Search

The continuous development of machine learning algorithms has stimulated the technological revolution on turbulence modeling for Reynolds-averaged Navier–Stokes (RANS) simulations. In this paper, a computable transition-enabled turbulence model is developed with the aid of an artificial neural network (ANN), which maps the relation between the mean flow variables from the shear stress transport (SST) model on coarse grid and the turbulent viscosity from SST- γ model on fine grid. It turns out that the ANN model can predict the aerodynamic integral quantities, transition onset location, laminar separation bubble structure, streamwise velocity distribution, etc. with superior accuracy and robustness for subsonic and moderate transonic airfoil flows. Meanwhile, the ANN model can significantly improve the convergence property with a much higher convergence speed of the model equation in comparison with traditional transition-enabled RANS model. Moreover, due to the lack of solving RANS model equations and use of grid interpolation technology, the computation speed of this ANN model is improved by a factor of about six over the conventional benchmark model. Therefore, the present computable ANN model provides a new perspective for high-efficiency simulation of transition-characterized flows in engineering applications. • A new transition-turbulence modeling strategy is suggested based on artificial neural network (ANN). • The ANN algorithm provides a corrector for the eddy viscosity in full-turbulence model. • The ANN model is intended to mimic the eddy viscosity in transition-enabled model. • No turbulence model equations need to be solved while retaining a good generalization property. • Grid interpolation and frozen correction help improve the computation efficiency while ensuring the simulation accuracy. [ABSTRACT FROM AUTHOR]

• A unified modeling and coupling framework for turbulence modeling over high Reynolds number airfoils is proposed. • A feature selection method based on the feature importance is proposed. It can effectively reduce the number of features and improve the stability and convergence of coupled computation. • Based on the new features, a data-driven turbulence model is constructed, which has good accuracy and generalization. • Mutual coupling between data-driven turbulence model and CFD solver is realized. In this paper, a turbulence model based on deep neural network is developed for turbulent flow around airfoil at high Reynolds numbers. According to the data got from the Spalart-Allmaras (SA) turbulence model, we build a neural network model that maps flow features to eddy viscosity. The model is then used to replace the SA turbulence model to mutually couple with the CFD solver. We build this suitable data-driven turbulence model mainly from the inputs, outputs features and loss function of the model. A feature selection method based on feature importance is also implemented. The results show that this feature selection method can effectively remove redundant features. The model based on the new input features has better accuracy and stability in mutual coupling with the CFD solver. The force coefficient obtained from solution can match the sample data well. The developed model also shows strong generalization at different inflow condition (angle of attack, Mach number, Reynolds number and airfoil). [ABSTRACT FROM AUTHOR]

• For CFD data, a local key time steps selection method based on DML is proposed. • Compared with one of the existing methods, ours yields better selection results. • The good generalization of the proposed method is demonstrated. As one of the main technologies of flow visualization, key time steps selection plays a key role in solving storage limit and has been intensively studied. In this paper, we introduce Deep Metric Learning (DML) into key time steps selection for Computational Fluid Dynamics (CFD) data and propose a local selection method based on DML. In specific, the proposed method samples small patches from CFD data, trains a Siamese deep neural network which has a symmetry structure with two Convolutional Neural Networks (CNN), and then selects the key time steps according to the similarities between consecutive time steps which are assessed by the networks. Compared with one of the existing local selection methods, the Myers's method, our method has advantages in accuracy, precision and recall, and the selection results are better. Experimental results also demonstrate the good generalization of the proposed method on CFD datasets. [ABSTRACT FROM AUTHOR]