TY - JOUR
T1 - Real-Time Computing for a Parameterized Feedback Control Problem of Boussinesq Equations by POD and Deep Learning
AU - Piao , Guang-Ri
AU - Lee , Hyung-Chun
JO - East Asian Journal on Applied Mathematics
VL - 3
SP - 507
EP - 529
PY - 2024
DA - 2024/05
SN - 14
DO - http://doi.org/10.4208/eajam.2023-094.250623
UR - https://global-sci.org/intro/article_detail/eajam/23159.html
KW - Optimal control, feedback control, Boussinesq, finite element, POD, LSTM.
AB - <p style="text-align: justify;">An efficient real-time computational method for a feedback control problem
of the Boussinesq equations is studied. We consider a simple and effective feedback control law based on the relationship between the control and adjoint variables in the optimality system. We investigate a closure type 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, which is currently being actively researched,
is studied and applied. Computational results presented show that the suggested methods work well.</p>