A statistical learning strategy for closed-loop control of fluid flows

Abstract

This work discusses a closed-loop control strategy for complex systems utilizing scarce and streaming data. A discrete embedding space is first built using hash functions applied to the sensor measurements from which a Markov process model is derived, approximating the complex system's dynamics. A control strategy is then learned using reinforcement learning once rewards relevant with respect to the control objective are identified. This method is designed for experimental configurations, requiring no computations nor prior knowledge of the system, and enjoys intrinsic robustness. It is illustrated on two systems: the control of the transitions of a Lorenz 63 dynamical system, and the control of the drag of a cylinder flow. The method is shown to perform well.

References in corpus (3)

• Cluster-based reduced-order modelling of a mixing layer
• Closed-loop separation control using machine learning
• Reduced order models for control of fluids using the Eigensystem Realization Algorithm

Cited by in corpus (11)

• Machine Learning for Fluid Mechanics
• Artificial Neural Networks trained through Deep Reinforcement Learning discover control strategies for active flow control
• Data-assisted reduced-order modeling of extreme events in complex dynamical systems
• Control of chaotic systems by Deep Reinforcement Learning
• Comparative analysis of machine learning methods for active flow control
• The chaotic dynamics of large-scale structures in a turbulent wake
• Reinforcement-learning-based control of convectively-unstable flows
• Reinforcement-learning-based control of turbulent channel flows at high Reynolds numbers
• Stabilising viscous extensional flows using Reinforcement Learning
• Learning swimming escape patterns for larval fish under energy constraints
• Symmetry reduction for deep reinforcement learning active control of chaotic spatiotemporal dynamics