DrivAerML: High-Fidelity Computational Fluid Dynamics Dataset for Road-Car External Aerodynamics

2024-08-21

arXiv.org

AI Summary

The automotive aerodynamics community lacks high-fidelity, open-source computational fluid dynamics (CFD) training data for real-world vehicles, severely hindering machine learning (ML) applications in rapid aerodynamic prediction. Method: We construct the first open-source, high-fidelity CFD dataset for realistic road vehicles: 500 parametric variants of the DrivAer notchback model are generated; automated unstructured meshing and scale-resolving simulations (LES/DES) are performed using an industrial-grade open-source toolchain, ensuring end-to-end standardization from geometry to simulation to data. Contribution/Results: The dataset comprises full CAD models, unstructured meshes, three-dimensional pressure and velocity fields, and aerodynamic force coefficients—all released under the CC-BY-SA license. It is the first large-scale, industrially accurate, fully open dataset of external flow fields around complete vehicles, significantly lowering the barrier to ML model training and filling a critical gap in high-fidelity, whole-vehicle CFD data.

Technology Category

• Application Domains: Mobility, Driving & Flight
• Machine Learning: Hardware-aware ML
• Computer Vision: Large Vision Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• 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

Abstract

Machine Learning (ML) has the potential to revolutionise the field of automotive aerodynamics, enabling split-second flow predictions early in the design process. However, the lack of open-source training data for realistic road cars, using high-fidelity CFD methods, represents a barrier to their development. To address this, a high-fidelity open-source (CC-BY-SA) public dataset for automotive aerodynamics has been generated, based on 500 parametrically morphed variants of the widely-used DrivAer notchback generic vehicle. Mesh generation and scale-resolving CFD was executed using consistent and validated automatic workflows representative of the industrial state-of-the-art. Geometries and rich aerodynamic data are published in open-source formats. To our knowledge, this is the first large, public-domain dataset for complex automotive configurations generated using high-fidelity CFD.

Problem

• Lack of open-source training data for realistic road cars
• Need for high-fidelity CFD methods in automotive aerodynamics
• Absence of large public datasets for complex automotive configurations

Innovation

• High-fidelity CFD dataset for road cars
• Parametric morphing of DrivAer vehicle
• Automated mesh generation and CFD workflows