Deep Dynamical Modeling and Control of Unsteady Fluid Flows

Abstract

The design of flow control systems remains a challenge due to the nonlinear nature of the equations that govern fluid flow. However, recent advances in computational fluid dynamics (CFD) have enabled the simulation of complex fluid flows with high accuracy, opening the possibility of using learning-based approaches to facilitate controller design. We present a method for learning the forced and unforced dynamics of airflow over a cylinder directly from CFD data. The proposed approach, grounded in Koopman theory, is shown to produce stable dynamical models that can predict the time evolution of the cylinder system over extended time horizons. Finally, by performing model predictive control with the learned dynamical models, we are able to find a straightforward, interpretable control law for suppressing vortex shedding in the wake of the cylinder.

arXiv comment10 pages, 7 figures

Cited by in corpus (25)

• Learning data driven discretizations for partial differential equations
• Deep Neural Networks with Koopman Operators for Modeling and Control of Autonomous Vehicles
• Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
• Deep Model Predictive Control with Online Learning for Complex Physical Systems
• Incorporating Symmetry into Deep Dynamics Models for Improved Generalization
• Recovering missing CFD data for high-order discretizations using deep neural networks and dynamics learning
• Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction
• Lagrangian Dynamic Mode Decomposition for Construction of Reduced-Order Models of Advection-Dominated Phenomena
• Parameterized Neural Ordinary Differential Equations: Applications to Computational Physics Problems
• Learning Compositional Koopman Operators for Model-Based Control
• Learning to Control PDEs with Differentiable Physics
• Differentiable Molecular Simulations for Control and Learning
• Learning Deep Stochastic Optimal Control Policies using Forward-Backward SDEs
• Forecasting Sequential Data using Consistent Koopman Autoencoders
• Solving PDE-constrained Control Problems Using Operator Learning
• Stochastic Adversarial Koopman Model for Dynamical Systems
• Meta-Learning Dynamics Forecasting Using Task Inference
• Variational Optimization Based Reinforcement Learning for Infinite Dimensional Stochastic Systems
• Structured Mechanical Models for Robot Learning and Control
• Dynamic Mode Decomposition for Construction of Reduced-Order Models of Hyperbolic Problems with Shocks
• Learning Dynamics Models with Stable Invariant Sets
• Deep Learning-Aided Model Predictive Control of Wind Farms for AGC Considering the Dynamic Wake Effect
• Self-Supervised Decomposition, Disentanglement and Prediction of Video Sequences while Interpreting Dynamics: A Koopman Perspective
• Three-dimensional realizations of flood flow in large-scale rivers using the neural fuzzy-based machine-learning algorithm
• Meta-Learning for Koopman Spectral Analysis with Short Time-series