Fast Prediction of Flow Field around Airfoils Based on Deep Convolutional Neural Network

Abstract

We propose a steady-state aerodynamic data-driven method to predict the incompressible flow around airfoils of NACA (National Advisory Committee for Aeronautics) 0012-series. Using the Signed Distance Function (SDF) to parameterize the geometric and flow condition setups, the prediction core of the method is constructed essentially by a consecutive framework of a convolutional neural network (CNN) and a deconvolutional neural network (DCNN). Impact of training parameters on the behavior of the proposed CNN-DCNN model is studied, so that appropriate learning rate, mini-batch size, and random deactivation rate are specified. Tested by “unseen” airfoil geometries and far-field velocities, it is found that the prediction process is three orders of magnitudes faster than a corresponding Computational Fluid Dynamics (CFD) simulation, while relative errors are maintained lower than 1% on most of the sample points. The proposed model manages to capture the essential dynamics of the flow field, as its predictions correspond reasonably with the reconstructed field by proper orthogonal decomposition (POD). The performance and accuracy of the proposed model indicate that the deep learning-based approach has great potential as a robust predictive tool for aerodynamic design and optimization.

On the Hard Boundary Constraint Method for Fluid Flow Prediction based on the Physics-Informed Neural Network

“…Depending on the manners by which the ML approaches are integrated with CFD solvers, ML approaches for fluid mechanics can be roughly categorized into three classes, i.e., data-fit models, projection-based models and physics-informed models. A data-fit model is usually based on the artificial neural network (ANN) [5,6], radial basis function (RBF) [7] and support vector regression (SVR) [8,9], and it treats a CFD solver as a black box and is essentially a fast, inexpensive but approximate model that extracts mechanisms underlying the complex system from available data in a supervised manner. Data-fit models have been widely used as a substitute for expensive CFD simulations in design optimization or uncertainty quantification of fluid systems [10].…”

Prediction of Transonic Flow over Cascades via Graph Embedding Methods on Large-Scale Point Clouds

“…The proposed model achieved a mean squared error of less than 2% for test cases. Wu et al [21] proposed a CNN-DCNN model, tested the influence of training parameters, and quantified the feature extraction capabilities of the presented model. Despite CNN demonstrating excellent predictive performance, precision, and the ability to capture inherent flow characteristics, particularly in the context of airfoil flow-field prediction, the capability of CNN in handling unstructured flow-field data remains suboptimal, particularly in practical applications with irregular flow path structure [22,23].…”

Fast Flapping Aerodynamics Prediction Using a Recurrent Neural Network

“…However, these simulations can easily become very computationally intensive. In an attempt to reduce the computational burden of CFD simulations, several Reduced Order Models (ROM) have been developed, but these lack good generalization capabilities and struggle when dealing with dynamic, non-linear, aerodynamic phenomena [4,5].…”

“…Also, once trained, they are able to produce accurate predictions very quickly [6]. Examples of such applications include the works of Zhang et al [4], Peng et al [7], Wu et al [5], Balla et al [6], and Moin et al [1].…”