Busca avançada
Ano de início
Entree


Assessing the robustness of neural networks trained for closed loop flow stabilization

Autor(es):
Deda, Tarcisio C. ; Wolf, William R. ; Dawson, Scott T. M.
Número total de Autores: 3
Tipo de documento: Artigo Científico
Fonte: AIAA AVIATION FORUM AND ASCEND 2024; v. N/A, p. 10-pg., 2024-01-01.
Resumo

We explore the application of neural networks for developing surrogate models and controllers aiming for closed-loop stabilization. Leveraging a grid of velocity sensors in a confined cylinder wake, convergence to equilibrium is demonstrated. The methodology, developed in previous work, involves training neural network surrogate models (NNSMs) that are leveraged for designing neural network controllers (NNCs). During the training of NNSMs, sensor selection minimizes the number of probes required by implementing a sparsity layer within the neural network architecture. Equilibrium estimation, required for providing a control setpoint, is achieved through the Newton method applied to the NNSMs. The networks are trained iteratively, with progressive improvements as more data near equilibrium becomes available. The present work focuses on analyses conducted to assess the robustness of these trained NNCs. First, we show the main results involving a series of tests conducted with the Lorenz system, in which we verify the behavior of the closed-loop system subject to phenomena such as plant variations, measurement noise and disturbances. A controller is then trained to stabilize a confined cylinder flow at Reynolds number Re = 150. We subsequently demonstrate that the controller is able to stabilize unstable flows at lower and higher Reynolds numbers than that for which the NNC was trained. As the Reynolds number increases, we find that reducing the timestep at which control is applied can be required to achieve complete stabilization. (AU)

Processo FAPESP: 19/19179-7 - Estratégias de controle de escoamentos aplicadas a escoamentos não estacionários com transição e turbulência
Beneficiário:Tarcísio Costa Déda Oliveira
Modalidade de apoio: Bolsas no Brasil - Doutorado
Processo FAPESP: 13/08293-7 - CECC - Centro de Engenharia e Ciências Computacionais
Beneficiário:Munir Salomao Skaf
Modalidade de apoio: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs
Processo FAPESP: 21/06448-0 - Simulações numéricas de alta fidelidade aplicadas em aerodinâmica não-estacionária, turbulência e aeroacústica
Beneficiário:William Roberto Wolf
Modalidade de apoio: Auxílio à Pesquisa - Jovens Pesquisadores - Fase 2
Processo FAPESP: 22/00469-8 - Estratégias de aprendizado profundo aplicadas ao controle em malha fechada de escoamentos não-estacionários
Beneficiário:Tarcísio Costa Déda Oliveira
Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Doutorado