Главная
Study mode:
on
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
Description:
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only! Grab it Explore a comprehensive webinar on modelling and controlling turbulent flows through deep learning, led by Ricardo Vinuesa as part of the Data-Centric Engineering Webinar Series. Delve into advanced topics such as the effect of Reynolds number on well-resolved LES, adaptive simulations of NACA0012 profile, and high-fidelity simulations of wing-tip vortices. Discover various applications of machine learning in fluid mechanics, including flow reconstruction using convolutional neural networks (CNN), transfer learning techniques, and generative adversarial networks (GANs) for high-resolution predictions. Examine the use of CNN-based β-variational autoencoders for introducing stochasticity and improving interpretability in turbulent flow modeling. Investigate deep reinforcement learning approaches for flow control, including the control of 2D separation bubbles and opposition control in turbulent channel flow. This 50-minute presentation, hosted by Cambridge University Press, offers valuable insights into cutting-edge data-centric engineering techniques for researchers, engineers, and professionals interested in the intersection of data science and fluid dynamics. Read more

Modelling and Controlling Turbulent Flows through Deep Learning

Cambridge University Press
Add to list
#Computer Science #Deep Learning #Machine Learning #Reinforcement Learning #Science #Physics #Fluid Mechanics #Fluid Dynamics #Computational Fluid Dynamics #Turbulent Flows #Variational Autoencoders
0:00 / 0:00
1 of 25

Intro