Fusing nonlinear solvers with transformers for accelerating the solution of parametric transient problems

DOI10.1016/J.CMA.2024.117074MaRDI QIDQ6566042zbMATH OpenFDO

Authors Leonidas Papadopoulos, Konstantinos Atzarakis, Gerasimos Sotiropoulos, Ioannis Kalogeris, V. Papadopoulos

Publication date 3 July 2024

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

zbMATH Keywords

deep learningtime series forecastingnonlinear dynamicstransformers

Mathematics Subject Classification ID

Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30)

Recommendations

• AI‐enhanced iterative solvers for accelerating the solution of large‐scale parametrized systems
• A hybrid numerical methodology coupling reduced order modeling and graph neural networks for non-parametric geometries: applications to structural dynamics problems
• Non-intrusive parametric hyper-reduction for nonlinear structural finite element formulations
• Parametric model reduction with convolutional neural networks

Cites work

• A GRU-based ensemble learning method for time-variant uncertain structural response analysis
• A radial basis function method for global optimization
• AI‐enhanced iterative solvers for accelerating the solution of large‐scale parametrized systems
• Computational mechanics enhanced by deep learning
• Data-driven surrogates for high dimensional models using Gaussian process regression on the Grassmann manifold
• Design and analysis of computer experiments. With comments and a rejoinder by the authors
• Hierarchical deep learning neural network (HiDeNN): an artificial intelligence (AI) framework for computational science and engineering
• Krylov-subspace recycling via the POD-augmented conjugate-gradient method
• Machine learning-combined topology optimization for functionary graded composite structure design
• Recurrent neural networks (RNNs) with dimensionality reduction and break down in computational mechanics; application to multi-scale localization step
• Smart finite elements: a novel machine learning application
• Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition
• Surrogate modeling of high-dimensional problems via data-driven polynomial chaos expansions and sparse partial least square
• The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations
• Turbulence modeling in the age of data

This page was built for publication: Fusing nonlinear solvers with transformers for accelerating the solution of parametric transient problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6566042)