Learning neural-network-based turbulence models for external transonic flows using ensemble Kalman method

TL;DR

This paper introduces a neural network turbulence model trained with the ensemble Kalman method for transonic flows, effectively capturing complex shock and compressibility effects in 2D and 3D configurations.

Contribution

It develops a tensor basis neural network turbulence model with modified inputs for compressibility and trains it using ensemble Kalman filtering, a novel approach for transonic flow modeling.

Findings

Accurately predicts turbulence in transonic flows over airfoils and wings.

Demonstrates robustness of the neural network model in complex flow regimes.

Shows improved turbulence modeling compared to traditional methods.

Abstract

This paper presents a neural network-based turbulence modeling approach for transonic flows based on the ensemble Kalman method. The approach adopts a tensor basis neural network for the Reynolds stress representation, with modified inputs to consider fluid compressibility. The normalization of input features is also investigated to avoid feature collapsing in the presence of shock waves. Moreover, the turbulent heat flux is accordingly estimated with the neural network-based turbulence model based on the gradient diffusion hypothesis. The ensemble Kalman method is used to train the neural network with the experimental data in velocity and wall pressure due to its derivative-free nature. The proposed framework is tested in two canonical configurations, i.e., 2D transonic flows over the RAE2822 airfoils and 3D transonic flows over the ONERA M6 wings. Numerical results demonstrate the capability of the proposed method in learning accurate turbulence models for external transonic flows.