Non-intrusive model reduction of large-scale, nonlinear dynamical systems using deep learning
From MaRDI portal
Publication:2127404
Abstract: Projection-based model reduction has become a popular approach to reduce the cost associated with integrating large-scale dynamical systems so they can be used in many-query settings such as optimization and uncertainty quantification. For nonlinear systems, significant cost reduction is only possible with an additional layer of approximation to reduce the computational bottleneck of evaluating the projected nonlinear terms. Prevailing methods to approximate the nonlinear terms are code intrusive, potentially requiring years of development time to integrate into an existing codebase, and have been known to lack parametric robustness. This work develops a non-intrusive method to efficiently and accurately approximate the expensive nonlinear terms that arise in reduced nonlinear dynamical system using deep neural networks. The neural network is trained using only the simulation data used to construct the reduced basis and evaluations of the nonlinear terms at these snapshots. Once trained, the neural network-based reduced-order model only requires forward and backward propagation through the network to evaluate the nonlinear term and its derivative, which are used to integrate the reduced dynamical system at a new parameter configuration. We provide two numerical experiments---the dynamical systems result from the semi-discretization of parametrized, nonlinear, hyperbolic partial differential equations---that show, in addition to non-intrusivity, the proposed approach provides more stable and accurate approximations to each dynamical system across a large number of training and testing points than the popular empirical interpolation method.
Recommendations
- Operator inference for non-intrusive model reduction of systems with non-polynomial nonlinear terms
- A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
- Neural network closures for nonlinear model order reduction
- Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
- Non-intrusive reduced order modeling of nonlinear problems using neural networks
Cites work
- scientific article; zbMATH DE number 6378127 (Why is no real title available?)
- A fully discrete adjoint method for optimization of flow problems on deforming domains with time-periodicity constraints
- A priori hyperreduction method: an adaptive approach
- An `empirical interpolation' method: Application to efficient reduced-basis discretization of partial differential equations
- An adjoint method for a high-order discretization of deforming domain conservation laws for optimization of flow problems
- An artificial neural network framework for reduced order modeling of transient flows
- Construction of reduced-order models for fluid flows using deep feedforward neural networks
- Convergence rates of the POD-greedy method
- Data-driven discovery of closure models
- Data-driven operator inference for nonintrusive projection-based model reduction
- Data-driven science and engineering. Machine learning, dynamical systems, and control
- Diagonally Implicit Runge–Kutta Methods for Stiff O.D.E.’s
- Energetically optimal flapping wing motions via adjoint-based optimization and high-order discretizations
- Enhanced linearized reduced-order models for subsurface flow simulation
- Evaluating Derivatives
- Linearized reduced-order models for subsurface flow simulation
- Machine learning closures for model order reduction of thermal fluids
- Machine learning for fast and reliable solution of time-dependent differential equations
- Missing Point Estimation in Models Described by Proper Orthogonal Decomposition
- Neural network closures for nonlinear model order reduction
- Non-intrusive reduced order modeling of nonlinear problems using neural networks
- Non-intrusive reduced order modeling of unsteady flows using artificial neural networks with application to a combustion problem
- Non-intrusive reduced order modelling of the Navier-Stokes equations
- Nonintrusive reduced-order modeling of parametrized time-dependent partial differential equations
- Nonlinear model order reduction based on local reduced-order bases
- Nonlinear model reduction via discrete empirical interpolation
- On early stopping in gradient descent learning
- Reduced basis approximation and a posteriori error estimation for affinely parametrized elliptic coercive partial differential equations. Application to transport and continuum mechanics.
- Structure-preserving, stability, and accuracy properties of the energy-conserving sampling and weighting method for the hyper reduction of nonlinear finite element dynamic models
- The GNAT method for nonlinear model reduction: effective implementation and application to computational fluid dynamics and turbulent flows
- The complexity of partial derivatives
- Turbulence and the dynamics of coherent structures. I. Coherent structures
Cited in
(31)- A pruning algorithm preserving modeling capabilities for polycrystalline data
- Fast reduced model of non-linear dynamic Euler-Bernoulli beam behaviour
- Reduced-order deep learning for flow dynamics. The interplay between deep learning and model reduction
- Data-driven reduced order modeling of poroelasticity of heterogeneous media based on a discontinuous Galerkin approximation
- Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
- The neural network shifted-proper orthogonal decomposition: a machine learning approach for non-linear reduction of hyperbolic equations
- CD-ROM: complemented deep -- reduced order model
- Nonlinear reduced DNN models for state estimation
- Model reduction for the material point method via an implicit neural representation of the deformation map
- Network flow problem heuristic reduction using machine learning
- Lift \& learn: physics-informed machine learning for large-scale nonlinear dynamical systems
- Neural network closures for nonlinear model order reduction
- Operator learning using random features: a tool for scientific computing
- Applied unsupervised learning in model reduction of linear dynamic systems
- Operator inference for non-intrusive model reduction with quadratic manifolds
- A fast time-stepping strategy for dynamical systems equipped with a surrogate model
- Data-driven nonintrusive reduced order modeling for dynamical systems with moving boundaries using Gaussian process regression
- Operator inference for non-intrusive model reduction of systems with non-polynomial nonlinear terms
- Deep learning of thermodynamics-aware reduced-order models from data
- Transformers for modeling physical systems
- Level Set Learning with Pseudoreversible Neural Networks for Nonlinear Dimension Reduction in Function Approximation
- Symplectic model reduction of Hamiltonian systems using data-driven quadratic manifolds
- Leveraging reduced-order models for state estimation using deep learning
- The model reduction of the Vlasov–Poisson–Fokker–Planck system to the Poisson–Nernst–Planck system via the Deep Neural Network Approach
- Non-intrusive data-driven model reduction for differential-algebraic equations derived from lifting transformations
- Deep subspace encoders for nonlinear system identification
- Deep-HyROMnet: a deep learning-based operator approximation for hyper-reduction of nonlinear parametrized PDEs
- Parametrized non intrusive space-time approximation for explicit dynamic fem applications
- Deep learning‐based reduced order models for the real‐time simulation of the nonlinear dynamics of microstructures
- Bifidelity data-assisted neural networks in nonintrusive reduced-order modeling
- Non-intrusive parametric hyper-reduction for nonlinear structural finite element formulations
This page was built for publication: Non-intrusive model reduction of large-scale, nonlinear dynamical systems using deep learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2127404)
