Machine learning flow control with few sensor feedback and measurement noise

Abstract

A comparative assessment of machine learning (ML) methods for active flow control is performed. The chosen benchmark problem is the drag reduction of a two-dimensional Kármán vortex street past a circular cylinder at a low Reynolds number ($Re=100$). The flow is manipulated with two blowing/suction actuators on the upper and lower side of a cylinder. The feedback employs several velocity sensors. Two probe configurations are evaluated: 5 and 11 velocity probes located at different points around the cylinder and in the wake. The control laws are optimized with Deep Reinforcement Learning (DRL) and Linear Genetic Programming Control (LGPC). By interacting with the unsteady wake, both methods successfully stabilize the vortex alley and effectively reduce drag while using small mass flow rates for the actuation. DRL has shown higher robustness with respect to variable initial conditions and to noise contamination of the sensor data; on the other hand, LGPC is able to identify compact and interpretable control laws, which only use a subset of sensors, thus allowing reducing the system complexity with reasonably good results. Our study points at directions of future machine learning control combining desirable features of different approaches.

References in corpus (17)

• Machine Learning for Fluid Mechanics
• Artificial Neural Networks trained through Deep Reinforcement Learning discover control strategies for active flow control
• Deep Reinforcement Learning Attitude Control of Fixed-Wing UAVs Using Proximal Policy Optimization
• Accelerating Deep Reinforcement Learning strategies of Flow Control through a multi-environment approach
• Closed-loop separation control using machine learning
• Robust active flow control over a range of Reynolds numbers using an artificial neural network trained through deep reinforcement learning
• Applying deep reinforcement learning to active flow control in turbulent conditions
• Reinforcement-learning-based control of confined cylinder wakes with stability analyses
• Artificial intelligence control of a turbulent jet
• Drag reduction of a car model by linear genetic programming control
• Controlling Rayleigh-Bénard convection via Reinforcement Learning
• Cluster-based feedback control of turbulent post-stall separated flows
• Comparative analysis of machine learning methods for active flow control
• Cluster-based network model
• Jet mixing optimization using machine learning control
• Stabilization of the fluidic pinball with gradient-enriched machine learning control
• Exploiting locality and physical invariants to design effective Deep Reinforcement Learning control of the unstable falling liquid film

Cited by in corpus (10)

• A review on deep reinforcement learning for fluid mechanics: an update
• A review on Deep Reinforcement Learning for Fluid Mechanics
• DRLinFluids -- An open-source python platform of coupling Deep Reinforcement Learning and OpenFOAM
• Comparative analysis of machine learning methods for active flow control
• Reinforcement-learning-based control of convectively-unstable flows
• Machine-learned control-oriented flow estimation for multiactuator multi-sensor systems exemplified for the fluidic pinball
• Genetically-inspired convective heat transfer enhancement in a turbulent boundary layer
• Flow control by a hybrid use of machine learning and control theory
• Self-tuning model predictive control for wake flows
• xMLC -- A Toolkit for Machine Learning Control