Finite element approximation of wave problems with correcting terms based on training artificial neural networks with fine solutions

DOI10.1016/J.CMA.2022.115280MaRDI QIDQ2674053zbMATH OpenOpenAlexWikidataFDO

Authors Arnau Fabra, Joan Baiges, Ramon Codina

Publication date 22 September 2022

Published in Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.cma.2022.115280

zbMATH Keywords

artificial neural networksleast squares trainingstabilized finite element methodswave equation

Mathematics Subject Classification ID

Finite element, Rayleigh-Ritz and Galerkin methods for initial value and initial-boundary value problems involving PDEs (65M60) Finite element methods applied to problems in fluid mechanics (76M10)

Recommendations

• Neural network model for solving integral equation of acoustic scattering using wavelet basis
• A phase shift deep neural network for high frequency approximation and wave problems
• Convolutional Neural Networks in Phase Space and Inverse Problems
• High dimensional finite elements for multiscale wave equations
• Finite neuron method and convergence analysis

Cites work

• A Helmholtz equation solver using unsupervised learning: application to transcranial ultrasound
• A Sommerfeld non-reflecting boundary condition for the wave equation in mixed form
• A variational multiscale method with subscales on the element boundaries for the Helmholtz equation
• Adaptive sparse grid model order reduction for fast Bayesian estimation and inversion
• Analysis of a stabilized finite element approximation of the Oseen equations using orthogonal subscales
• Certified reduced basis methods for parametrized partial differential equations
• Finite element analysis of acoustic scattering
• Finite element approximation of the hyperbolic wave equation in mixed form
• scientific article; zbMATH DE number 1748418 (Why is no real title available?)
• Multiscale phenomena: Green's functions, the Dirichlet-to-Neumann formulation, subgrid scale models, bubbles and the origins of stabilized methods
• Non-intrusive reduced order modeling of nonlinear problems using neural networks
• Numerical investigations of stabilized finite element computations for acoustics
• POD and CVT-based reduced-order modeling of Navier-Stokes flows
• Reduced-order subscales for POD models
• Review of model order reduction methods for numerical simulation of nonlinear circuits
• Stabilized finite element approximation of transient incompressible flows using orthogonal subscales
• The probability lifesaver: all the tools you need to understand chance
• The variational multiscale method -- a paradigm for computational mechanics

Cited in

(5)

• Approximation de calculs éléments finis par un nouveau réseau de neurones
• Artificial neural network based correction for reduced order models in computational fluid mechanics
• Accelerating high order discontinuous Galerkin solvers using neural networks: 3D compressible Navier-Stokes equations
• DNN-MG: a hybrid neural network/finite element method with applications to 3D simulations of the Navier-Stokes equations
• Deep learning in computational mechanics: a review

Describes a project that uses

Uses Software

• redbKIT
• FANN
• GitHub

This page was built for publication: Finite element approximation of wave problems with correcting terms based on training artificial neural networks with fine solutions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2674053)