Assessment of unsteady flow predictions using hybrid deep learning based reduced order models

Abstract

In this paper, we present two deep learning-based hybrid data-driven reduced order models for the prediction of unsteady fluid flows. The first model projects the high-fidelity time series data from a finite element Navier-Stokes solver to a low-dimensional subspace via proper orthogonal decomposition (POD). The time-dependent coefficients in the POD subspace are propagated by the recurrent net (closed-loop encoder-decoder updates) and mapped to a high-dimensional state via the mean flow field and POD basis vectors. This model is referred as POD-RNN. The second model, referred to as convolution recurrent autoencoder network (CRAN), employs convolutional neural networks (CNN) as layers of linear kernels with nonlinear activations, to extract low-dimensional features from flow field snapshots. The flattened features are advanced using a recurrent (closed-loop manner) net and up-sampled (transpose convoluted) gradually to high-dimensional snapshots. Two benchmark problems of the flow past a cylinder and flow past a side-by-side cylinder are selected as the test problems to assess the efficacy of these models. For the problem of flow past a single cylinder, the performance of both the models is satisfactory, with CRAN being a bit overkill. However, it completely outperforms the POD-RNN model for a more complicated problem of flow past side-by-side cylinders. Owing to the scalability of CRAN, we briefly introduce an observer-corrector method for the calculation of integrated pressure force coefficients on the fluid-solid boundary on a reference grid. This reference grid, typically a structured and uniform grid, is used to interpolate scattered high-dimensional field data as snapshot images. These input images are convenient in training CRAN. This motivates us to further explore the application of CRAN models for the prediction of fluid flows.

References in corpus (33)

• Adam: A Method for Stochastic Optimization
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Deep learning for universal linear embeddings of nonlinear dynamics
• Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control
• Data-driven discovery of coordinates and governing equations
• Applied Koopmanism
• A Physics Informed Machine Learning Approach for Reconstructing Reynolds Stress Modeling Discrepancies Based on DNS Data
• Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• Neural Ordinary Differential Equations
• Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks
• Extended dynamic mode decomposition with dictionary learning: a data-driven adaptive spectral decomposition of the Koopman operator
• Deep Learning of Vortex Induced Vibrations
• On Convergence of Extended Dynamic Mode Decomposition to the Koopman Operator
• Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
• Deep Fluids: A Generative Network for Parameterized Fluid Simulations
• Koopman operator-based model reduction for switched-system control of PDEs
• Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stability
• A Deep Learning based Approach to Reduced Order Modeling for Turbulent Flow Control using LSTM Neural Networks
• Time-series learning of latent-space dynamics for reduced-order model closure
• Deep learning algorithm for data-driven simulation of noisy dynamical system
• Nonlinear Systems Identification Using Deep Dynamic Neural Networks
• Long-time predictive modeling of nonlinear dynamical systems using neural networks
• An Efficient Deep Learning Technique for the Navier-Stokes Equations: Application to Unsteady Wake Flow Dynamics
• Data-driven Discovery of Closure Models
• Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systems
• Recovering missing CFD data for high-order discretizations using deep neural networks and dynamics learning
• DR-RNN: A deep residual recurrent neural network for model reduction
• Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction
• Decomposition of wake dynamics in fluid-structure interaction via low-dimensional models
• Dynamics of gap flow interference in a vibrating side-by-side arrangement of two circular cylinders at moderate Reynolds number
• Model-free prediction of noisy chaotic time series by deep learning
• Decomposition of Nonlinear Dynamical Systems Using Koopman Gramians

Cited by in corpus (10)

• A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries
• Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
• Experimental velocity data estimation for imperfect particle images using machine learning
• Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: comparison with linear subspace techniques
• Predicting waves in fluids with deep neural network
• A Finite Element-Inspired Hypergraph Neural Network: Application to Fluid Dynamics Simulations
• Predicting fluid-structure interaction with graph neural networks
• CD-ROM: Complemented Deep-Reduced Order Model
• Real-time simulation of parameter-dependent fluid flows through deep learning-based reduced order models
• Sensitivity Analysis of Lift and Drag Coefficients for Flow over Elliptical Cylinders of Arbitrary Aspect Ratio and Angle of Attack using Neural Network