Deep Neural Networks for Nonlinear Model Order Reduction of Unsteady Flows

Abstract

Unsteady fluid systems are nonlinear high-dimensional dynamical systems that may exhibit multiple complex phenomena both in time and space. Reduced Order Modeling (ROM) of fluid flows has been an active research topic in the recent decade with the primary goal to decompose complex flows to a set of features most important for future state prediction and control, typically using a dimensionality reduction technique. In this work, a novel data-driven technique based on the power of deep neural networks for reduced order modeling of the unsteady fluid flows is introduced. An autoencoder network is used for nonlinear dimension reduction and feature extraction as an alternative for singular value decomposition (SVD). Then, the extracted features are used as an input for long short-term memory network (LSTM) to predict the velocity field at future time instances. The proposed autoencoder-LSTM method is compared with non-intrusive reduced order models based on dynamic mode decomposition (DMD) and proper orthogonal decomposition (POD). Moreover, an autoencoder-DMD algorithm is introduced for reduced order modeling, which uses the autoencoder network for dimensionality reduction rather than SVD rank truncation. Results show that the autoencoder-LSTM method is considerably capable of predicting fluid flow evolution, where higher values for coefficient of determination $R^2$ are obtained using autoencoder-LSTM compared to other models.

arXiv commentThis article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. This article appeared in Phys. Fluids 32, 105104 (2020), and may be found at https://doi.org/10.1063/5.0020526

References in corpus (23)

• Adam: A Method for Stochastic Optimization
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Machine Learning for Fluid Mechanics
• A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
• On Dynamic Mode Decomposition: Theory and Applications
• Turbulence Modeling in the Age of Data
• Deep learning for universal linear embeddings of nonlinear dynamics
• Artificial Neural Networks trained through Deep Reinforcement Learning discover control strategies for active flow control
• Ergodic theory, Dynamic Mode Decomposition and Computation of Spectral Properties of the Koopman operator
• Extended dynamic mode decomposition with dictionary learning: a data-driven adaptive spectral decomposition of the Koopman operator
• Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
• Assessment of supervised machine learning methods for fluid flows
• Robust active flow control over a range of Reynolds numbers using an artificial neural network trained through deep reinforcement learning
• A deep learning enabler for non-intrusive reduced order modeling of fluid flows
• An artificial neural network framework for reduced order modeling of transient flows
• A Deep Learning based Approach to Reduced Order Modeling for Turbulent Flow Control using LSTM Neural Networks
• Data-driven recovery of hidden physics in reduced order modeling of fluid flows
• Controlling Rayleigh-Bénard convection via Reinforcement Learning
• Learning Koopman Invariant Subspaces for Dynamic Mode Decomposition
• Physically-Constrained Data-Driven, Filtered Reduced Order Modeling of Fluid Flows
• A long short-term memory embedding for hybrid uplifted reduced order models
• Prediction of wall-bounded turbulence from wall quantities using convolutional neural networks
• A Koopman-based framework for forecasting the spatiotemporal evolution of chaotic dynamics with nonlinearities modeled as exogenous forcings

Cited by in corpus (29)

• Physics-informed neural networks for solving Reynolds-averaged Navier$\unicode{x2013}$Stokes equations
• Machine Learning in Aerodynamic Shape Optimization
• Experimental velocity data estimation for imperfect particle images using machine learning
• A Comparison of Neural Network Architectures for Data-Driven Reduced-Order Modeling
• Data-driven subgrid-scale modeling of forced Burgers turbulence using deep learning with generalization to higher Reynolds numbers via transfer learning
• Data-driven peakon and periodic peakon travelling wave solutions of some nonlinear dispersive equations via deep learning
• Parametric Dynamic Mode Decomposition for Reduced Order Modeling
• Model fusion with physics-guided machine learning
• An AI-based Domain-Decomposition Non-Intrusive Reduced-Order Model for Extended Domains applied to Multiphase Flow in Pipes
• Linear and Nonlinear Dimensionality Reduction from Fluid Mechanics to Machine Learning
• Physics-aware Reduced-order Modeling of Transonic Flow via $\beta$-Variational Autoencoder
• A Parametric and Feasibility Study for Data Sampling of the Dynamic Mode Decomposition: Spectral Insights and Further Explorations
• State estimation with limited sensors -- A deep learning based approach
• Physically Interpretable Feature Learning and Inverse Design of Supercritical Airfoils
• The Linear-Time-Invariance Notion of the Koopman Analysis-Part 1: The Architecture, Practical Rendering on the Prism Wake, and Fluid-Structure Association
• The Linear-Time-Invariance Notion of the Koopman Analysis-Part 2: Physical Interpretations of Invariant Koopman Modes and Phenomenological Revelations
• A deep neural network physics-based reduced order model for dynamic stall
• Towards aerodynamic surrogate modeling based on $\beta$-variational autoencoders
• Deep learning for surrogate modelling of 2D mantle convection
• CD-ROM: Complemented Deep-Reduced Order Model
• Generalizability of reservoir computing for flux-driven two-dimensional convection
• Numerical assessments of a nonintrusive surrogate model based on recurrent neural networks and proper orthogonal decomposition: Rayleigh Benard convection
• Energy preserving reduced-order modelling of thermal shallow water equation
• Polytopic Autoencoders with Smooth Clustering for Reduced-order Modelling of Flows
• Data-Driven Forecasting of Non-Equilibrium Solid-State Dynamics
• Studying First Passage Problems using Neural Networks: A Case Study in the Slit-Well Microfluidic Device
• Mitigating distribution shift in machine learning-augmented hybrid simulation
• On Deep-Learning-Based Closures for Algebraic Surrogate Models of Turbulent Flows
• Data-driven system identification using quadratic embeddings of nonlinear dynamics