Author: Ling, J.; Kurzawski, A.; Templeton, J.
Description: There exists significant demand for improved Reynolds-averaged Navier–Stokes (RANS) turbulence models that are informed by and can represent a richer set of turbulence physics. This paper presents a method of using deep neural networks to learn a model for the Reynolds stress anisotropy tensor from high-fidelity simulation data. A novel neural network architecture is proposed which uses a multiplicative layer with an invariant tensor basis to embed Galilean invariance into the predicted anisotropy tensor. It is demonstrated that this neural network architecture provides improved prediction accuracy compared with a generic neural network architecture that does not embed this invariance property. The Reynolds stress anisotropy predictions of this invariant neural network are propagated through to the velocity field for two test cases. For both test cases, significant improvement versus baseline RANS linear eddy viscosity and nonlinear eddy viscosity models is demonstrated.
Subject headings: Turbulence modelling
Publication year: 2016
Journal or book title: Journal of Fluid Mechanics
Volume: 807
Issue:
Pages: 155-166
Find the full text :Â https://www.cambridge.org/core/journals/journal-of-fluid-mechanics/article/reynolds-averaged-turbulence-modelling-using-deep-neural-networks-with-embedded-invariance/0B280EEE89C74A7BF651C422F8FBD1EB
Find more like this one (cited by): https://scholar.google.com/scholar?cites=17265256326087997648&as_sdt=1000005&sciodt=0,16&hl=en
Type: Journal Article
Serial number: 2047