DrivAerNet: A Parametric Car Dataset for Data-Driven Aerodynamic Design and Graph-Based Drag Prediction

Mohamed Elrefaie, Angela Dai, Faez Ahmed

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This study introduces DrivAerNet, a large-scale high-fidelity CFD dataset of 3D industry-standard car shapes, and RegDGCNN, a dynamic graph convolutional neural network model, both aimed at aerodynamic car design through machine learning. DrivAerNet, with its 4000 detailed 3D car meshes using 0.5 million surface mesh faces and comprehensive aerodynamic performance data comprising of full 3D pressure, velocity fields, and wall-shear stresses, addresses the critical need for extensive datasets to train deep learning models in engineering applications. It is 60% larger than the previously available largest public dataset of cars, and is the only open-source dataset that also models wheels and underbody. RegDGCNN leverages this large-scale dataset to provide high-precision drag estimates directly from 3D meshes, bypassing traditional limitations such as the need for 2D image rendering or Signed Distance Fields (SDF). By enabling fast drag estimation in seconds, RegDGCNN facilitates rapid aerodynamic assessments, offering a substantial leap towards integrating data-driven methods in automotive design. Together, DrivAerNet and RegDGCNN promise to accelerate the car design process and contribute to the development of more efficient vehicles. To lay the groundwork for future innovations in the field, the dataset and code used in our study are publicly accessible at https://github.com/Mohamedelrefaie/DrivAerNet1.

Original languageEnglish
Title of host publication50th Design Automation Conference (DAC)
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791888360
DOIs
StatePublished - 2024
EventASME 2024 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC-CIE 2024 - Washington, United States
Duration: 25 Aug 202428 Aug 2024

Publication series

NameProceedings of the ASME Design Engineering Technical Conference
Volume3A-2024

Conference

ConferenceASME 2024 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC-CIE 2024
Country/TerritoryUnited States
CityWashington
Period25/08/2428/08/24

Keywords

  • Car Aerodynamics
  • Computational Fluid Dynamics
  • Graph Neural Networks
  • Parametric Design
  • Surrogate Modeling

Fingerprint

Dive into the research topics of 'DrivAerNet: A Parametric Car Dataset for Data-Driven Aerodynamic Design and Graph-Based Drag Prediction'. Together they form a unique fingerprint.

Cite this