A wall model for separated flows: embedded learning to improve a posteriori performance

Abstract

The development of a wall model using machine learning methods for the large-eddy simulation (LES) of separated flows is still an unsolved problem. Our approach is to leverage the significance of separated flow data, for which existing theories are not applicable, and the existing knowledge of wall-bounded flows (such as the law of the wall) along with embedded learning to address this issue. The proposed so-called features-embedded-learning (FEL) wall model comprises two submodels: one for predicting the wall shear stress and another for calculating the eddy viscosity at the first off-wall grid nodes. We train the former using the wall-resolved LES data of the periodic hill flow and the law of the wall. For the latter, we propose a modified mixing length model, with the model coefficient trained using the ensemble Kalman method. The proposed FEL model is assessed using the separated flows with different flow configurations, grid resolutions, and Reynolds numbers. Overall good a posteriori performance is observed for predicting the statistics of the recirculation bubble, wall stresses, and turbulence characteristics. The statistics of the modelled subgrid-scale (SGS) stresses at the first off-wall grids are compared with those calculated using the wall-resolved LES data. The comparison shows that the amplitude and distribution of the SGS stresses obtained using the proposed model agree better with the reference data when compared with the conventional wall model.

References in corpus (12)

• RANS Turbulence Model Development using CFD-Driven Machine Learning
• Sub-grid modelling for two-dimensional turbulence using neural networks
• Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
• Grid-point and time-step requirements for direct numerical simulation and large-eddy simulation
• Scientific multi-agent reinforcement learning for wall-models of turbulent flows
• Iterative ensemble smoother as an approximate solution to a regularized minimum-average-cost problem: theory and applications
• Ensemble Kalman method for learning turbulence models from indirect observation data
• Machine learning building-block-flow wall model for large-eddy simulation
• Ensemble Neural Networks (ENN): A gradient-free stochastic method
• Evaluation of ensemble methods for quantifying uncertainties in steady-state CFD applications with small ensemble sizes
• Neural-network-based mixed subgrid-scale model for turbulent flow
• Ensemble data assimilation-based mixed subgrid-scale model for large-eddy simulations

Cited by in corpus (2)

• Machine-learning-based simulation of turbulent flows over periodic hills using a hybrid U-Net and Fourier neural operator framework
• Data-driven detached-eddy simulations based on explicit algebraic stress expressions for turbulent flows