Convolutional Autoencoders, Clustering and POD for Low-dimensional Parametrization of Navier-Stokes Equations

02/02/2023

∙

Simulations of large-scale dynamical systems require expensive computations. Low-dimensional parametrization of high-dimensional states such as Proper Orthogonal Decomposition (POD) can be a solution to lessen the burdens by providing a certain compromise between accuracy and model complexity. However, for really low-dimensional parametrizations (for example for controller design) linear methods like the POD come to their natural limits so that nonlinear approaches will be the methods of choice. In this work we propose a convolutional autoencoder (CAE) consisting of a nonlinear encoder and an affine linear decoder and consider combinations with k-means clustering for improved encoding performance. The proposed set of methods is compared to the standard POD approach in two cylinder-wake scenarios modeled by the incompressible Navier-Stokes equations.

READ FULL TEXT

Convolutional Autoencoders, Clustering and POD for Low-dimensional Parametrization of Navier-Stokes Equations

Low-complexity linear parameter-varying approximations of incompressible Navier-Stokes equations for truncated state-dependent Riccati feedback

Learning low-dimensional feature dynamics using deep convolutional recurrent autoencoders

Non-intrusive reduced-order modeling using convolutional autoencoders

Learning a Low-dimensional Representation of a Safe Region for Safe Reinforcement Learning on Dynamical Systems

Error analysis of proper orthogonal decomposition data assimilation schemes for the Navier-Stokes equations

Model reduction in Smoluchowski-type equations

Investigation of Nonlinear Model Order Reduction of the Quasigeostrophic Equations through a Physics-Informed Convolutional Autoencoder

Convolutional Autoencoders, Clustering and POD for Low-dimensional Parametrization of Navier-Stokes Equations

Related Research

Low-complexity linear parameter-varying approximations of incompressible Navier-Stokes equations for truncated state-dependent Riccati feedback

Learning low-dimensional feature dynamics using deep convolutional recurrent autoencoders

Non-intrusive reduced-order modeling using convolutional autoencoders

Learning a Low-dimensional Representation of a Safe Region for Safe Reinforcement Learning on Dynamical Systems

Error analysis of proper orthogonal decomposition data assimilation schemes for the Navier-Stokes equations

Model reduction in Smoluchowski-type equations

Investigation of Nonlinear Model Order Reduction of the Quasigeostrophic Equations through a Physics-Informed Convolutional Autoencoder