Reduced-order modeling for stochastic large-scale and time-dependent flow problems using deep spatial and temporal convolutional autoencoders

A non-intrusive reduced-order model based on convolutional autoencoders is proposed as a data-driven tool to build an efficient nonlinear reduced-order model for stochastic spatiotemporal large-scale flow problems. The objective is to perform accurate and rapid uncertainty analyses of the flow outpu...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Advanced modeling and simulation in engineering sciences Ročník 10; číslo 1; s. 7 - 27
Hlavní autoři:	Abdedou, Azzedine, Soulaimani, Azzeddine
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Cham Springer International Publishing 19.05.2023 Springer Nature B.V Springer SpringerOpen
Témata:	Accuracy Artificial neural networks Classical and Continuum Physics Computational Science and Engineering Convolutional autoencoders Deep learning Engineering Engineering Sciences Finite element method Mathematical models Multilayer perceptrons Parameter uncertainty Partial differential equations Proper Orthogonal Decomposition Reduced order models Reduced-order modeling Research Article Solvers Statistical analysis Theoretical and Applied Mechanics Time compression Time dependence Uncertainty analysis Uncertainty propagation Deep learning Uncertainty propagation Convolutional autoencoders Reduced-order modeling
ISSN:	2213-7467, 2213-7467
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!