Machine Learning to Predict Aerodynamic Stall
This work addresses aerodynamic prediction for engineering applications, but it is incremental as it applies an existing autoencoder method to a specific domain problem.
The researchers tackled the problem of predicting aerodynamic stall by training a convolutional autoencoder on airfoil simulation data, achieving interpretable results through latent space analysis and enabling synthetic data generation via decoder interpolation/extrapolation.
A convolutional autoencoder is trained using a database of airfoil aerodynamic simulations and assessed in terms of overall accuracy and interpretability. The goal is to predict the stall and to investigate the ability of the autoencoder to distinguish between the linear and non-linear response of the airfoil pressure distribution to changes in the angle of attack. After a sensitivity analysis on the learning infrastructure, we investigate the latent space identified by the autoencoder targeting extreme compression rates, i.e. very low-dimensional reconstructions. We also propose a strategy to use the decoder to generate new synthetic airfoil geometries and aerodynamic solutions by interpolation and extrapolation in the latent representation learned by the autoencoder.