Generalizability of transformer-based deep learning for multidimensional turbulent flow data
Physics of Fluids · 2024-02-01 · 36 (2)
DOI: 10.1063/5.0189366 ↗At a glance
Journal article in Physics of Fluids, published online on 2024-02-01. Written by Dimitris Drikakis and 3 co-authors. Cited 26 times so far (Crossref); 73 references. Funded by: European Office of Aerospace Research and Development.
Abstract (original language)
Deep learning has been going through rapid advancement and becoming useful in scientific computation, with many opportunities to be applied to various fields, including but not limited to fluid flows and fluid–structure interactions. High-resolution numerical simulations are computationally expensive, while experiments are equally demanding and encompass instrumentation constraints for obtaining flow, acoustics and structural data, particularly at high flow speeds. This paper presents a Transformer-based deep learning method for turbulent flow time series data. Turbulent signals across spatiotemporal and geometrical variations are investigated. The pressure signals are coarsely-grained, and the Transformer creates a fine-grained pressure signal. The training includes data across spatial locations of compliant panels with static deformations arising from the aeroelastic effects of shock-boundary layer interaction. Different training approaches using the Transformer were investigated. Evaluations were carried out using the predicted pressure signal and their power spectra. The Transformer's predicted signals show promising performance. The proposed method is not limited to pressure fluctuations and can be extended to other turbulent or turbulent-like signals.
Funding
- European Office of Aerospace Research and Development
Cite
APA
Drikakis, D., Kokkinakis, I. W., Fung, D., & Spottswood, S. M. (2024). Generalizability of transformer-based deep learning for multidimensional turbulent flow data. Physics of Fluids, 36(2). https://doi.org/10.1063/5.0189366
Vancouver
Drikakis D, Kokkinakis IW, Fung D, Spottswood SM. Generalizability of transformer-based deep learning for multidimensional turbulent flow data. Physics of Fluids. 2024;36(2). doi:10.1063/5.0189366
BibTeX
@article{Drikakis2024,
author = {Drikakis, Dimitris and Kokkinakis, Ioannis William and Fung, Daryl and Spottswood, S. Michael},
title = {Generalizability of transformer-based deep learning for multidimensional turbulent flow data},
journal = {Physics of Fluids},
year = {2024},
volume = {36},
number = {2},
doi = {10.1063/5.0189366}
}
EUVIMED