Completed
Deep reinforcement learning for flow control Introduction
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Modelling and Controlling Turbulent Flows through Deep Learning
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Modeling and controlling turbulent flow through deep learning
- 3 Motivation
- 4 Effect of Reynolds number for a given pressure gradient history: well-resolved LES
- 5 Adaptive simulations of NACA0012 profile with rounded wing tip
- 6 High-fidelity simulation of wing-tip vortex at Rec-200,000 and 5 degree angle of attack
- 7 Applications of machine learning to fluid mechanics
- 8 Outline of machine-learning applications to fluid mechanics
- 9 Flow reconstruction with a convolutional neu network (CNN)
- 10 CNN architecture
- 11 Turbulence statistics at Re,=550
- 12 Improving training performance: Transfer learning at Re,=180
- 13 Transfer learning from Re,=180 to 550
- 14 From sparse measurements to high-resolution predictions using GANS
- 15 FCN model for predictions closer to the wall
- 16 Self similarity in the overlap region: Off-wall boundary conditions
- 17 Turbulent flow in a simplified urban environment
- 18 CNN-based B-variational autoencoders CNN- Introducing stochasticity
- 19 Orthogonality: determinant of the cross-corre matrix
- 20 Effect of the penalization factor B
- 21 Optimality: ranking CNN-BVAE modes and interpretability
- 22 Deep reinforcement learning for flow control Introduction
- 23 Control of a 2D separation bubble
- 24 DRL and opposition control in turbulent channel flow: blowing and suction
- 25 Summary and Conclusions
