Contribution to a conference proceedings

FZJ-2023-02166

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Parallel and Scalable Deep Learning to Reconstruct Actuated Turbulent Boundary Layer Flows. Part I: Investigation of Autoencoder-Based Trainings

Sarma, R. (Corresponding author)FZJ* ; Albers, M.RWTH* ; Inanc, E.FZJ* ; Aach, M.FZJ* ; Schröder, W.RWTH* ; Lintermann, A.FZJ*

2022

Please use a persistent id in citations: http://hdl.handle.net/2128/34555

Abstract: With the availability of large datasets and increasing high-performance computing resources, machine learning tools offer many opportunities to improve and/or augment numerical methods used in the field of computational fluid dynamics. A low-dimensional representation of a turbulent boundary layer flow field is generated by a plain and a physics-contrained autoencoder. The training makes use of a distributed learning environment. The average test error of the plain autoencoder is ~4.4 times smaller than the error of the physics-constrained autoencoder although the latter integrates physical laws in the training process. Furthermore, after 1,000 epochs, the training loss of the physics-constrained autoencoder is ~9.1 times higher than the plain autoencoder after 300 epochs. The neural network corresponding to the plain autoencoder is able to provide accurate reconstructions of a turbulent boundary layer flow.

---

Contributing Institute(s):

1. Jülich Supercomputing Center (JSC)

Research Program(s):

1. 5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511) (POF4-511)
2. RAISE - Research on AI- and Simulation-Based Engineering at Exascale (951733) (951733)

Appears in the scientific report 2023

---

Database coverage:

---