Reinforcement-learning-based actuator selection method for active flow control

DOI10.1017/JFM.2022.1043MaRDI QIDQ5871612zbMATH OpenOpenAlexFDO

Authors Romain Paris, Samir Beneddine, J. Dandois

Publication date 23 January 2023

Published in Journal of Fluid Mechanics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2209.14895

zbMATH Keywords

drag reductionFourier spatial decompositioninstability controlKuramoto-Sivashinsky equationlaminar two-dimensional airfoil flowmachine learningthird-order semi-implicit temporal Runge-Kutta scheme

Mathematics Subject Classification ID

Flow control and optimization for incompressible viscous fluids (76D55) Finite difference methods applied to problems in fluid mechanics (76M20) Spectral methods applied to problems in fluid mechanics (76M22) Basic methods in fluid mechanics (76M99)

Recommendations

• Robust flow control and optimal sensor placement using deep reinforcement learning
• Comparative analysis of machine learning methods for active flow control
• Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control
• Active flow separation control by a position-based iterative learning control algorithm with experimental validation
• A review on deep reinforcement learning for fluid mechanics

Cites work

• A heuristic approach to effective sensor placement for modeling of a cylinder wake
• A review on deep reinforcement learning for fluid mechanics
• Actuator selection and placement for localized feedback flow control
• Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control
• Control of chaotic systems by deep reinforcement learning
• GLOBAL INSTABILITIES IN SPATIALLY DEVELOPING FLOWS: Non-Normality and Nonlinearity
• Large-eddy simulation of laminar transonic buffet
• Machine learning for fluid mechanics
• Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
• Neural network modeling for near wall turbulent flow.
• Numerical modelling and passive flow control using porous media
• On Flame Propagation Under Conditions of Stoichiometry
• Optimal sensor and actuator placement for feedback control of vortex shedding
• Optimal Sensor and Actuator Selection Using Balanced Model Reduction
• Post-stall flow control on an airfoil by local unsteady forcing
• Prediction of aerodynamic flow fields using convolutional neural networks
• Reinforcement-learning-based control of confined cylinder wakes with stability analyses
• Resolvent-analysis-based design of airfoil separation control
• Robust flow control and optimal sensor placement using deep reinforcement learning
• Sensor and actuator placement trade-offs for a linear model of spatially developing flows
• Structural sensitivity of the first instability of the cylinder wake
• Turbulence modeling in the age of data
• Unsteady flow sensing and estimation via the gappy proper orthogonal decomposition

Cited in

(5)

• Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control
• Robust flow control and optimal sensor placement using deep reinforcement learning
• Comparative analysis of machine learning methods for active flow control
• Self-tuning model predictive control for wake flows
• Transonic buffet flow adaptive control with time-variant reduced-order model

Describes a project that uses

Uses Software

• Adam

This page was built for publication: Reinforcement-learning-based actuator selection method for active flow control

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5871612)