3209243383 hasRelatedWork W2360796461 @default.
- W3209243383 hasRelatedWork W2379533788 @default.
- W3209243383 hasRelatedWork W2390459957 @default.
- W3209243383 hasRelatedWork W2621866652 @default.
- W3209243383 hasRelatedWork W2971445050 @default.
- W3209243383 hasRelatedWork W4290792893 @default.
- W3209243383 hasVolume "55" @default.
- W3209243383 isParatext "false" @default.
- W3209243383 isRetracted "false" @default.
- W3209243383 magId "3209243383" @default.
- W3209243383 workType "article" @default.