A Deep Learning based Approach to Reduced Order Modeling for Turbulent Flow Control using LSTM Neural Networks
arXiv:1804.09269
Abstract
Reduced Order Modeling (ROM) for engineering applications has been a major research focus in the past few decades due to the unprecedented physical insight into turbulence offered by high-fidelity CFD. The primary goal of a ROM is to model the key physics/features of a flow-field without computing the full Navier-Stokes (NS) equations. This is accomplished by projecting the high-dimensional dynamics to a low-dimensional subspace, typically utilizing dimensionality reduction techniques like Proper Orthogonal Decomposition (POD), coupled with Galerkin projection. In this work, we demonstrate a deep learning based approach to build a ROM using the POD basis of canonical DNS datasets, for turbulent flow control applications. We find that a type of Recurrent Neural Network, the Long Short Term Memory (LSTM) which has been primarily utilized for problems like speech modeling and language translation, shows attractive potential in modeling temporal dynamics of turbulence. Additionally, we introduce the Hurst Exponent as a tool to study LSTM behavior for non-stationary data, and uncover useful characteristics that may aid ROM development for a variety of applications.
References in corpus (3)
Cited by in corpus (40)
- Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders
- Deep Neural Networks for Nonlinear Model Order Reduction of Unsteady Flows
- A machine learning based plasticity model using proper orthogonal decomposition
- A new prediction method of unsteady wake flow by the hybrid deep neural network
- 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
- Probabilistic neural networks for fluid flow surrogate modeling and data recovery
- On closures for reduced order models A spectrum of first-principle to machine-learned avenues
- Time-series learning of latent-space dynamics for reduced-order model closure
- Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers
- Assessment of unsteady flow predictions using hybrid deep learning based reduced order models
- A non-intrusive reduced order modeling framework for quasi-geostrophic turbulence
- Deep learning-based reduced order models in cardiac electrophysiology
- Reservoir computing model of two-dimensional turbulent convection
- A long short-term memory embedding for hybrid uplifted reduced order models
- Compressed Convolutional LSTM: An Efficient Deep Learning framework to Model High Fidelity 3D Turbulence
- Memory embedded non-intrusive reduced order modeling of non-ergodic flows
- Embedding Hard Physical Constraints in Neural Network Coarse-Graining of 3D Turbulence
- An advanced hybrid deep adversarial autoencoder for parameterized nonlinear fluid flow modelling
- Non-intrusive model reduction of large-scale, nonlinear dynamical systems using deep learning
- Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulation
- From Deep to Physics-Informed Learning of Turbulence: Diagnostics
- Neural-network learning of SPOD latent dynamics
- Model Order Reduction based on Runge-Kutta Neural Network
- POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition
- A Tailored Convolutional Neural Network for Nonlinear Manifold Learning of Computational Physics Data using Unstructured Spatial Discretizations
- Deep Learning for Reduced Order Modelling and Efficient Temporal Evolution of Fluid Simulations
- Bridging the Gap: Machine Learning to Resolve Improperly Modeled Dynamics
- Deep Learning for Efficient Reconstruction of High-Resolution Turbulent DNS Data
- Generalization capabilities and robustness of hybrid models grounded in physics compared to purely deep learning models
- Learning Stable Galerkin Models of Turbulence with Differentiable Programming
- On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysis
- Data-Driven Modeling of Geometry-Adaptive Steady Heat Transfer based on Convolutional Neural Networks: Heat Conduction
- Artificial neural network approach for turbulence models: A local framework
- Machine-Learning for Nonintrusive Model Order Reduction of the Parametric Inviscid Transonic Flow past an airfoil
- Three-dimensional realizations of flood flow in large-scale rivers using the neural fuzzy-based machine-learning algorithm
- Prediction of three-dimensional flood-flow past bridge piers in a large-scale meandering river using convolutional neural networks
- Spatio-Temporal Differential Dynamic Programming for Control of Fields
- Complete CVDL Methodology for Investigating Hydrodynamic Instabilities
- Pressure-Informed Velocity Estimation in a Subsonic Jet