Nonlinear reduced-order modeling for three-dimensional turbulent flow by large-scale machine learning
From MaRDI portal
Publication:6060754
DOI10.1016/j.compfluid.2023.106047MaRDI QIDQ6060754
Keiji Onishi, Akiyoshi Kuroda, Makoto Tsubokura, Rahul Bale, Kazuto Ando
Publication date: 4 November 2023
Published in: Computers and Fluids (Search for Journal in Brave)
turbulencereduced-order modelconvolutional autoencoder (CAE)distributed machine learninglong short-term memory (LSTM) networksthree-dimensional flow field
Cites Work
- Unnamed Item
- Unnamed Item
- A unified mathematical framework and an adaptive numerical method for fluid-structure interaction with rigid, deforming, and elastic bodies
- An `empirical interpolation' method: Application to efficient reduced-basis discretization of partial differential equations
- Topology-free immersed boundary method for incompressible turbulence flows: an aerodynamic simulation for ``dirty CAD geometry
- Time-series learning of latent-space dynamics for reduced-order model closure
- Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
- Parametric non-intrusive model order reduction for flow-fields using unsupervised machine learning
- Nonlinear normal modes and spectral submanifolds: existence, uniqueness and use in model reduction
- Über die beste Annäherung von Funktionen einer gegebenen Funktionenklasse
- Efficient non-linear model reduction via a least-squares Petrov-Galerkin projection and compressive tensor approximations
- Reducing the Dimensionality of Data with Neural Networks
- The immersed boundary method
- Building-Cube Method for Flow Problems with Broadband Characteristic Length
- Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
- Eulerian finite volume formulation using Lagrangian marker particles for incompressible fluid–structure interaction problems
