MINDS Seminar Series | Hyung Chun Lee (Ajou University) - Reduced Order Modeling Based on POD and Deep Learning for Parameterized Feedback Control Problems of Fluid Flows
Date |
2021-11-02 ~ 2021-11-02 |
Time |
17:00:00 ~ 18:00 |
Speaker |
Hyung Chun Lee |
Affiliation |
Ajou University |
Place |
Online streaming (Zoom) |
Streaming link |
ID : 688 896 1076 /
PW : 54321 |
Topic |
Reduced Order Modeling Based on POD and Deep Learning for Parameterized Feedback Control Problems of Fluid Flows |
Contents |
An efficient and real-time computational method for a feedback control problem of the fluid flows such as Navier-Stokes equations and Boussinesq equations is considered. We consider a simple and effective feedback control law based on the relationship between the controls and the adjoint variables in the optimality system. We investigate a closure modeling in reduced order model (ROM) of this problem for real-time computing. In order to improve the existing well-known POD-ROM method, the deep learning technique with closure model, which is currently being actively researched, is studied and applied. Some computational results are also presented to show that the methods suggested in this article work well. |