Parameterised non-intrusive reduced-order model for general unsteady flow problems using artificial neural networks

Sugar-Gabor, O ORCID: https://orcid.org/0000-0001-6366-9623 2021, 'Parameterised non-intrusive reduced-order model for general unsteady flow problems using artificial neural networks' , International Journal for Numerical Methods in Fluids, 93 (5) , pp. 1309-1331.

Preview

PDF - Accepted Version Download (1MB) | Preview

Abstract

A non-intrusive reduced-order model for nonlinear parametric flow problems is developed. It is based on extracting a reduced-order basis from high-order snapshots via proper orthogonal decomposition and using multi-layered feedforward artificial neural networks to approximate the reduced-order coefficients. The model is a generic and efficient approach for the reduction of time-dependent parametric systems, including those described by partial differential equations. Since it is non-intrusive, it is independent of the high-order computational method and can be used together with black-box solvers. Numerical studies are presented for steadystate isentropic nozzle flow with geometric parameterisation and unsteady parameterised viscous Burgers equation. An adaptive sampling strategy is proposed to increase the quality of the neural network approximation while minimising the required number of parameter samples and, as a direct consequence, the number of high-order snapshots and the size of the network training set. Results confirm the accuracy of the non-intrusive approach as well as the speed-up achieved compared with intrusive hyper reduced-order approaches.

Actions (login required)

Edit record (repository staff only)