Busca avançada
Ano de início
Entree
(Referência obtida automaticamente do Web of Science, por meio da informação sobre o financiamento pela FAPESP e o número do processo correspondente, incluída na publicação pelos autores.)

Construction of reduced-order models for fluid flows using deep feedforward neural networks

Texto completo
Autor(es):
Lui, Hugo F. S. [1] ; Wolf, William R. [1]
Número total de Autores: 2
Afiliação do(s) autor(es):
[1] Univ Estadual Campinas, Sch Mech Engn, BR-13083860 Campinas, SP - Brazil
Número total de Afiliações: 1
Tipo de documento: Artigo Científico
Fonte: JOURNAL OF FLUID MECHANICS; v. 872, p. 963-994, AUG 10 2019.
Citações Web of Science: 0
Resumo

We present a numerical methodology for construction of reduced-order models (ROMs) of fluid flows through the combination of flow modal decomposition and regression analysis. Spectral proper orthogonal decomposition is applied to reduce the dimensionality of the model and, at the same time, filter the proper orthogonal decomposition temporal modes. The regression step is performed by a deep feedforward neural network (DNN), and the current framework is implemented in a context similar to the sparse identification of nonlinear dynamics algorithm. A discussion on the optimization of the DNN hyperparameters is provided for obtaining the best ROMs and an assessment of these models is presented for a canonical nonlinear oscillator and the compressible flow past a cylinder. Then the method is tested on the reconstruction of a turbulent flow computed by a large eddy simulation of a plunging airfoil under dynamic stall. The reduced-order model is able to capture the dynamics of the leading edge stall vortex and the subsequent trailing edge vortex. For the cases analysed, the numerical framework allows the prediction of the flow field beyond the training window using larger time increments than those employed by the full-order model. We also demonstrate the robustness of the current ROMs constructed via DNNs through a comparison with sparse regression. The DNN approach is able to learn transient features of the flow and presents more accurate and stable long-term predictions compared to sparse regression. (AU)

Processo FAPESP: 13/07375-0 - CeMEAI - Centro de Ciências Matemáticas Aplicadas à Indústria
Beneficiário:José Alberto Cuminato
Linha de fomento: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs
Processo FAPESP: 13/08293-7 - CECC - Centro de Engenharia e Ciências Computacionais
Beneficiário:Munir Salomao Skaf
Linha de fomento: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs