Eventos Anais de eventos
ENCIT 2020
18th Brazilian Congress of Thermal Sciences and Engineering
Application of Convolutional Neural Networks for Surrogate Models of Unsteady Flows
Submission Author:
Hugo Felippe da Silva Lui , SP
Co-Authors:
Hugo Felippe da Silva Lui, William Wolf
Presenter: Hugo Felippe da Silva Lui
doi://10.26678/ABCM.ENCIT2020.CIT20-0223
Abstract
In this work, we present a numerical methodology for construction of surrogate models of fluid flows which combine data-driven system identification and convolutional neural networks. The framework is implemented in a context similar to that of the sparse identification of non-linear dynamics (SINDy) algorithm with some modifications regarding the regression step. The approach presented in this work allows us to obtain an ODE for each flow variable at each mesh point. This should be beneficial for flow control approaches since every flow state can be modified by a control law. The method is tested for an unsteady compressible flow past a cylinder at low Reynolds number. Results demonstrate that the current methodology provides accurate reconstructions of the high fidelity model.
Keywords
Surrogate models, Deep learning, Computational Fluid Dynamics CFD
DOWNLOAD PDF VIEW PRESENTATION
