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

2024-03-12

Design Automation Conference

AI Summary

This work addresses the scarcity of high-fidelity aerodynamic data and the computational inefficiency of rapid performance evaluation in automotive aerodynamic design. To this end, we introduce DrivAerNet—the first open-source, high-fidelity CFD dataset comprising 4,000 three-dimensional surface meshes of full-vehicle configurations (including underbody and wheels), each containing ~500,000 triangular faces—representing a 60% scale increase over the largest prior public dataset. We further propose RegDGCNN, a dynamic graph convolutional neural network that enables end-to-end regression of aerodynamic drag directly from raw 3D mesh inputs, eliminating reliance on 2D renderings or signed distance functions. Our model achieves a drag coefficient prediction error of less than 2.1% and inference time under 3 seconds per geometry. All code, data, and trained models are publicly released to foster reproducible research and community advancement.

Technology Category

• Computer Vision: 3D Computer Vision
• Application Domains: Mobility, Driving & Flight
• Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

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/DrivAerNet.

Problem

• Large-scale CFD dataset for aerodynamic car design
• Dynamic graph CNN for high-precision drag estimation
• Public dataset and code for future innovations

Innovation

• Large-scale high-fidelity CFD dataset
• Dynamic graph convolutional neural network
• Fast drag estimation from 3D meshes