DrivAerNet: A Parametric Car Dataset for Data-Driven Aerodynamic Design and Graph-Based Drag Prediction
Preprint
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 \url{https://github.com/Mohamedelrefaie/DrivAerNet}Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- On-site aerodynamics using stereoscopic PIV and deep optical flow learningExperiments in Fluids, 2024
- Multi‐fidelity data fusion through parameter space reduction with applications to automotive engineeringInternational Journal for Numerical Methods in Engineering, 2023
- Assessing policy interventions to stimulate the transition of electric vehicle technology in the European UnionSocio-Economic Planning Sciences, 2023
- Physics-informed PointNet: A deep learning solver for steady-state incompressible flows and thermal fields on multiple sets of irregular geometriesJournal of Computational Physics, 2022
- Geometrical deep learning for performance prediction of high-speed craftOcean Engineering, 2022
- Evaluation of CFD methodologies for prediction of flows around simplified and complex automotive modelsComputers & Fluids, 2022
- Point2FFD: Learning Shape Representations of Simulation-Ready 3D Models for Engineering Design Optimization2021
- Road to zero or road to nowhere? Disrupting transport and energy in a zero carbon worldEnergy Policy, 2020
- A Generative Design and Drag Coefficient Prediction System for Sedan Car Side Silhouettes based on Computational Fluid DynamicsComputer-Aided Design, 2019
- Numerical studies of space-filling designs: optimization of Latin Hypercube Samples and subprojection propertiesJournal of Simulation, 2013