Journal of Fluid Mechanics· 2016Q1
Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
- 1,615citations
- Q1SCImago
- 2016year
Short summary
A novel deep neural network architecture embeds Galilean invariance to predict Reynolds stress anisotropy, improving accuracy over generic networks and baseline RANS models in velocity field predictions for two test cases.
AI-generated from the title and abstract; the full text is not read.
Key points
- A novel DNN architecture embeds Galilean invariance using a multiplicative layer with an invariant tensor basis.
- The invariant DNN architecture shows improved prediction accuracy for Reynolds stress anisotropy compared to a generic DNN.
- Velocity field predictions using the invariant DNN show significant improvement over baseline RANS linear and nonlinear eddy viscosity models.
- The method is demonstrated on two test cases, indicating broad applicability.
AI-generated from the title and abstract; the full text is not read.
Abstract
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.
The authors' abstract, as published at the source. Journal of Fluid Mechanics, 2016 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computational Mechanics
Computational MechanicsEngineering