A systematic dataset generation technique applied to data-driven automotive aerodynamics

TL;DR

This paper introduces a systematic dataset generation method for automotive aerodynamics, enabling efficient training of neural networks for drag prediction with limited initial data, and demonstrating high accuracy and extrapolation capabilities.

Contribution

A new dataset generation technique that interpolates between few initial data points to improve neural network training for automotive aerodynamic predictions.

Findings

Neural networks accurately predict drag coefficients and surface pressures.

The method shows promising extrapolation performance.

Applicable to aerodynamic shape optimization problems.

Abstract

A novel strategy for generating datasets is developed within the context of drag prediction for automotive geometries using neural networks. A primary challenge in this space is constructing a training databse of sufficient size and diversity. Our method relies on a small number of starting data points, and provides a recipe to interpolate systematically between them, generating an arbitrary number of samples at the desired quality. We test this strategy using a realistic automotive geometry, and demonstrate that convolutional neural networks perform exceedingly well at predicting drag coefficients and surface pressures. Promising results are obtained in testing extrapolation performance. Our method can be applied to other problems of aerodynamic shape optimization.