Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control
From MaRDI portal
Publication:4628789
DOI10.1017/jfm.2019.62zbMath1415.76222arXiv1808.07664OpenAlexW2888317899WikidataQ128353771 ScholiaQ128353771MaRDI QIDQ4628789
Miroslav Kuchta, Jean Rabault, Atle Jensen, Nicolas Cerardi, Ulysse Réglade
Publication date: 25 March 2019
Published in: Journal of Fluid Mechanics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1808.07664
Learning and adaptive systems in artificial intelligence (68T05) Viscous vortex flows (76D17) Flow control and optimization for incompressible viscous fluids (76D55)
Related Items (23)
Comparative analysis of machine learning methods for active flow control ⋮ A neural network based shock detection and localization approach for discontinuous Galerkin methods ⋮ Direct shape optimization through deep reinforcement learning ⋮ Deep reinforcement learning for the control of conjugate heat transfer ⋮ Dynamic metasurface control using deep reinforcement learning ⋮ ModalPINN: an extension of physics-informed neural networks with enforced truncated Fourier decomposition for periodic flow reconstruction using a limited number of imperfect sensors ⋮ A deep reinforcement learning framework for dynamic optimization of numerical schemes for compressible flow simulations ⋮ Hybrid analysis and modeling, eclecticism, and multifidelity computing toward digital twin revolution ⋮ Robust optimal well control using an adaptive multigrid reinforcement learning framework ⋮ Self-tuning model predictive control for wake flows ⋮ Multi-fidelity reinforcement learning framework for shape optimization ⋮ Unsupervised deep learning for super-resolution reconstruction of turbulence ⋮ A review on deep reinforcement learning for fluid mechanics ⋮ Control of chaotic systems by deep reinforcement learning ⋮ Reinforcement-learning-based control of confined cylinder wakes with stability analyses ⋮ Prediction of turbulent heat transfer using convolutional neural networks ⋮ Cluster-based feedback control of turbulent post-stall separated flows ⋮ Stabilization of the fluidic pinball with gradient-enriched machine learning control ⋮ Robust flow control and optimal sensor placement using deep reinforcement learning ⋮ Explorative gradient method for active drag reduction of the fluidic pinball and slanted Ahmed body ⋮ Reinforcement-learning-based control of convectively unstable flows ⋮ Reinforcement-learning-based actuator selection method for active flow control ⋮ A transformer-based synthetic-inflow generator for spatially developing turbulent boundary layers
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Machine learning control -- taming nonlinear dynamics and turbulence
- Automated solution of differential equations by the finite element method. The FEniCS book
- A multistep technique with implicit difference schemes for calculating two- or three-dimensional cavity flows
- Multilayer feedforward networks are universal approximators
- On the computational power of neural nets
- Closed-loop control of unsteadiness over a rounded backward-facing step
- Feedback shear layer control for bluff body drag reduction
- Closed-loop control of an open cavity flow using reduced-order models
- Using Non-Normality for Passive Laminar Flow Control
- Gmsh: A 3-D finite element mesh generator with built-in pre- and post-processing facilities
- Deep learning in fluid dynamics
- Algorithm 832
- A large-scale control strategy for drag reduction in turbulent boundary layers
This page was built for publication: Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control