Deep Learning for Real-Time Aerodynamic Evaluations of Arbitrary Vehicle Shapes

by   Sam Jacob Jacob, et al.

The aerodynamic optimization process of cars requires multiple iterations between aerodynamicists and stylists. Response Surface Modeling and Reduced-Order Modeling are commonly used to eliminate the overhead due to Computational Fluid Dynamics, leading to faster iterations. However, a primary drawback of these models is that they can work only on the parametrized geometric features they were trained with. This study evaluates if deep learning models can predict the drag coefficient for an arbitrary input geometry without explicit parameterization. We use two similar data sets based on the publicly available DrivAer geometry for training. We use a modified U-Net architecture that uses Signed Distance Fields to represent the input geometries. Our models outperform the existing models by at least 11 prediction accuracy for the drag coefficient. We achieved this improvement by combining multiple data sets that were created using different parameterizations, which is not possible with the methods currently used. We have also shown that it is possible to predict velocity fields and drag coefficient concurrently and that simple data augmentation methods can improve the results. In addition, we have performed an occlusion sensitivity study on our models to understand what information is used to make predictions. From the occlusion sensitivity study, we showed that the models were able to identify the geometric features and have discovered that the model has learned to exploit the global information present in the SDF. In contrast to the currently operational method, where design changes are restricted to the initially defined parameters, this study brings surrogate models one step closer to the long-term goal of having a model that can be used for approximate aerodynamic evaluation of unseen, arbitrary vehicle shapes, thereby providing complete design freedom to the vehicle stylists.


page 2

page 3

page 4

page 5

page 8

page 9

page 10


Surrogate Modeling of Fluid Dynamics with a Multigrid Inspired Neural Network Architecture

Algebraic or geometric multigrid methods are commonly used in numerical ...

Towards Reusable Surrogate Models: Graph-Based Transfer Learning on Trusses

Surrogate models have several uses in engineering design, including spee...

U-Net-Based Surrogate Model For Evaluation of Microfluidic Channels

Microfluidics have shown great promise in multiple applications, especia...

Tropical and Extratropical Cyclone Detection Using Deep Learning

Extracting valuable information from large sets of diverse meteorologica...

Surrogate Modeling of Car Drag Coefficient with Depth and Normal Renderings

Generative AI models have made significant progress in automating the cr...

Vehicle Behavior Prediction and Generalization Using Imbalanced Learning Techniques

The use of learning-based methods for vehicle behavior prediction is a p...

Well, how accurate is it? A Study of Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations

With this study we investigate the accuracy of deep learning models for ...

Please sign up or login with your details

Forgot password? Click here to reset