A turbulence model based on deep neural network considering the near-wall effect

TL;DR

This paper introduces a deep neural network-based turbulence model that incorporates near-wall effects and local turbulence Reynolds number, improving Reynolds stress predictions in RANS simulations.

Contribution

The paper develops a DNN turbulence model that explicitly considers near-wall effects and the local turbulence Reynolds number, enhancing accuracy over traditional models.

Findings

DNN model accurately predicts Reynolds stresses in channel flow.

Including local turbulence Reynolds number improves model performance.

Model construction and tuning are detailed for practical implementation.

Abstract

There exists continuous demand of improved turbulence models for the closure of Reynolds Averaged Navier-Stokes (RANS) simulations. Machine Learning (ML) offers effective tools for establishing advanced empirical Reynolds stress closures on the basis of high fidelity simulation data. This paper presents a turbulence model based on the Deep Neural Network(DNN) which takes into account the non-linear relationship between the Reynolds stress anisotropy tensor and the local mean velocity gradient as well as the near-wall effect. The construction and the tuning of the DNN-turbulence model are detailed. We show that the DNN-turbulence model trained on data from direct numerical simulations yields an accurate prediction of the Reynolds stresses for plane channel flow. In particular, we propose including the local turbulence Reynolds number in the model input.