Parametric non-intrusive model order reduction for flow-fields using unsupervised machine learning

DOI10.1016/j.cma.2021.113999OpenAlexW3174363380MaRDI QIDQ2237497

SiHun Lee, Haedong Kim, Kijoo Jang, Haeseong Cho, Sangjoon Shin

Publication date: 27 October 2021

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.2021.113999

zbMATH Keywords

proper orthogonal decompositionmachine learninggenerative adversarial networknon-intrusive model order reductionparameterized object

Mathematics Subject Classification ID

Spectral methods applied to problems in fluid mechanics (76M22) Finite element methods applied to problems in fluid mechanics (76M10) Applications to the sciences (65Z05)

Related Items (5)

Proper orthogonal decomposition and physical field reconstruction with artificial neural networks (ANN) for supercritical flow problems ⋮ Neural-network learning of SPOD latent dynamics ⋮ Nonlinear reduced-order modeling for three-dimensional turbulent flow by large-scale machine learning ⋮ Parametric reduced-order modeling enhancement for a geometrically imperfect component via hyper-reduction ⋮ Parametric dynamic mode decomposition for reduced order modeling

Uses Software

• darch
• Wasserstein GAN

Cites Work

• Unnamed Item
• Calibrated reduced-order POD-Galerkin system for fluid flow modelling
• Stable Galerkin reduced-order models for linearized compressible flow
• Stability properties of POD-Galerkin approximations for the compressible Navier-Stokes equations
• Krylov subspace techniques for reduced-order modeling of large-scale dynamical systems
• Model reduction for compressible flows using POD and Galerkin projection
• Reduced order modeling for nonlinear structural analysis using Gaussian process regression
• Error estimation of the parametric non-intrusive reduced order model using machine learning
• Multi-level convolutional autoencoder networks for parametric prediction of spatio-temporal dynamics
• Time-series learning of latent-space dynamics for reduced-order model closure
• Non-intrusive reduced order modeling of unsteady flows using artificial neural networks with application to a combustion problem
• A parameterized non-intrusive reduced order model and error analysis for general time-dependent nonlinear partial differential equations and its applications
• Reducing the Dimensionality of Data with Neural Networks
• An Online Method for Interpolating Linear Parametric Reduced-Order Models
• A method for interpolating on manifolds structural dynamics reduced-order models
• The Reduced Basis Method for Incompressible Viscous Flow Calculations
• Turbulence and the dynamics of coherent structures. I. Coherent structures
• Principal component analysis in linear systems: Controllability, observability, and model reduction
• A reduced-order approach for optimal control of fluids using proper orthogonal decomposition
• MODEL REDUCTION FOR FLUIDS, USING BALANCED PROPER ORTHOGONAL DECOMPOSITION

This page was built for publication: Parametric non-intrusive model order reduction for flow-fields using unsupervised machine learning