Construction of Reduced Order Models for Fluid Flows Using Deep Feedforward Neural Networks

Abstract

We present a numerical methodology for construction of reduced order models, ROMs, of fluid flows through the combination of flow modal decomposition and regression analysis. Spectral proper orthogonal decomposition, SPOD, is applied to reduce the dimensionality of the model and, at the same time, filter the POD temporal modes. The regression step is performed by a deep feedforward neural network, DNN, and the current framework is implemented in a context similar to the sparse identification of non-linear dynamics algorithm, SINDy. A discussion on the optimization of the DNN hyperparameters is provided for obtaining the best ROMs and an assessment of these models is presented for a canonical nonlinear oscillator and the compressible flow past a cylinder. Then, the method is tested on the reconstruction of a turbulent flow computed by a large eddy simulation of a plunging airfoil under dynamic stall. The reduced order model is able to capture the dynamics of the leading edge stall vortex and the subsequent trailing edge vortex. For the cases analyzed, the numerical framework allows the prediction of the flowfield beyond the training window using larger time increments than those employed by the full order model. We also demonstrate the robustness of the current ROMs constructed via deep feedforward neural networks through a comparison with sparse regression. The DNN approach is able to learn transient features of the flow and presents more accurate and stable long-term predictions compared to sparse regression.

References in corpus (12)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• On Dynamic Mode Decomposition: Theory and Applications
• Spectral proper orthogonal decomposition and its relationship to dynamic mode decomposition and resolvent analysis
• A Physics Informed Machine Learning Approach for Reconstructing Reynolds Stress Modeling Discrepancies Based on DNS Data
• Spectral proper orthogonal decomposition
• Data-assisted reduced-order modeling of extreme events in complex dynamical systems
• On the need for a nonlinear subscale turbulence term in POD models as exemplified for a high Reynolds number flow over an Ahmed body
• Deep learning of dynamics and signal-noise decomposition with time-stepping constraints
• Long-time predictive modeling of nonlinear dynamical systems using neural networks
• Minimal subspace rotation on the Stiefel manifold for stabilization and enhancement of projection-based reduced order models for the compressible Navier-Stokes equations
• Data-Driven, Physics-Based Feature Extraction from Fluid Flow Fields
• Optimal Nonlinear Eddy Viscosity in Galerkin Models of Turbulent Flows

Cited by in corpus (21)

• Assessment of supervised machine learning methods for fluid flows
• An artificial neural network framework for reduced order modeling of transient flows
• Experimental velocity data estimation for imperfect particle images using machine learning
• Deep learning to discover and predict dynamics on an inertial manifold
• Generalization techniques of neural networks for fluid flow estimation
• Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics
• Parametric Dynamic Mode Decomposition for Reduced Order Modeling
• Model fusion with physics-guided machine learning
• Data-driven Nonlinear Model Reduction to Spectral Submanifolds in Mechanical Systems
• Non-intrusive model reduction of large-scale, nonlinear dynamical systems using deep learning
• $\text{FastSVD-ML-ROM}$: A Reduced-Order Modeling Framework based on Machine Learning for Real-Time Applications
• Data-driven low-dimensional dynamic model of Kolmogorov flow
• Data-driven nonintrusive reduced order modeling for dynamical systems with moving boundaries using Gaussian process regression
• Stochastic modelling of a noise driven global instability in a turbulent swirling jet
• Calibration of projection-based reduced-order models for unsteady compressible flows
• Flow imaging as an alternative to pressure transducers through vision transformers and convolutional neural networks
• Parametric 3D Convolutional Autoencoder for the Prediction of Flow Fields in a Bed Configuration of Hot Particles
• Model order reduction with neural networks: Application to laminar and turbulent flows
• Reduced order modeling of dynamical systems using artificial neural networks applied to water circulation
• Data-Driven Closure of Projection-Based Reduced Order Models for Unsteady Compressible Flows
• Real-time simulation of parameter-dependent fluid flows through deep learning-based reduced order models