Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
From MaRDI portal
Publication:5154682
Abstract: We perform a sparse identification of nonlinear dynamics (SINDy) for low-dimensionalized complex flow phenomena. We first apply the SINDy with two regression methods, the thresholded least square algorithm (TLSA) and the adaptive Lasso (Alasso) which show reasonable ability with a wide range of sparsity constant in our preliminary tests, to a two-dimensional single cylinder wake at , its transient process, and a wake of two-parallel cylinders, as examples of high-dimensional fluid data. To handle these high dimensional data with SINDy whose library matrix is suitable for low-dimensional variable combinations, a convolutional neural network-based autoencoder (CNN-AE) is utilized. The CNN-AE is employed to map a high-dimensional dynamics into a low-dimensional latent space. The SINDy then seeks a governing equation of the mapped low-dimensional latent vector. Temporal evolution of high-dimensional dynamics can be provided by combining the predicted latent vector by SINDy with the CNN decoder which can remap the low-dimensional latent vector to the original dimension. The SINDy can provide a stable solution as the governing equation of the latent dynamics and the CNN-SINDy based modeling can reproduce high-dimensional flow fields successfully, although more terms are required to represent the transient flow and the two-parallel cylinder wake than the periodic shedding. A nine-equation turbulent shear flow model is finally considered to examine the applicability of SINDy to turbulence, although without using CNN-AE. The present results suggest that the proposed scheme with an appropriate parameter choice enables us to analyze high-dimensional nonlinear dynamics with interpretable low-dimensional manifolds.
Recommendations
- Constrained sparse Galerkin regression
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
- SINDy-PI: a robust algorithm for parallel implicit sparse identification of nonlinear dynamics
- Data-driven discovery of coordinates and governing equations
Cites work
- scientific article; zbMATH DE number 3014343 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- Characteristics of flow over two circular cylinders in a side-by-side arrangement at low Reynolds numbers
- Constrained sparse Galerkin regression
- Data-driven discovery of coordinates and governing equations
- Data-driven science and engineering. Machine learning, dynamical systems, and control
- Deterministic Nonperiodic Flow
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- Discovery of Nonlinear Multiscale Systems: Sampling Strategies and Embeddings
- From the POD-Galerkin method to sparse manifold models
- Global stability of base and mean flows: a general approach and its applications to cylinder and open cavity flows
- Low-order model for successive bifurcations of the fluidic pinball
- Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows
- Multi-level convolutional autoencoder networks for parametric prediction of spatio-temporal dynamics
- Neural network modeling for near wall turbulent flow.
- Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
- On the convergence of the SINDy algorithm
- Periodic Orbits and Chaotic Sets in a Low-Dimensional Model for Shear Flows
- Recovering missing CFD data for high-order discretizations using deep neural networks and dynamics learning
- Reducing the Dimensionality of Data with Neural Networks
- Regularization and Variable Selection Via the Elastic Net
- Ridge Regression: Biased Estimation for Nonorthogonal Problems
- Sparse identification of multiphase turbulence closures for coupled fluid-particle flows
- Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
- Sparse reduced-order modelling: sensor-based dynamics to full-state estimation
- Spectral proper orthogonal decomposition and its relationship to dynamic mode decomposition and resolvent analysis
- Spectral proper orthogonal decomposition and resolvent analysis of near-wall coherent structures in turbulent pipe flows
- The Adaptive Lasso and Its Oracle Properties
Cited in
(16)- Dynamics of a data-driven low-dimensional model of turbulent minimal Couette flow
- Airfoil-based convolutional autoencoder and long short-term memory neural network for predicting coherent structures evolution around an airfoil
- Data-driven transient lift attenuation for extreme vortex gust-airfoil interactions
- Extracting Sparse High-Dimensional Dynamics from Limited Data
- Sparse feature map-based Markov models for nonlinear fluid flows
- Recovering missing CFD data for high-order discretizations using deep neural networks and dynamics learning
- Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
- A surrogate reduced order model of the unsteady advection dominant problems based on combination of deep autoencoders-LSTM and POD
- Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
- Front transport reduction for complex moving fronts
- Constrained sparse Galerkin regression
- A framework based on symbolic regression coupled with eXtended physics-informed neural networks for gray-box learning of equations of motion from data
- Reduced order modeling of parametrized systems through autoencoders and SINDy approach: continuation of periodic solutions
- Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
- Kernel functions embed into the autoencoder to identify the sparse models of nonlinear dynamics
- Koopman dynamic-oriented deep learning for invariant subspace identification and full-state prediction of complex systems
This page was built for publication: Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5154682)
