No Cover Image

Journal article 574 views

Model identification of reduced order fluid dynamics systems using deep learning

Z. Wang, Dunhui Xiao Orcid Logo, F. Fang, R. Govindan, C. C. Pain, Y. Guo

International Journal for Numerical Methods in Fluids, Volume: 86, Issue: 4, Pages: 255 - 268

Swansea University Author: Dunhui Xiao Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1002/fld.4416

Abstract

This paper presents a novel model reduction method: deep learning reduced order model, which is based on proper orthogonal decomposition and deep learning methods. The deep learning approach is a recent technological advancement in the field of artificial neural networks. It has the advantage of lea...

Full description

Published in: International Journal for Numerical Methods in Fluids
ISSN: 0271-2091
Published: Wiley 2018
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa46449
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: This paper presents a novel model reduction method: deep learning reduced order model, which is based on proper orthogonal decomposition and deep learning methods. The deep learning approach is a recent technological advancement in the field of artificial neural networks. It has the advantage of learning the nonlinear system with multiple levels of representation and predicting data. In this work, the training data are obtained from high fidelity model solutions at selected time levels. The long short‐term memory network is used to construct a set of hypersurfaces representing the reduced fluid dynamic system. The model reduction method developed here is independent of the source code of the full physical system.The reduced order model based on deep learning has been implemented within an unstructured mesh finite element fluid model. The performance of the new reduced order model is evaluated using 2 numerical examples: an ocean gyre and flow past a cylinder. These results illustrate that the CPU cost is reduced by several orders of magnitude whilst providing reasonable accuracy in predictive numerical modelling.
Keywords: deep learning, LSTM, POD, ROM
College: Faculty of Science and Engineering
Issue: 4
Start Page: 255
End Page: 268