Reduced order modeling of parametrized systems through autoencoders and SINDy approach: continuation of periodic solutions
From MaRDI portal
Publication:6097611
Abstract: Highly accurate simulations of complex phenomena governed by partial differential equations (PDEs) typically require intrusive methods and entail expensive computational costs, which might become prohibitive when approximating steady-state solutions of PDEs for multiple combinations of control parameters and initial conditions. Therefore, constructing efficient reduced order models (ROMs) that enable accurate but fast predictions, while retaining the dynamical characteristics of the physical phenomenon as parameters vary, is of paramount importance. In this work, a data-driven, non-intrusive framework which combines ROM construction with reduced dynamics identification, is presented. Starting from a limited amount of full order solutions, the proposed approach leverages autoencoder neural networks with parametric sparse identification of nonlinear dynamics (SINDy) to construct a low-dimensional dynamical model. This model can be queried to efficiently compute full-time solutions at new parameter instances, as well as directly fed to continuation algorithms. These aim at tracking the evolution of periodic steady-state responses as functions of system parameters, avoiding the computation of the transient phase, and allowing to detect instabilities and bifurcations. Featuring an explicit and parametrized modeling of the reduced dynamics, the proposed data-driven framework presents remarkable capabilities to generalize with respect to both time and parameters. Applications to structural mechanics and fluid dynamics problems illustrate the effectiveness and accuracy of the proposed method.
Recommendations
- Non-intrusive data-driven reduced-order modeling for time-dependent parametrized problems
- A reduced order method for nonlinear parameterized partial differential equations using dynamic mode decomposition coupled with \(k\)-nearest-neighbors regression
- A data-driven surrogate modeling approach for time-dependent incompressible Navier-Stokes equations with dynamic mode decomposition and manifold interpolation
- A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
Cites work
- A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
- A deep learning approach to Reduced Order Modelling of parameter dependent partial differential equations
- A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
- A hierarchy of low-dimensional models for the transient and post-transient cylinder wake
- A purely frequency based Floquet-Hill formulation for the efficient stability computation of periodic solutions of ordinary differential systems
- A Taylor series-based continuation method for solutions of dynamical systems
- Approximation by superpositions of a sigmoidal function
- Certified reduced basis methods for parametrized partial differential equations
- Characterization of periodic motions in aircraft lateral dynamics
- Data-driven discovery of coordinates and governing equations
- Deep learning
- Direct computation of nonlinear mapping via normal form for reduced-order models of finite element nonlinear structures
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- From the POD-Galerkin method to sparse manifold models
- Harmonic balance for nonlinear vibration problems
- scientific article; zbMATH DE number 976302 (Why is no real title available?)
- LaSDI: parametric latent space dynamics identification
- Model reduction and approximation. Theory and algorithms
- Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
- Multi-fidelity surrogate modeling using long short-term memory networks
- Multilayer feedforward networks are universal approximators
- Nonlinear model order reduction based on local reduced-order bases
- Numerical approximation of parametrized problems in cardiac electrophysiology by a local reduced basis method
- Numerical continuation methods for dynamical systems. Path following and boundary value problems.
- Numerical simulation of laminar flow past a circular cylinder
- On shooting methods for boundary value problems
- On the role of nonlinear correlations in reduced-order modelling
- POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition
- Recipes for continuation
- Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
- Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
- The harmonic balance method for bifurcation analysis of large-scale nonlinear mechanical systems
Cited in
(22)- A reduced order method for nonlinear parameterized partial differential equations using dynamic mode decomposition coupled with \(k\)-nearest-neighbors regression
- gLaSDI: parametric physics-informed greedy latent space dynamics identification
- \textit{FastSVD-ML-ROM}: a reduced-order modeling framework based on machine learning for real-time applications
- GPLaSDI: Gaussian process-based interpretable latent space dynamics identification through deep autoencoder
- Non-intrusive data-driven reduced-order modeling for time-dependent parametrized problems
- A graph convolutional autoencoder approach to model order reduction for parametrized PDEs
- A super-real-time three-dimension computing method of digital twins in space nuclear power
- tLaSDI: thermodynamics-informed latent space dynamics identification
- A hybrid numerical methodology coupling reduced order modeling and graph neural networks for non-parametric geometries: applications to structural dynamics problems
- Deep learning in computational mechanics: a review
- EKF-SINDy: empowering the extended Kalman filter with sparse identification of nonlinear dynamics
- Greedy identification of latent dynamics from parametric flow data
- Data-driven model reduction via non-intrusive optimization of projection operators and reduced-order dynamics
- Convolutional autoencoders, clustering, and POD for low-dimensional parametrization of flow equations
- Non-intrusive parametric hyper-reduction for nonlinear structural finite element formulations
- Extraction and reconstruction of variable-coefficient governing equations using RES-KAN integrating sparse regression
- Weak-form modified sparse identification of nonlinear dynamics
- Data-driven nonlinear model reduction to spectral submanifolds via oblique projection
- Path-following strategy with consistent Jacobian for periodic solutions in multi-DOF nonlinear dynamic systems
- Multi-fidelity reduced-order surrogate modelling
- Hamiltonian-based neural networks for systems under nonholonomic constraints
- PDE-free mass-constrained learning of complex systems with hidden states
This page was built for publication: Reduced order modeling of parametrized systems through autoencoders and SINDy approach: continuation of periodic solutions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6097611)
