WindsorML: High-Fidelity Computational Fluid Dynamics Dataset For Automotive Aerodynamics

2024-07-27

arXiv.org

AI Summary

A lack of large-scale, high-fidelity, open-source computational fluid dynamics (CFD) datasets for automotive aerodynamics hinders the application of machine learning (ML) in aerodynamic optimization. To address this, we introduce the first open-source, high-fidelity CFD dataset specifically designed for automotive design—released under a CC-BY-SA license. The dataset comprises 355 geometric variants of the Windsor vehicle body, each simulated using GPU-accelerated wall-modeled large-eddy simulation (WMLES) on Cartesian grids with over 280 million cells. Geometries are discretized via an immersed boundary method and high-resolution structured mesh generation. Outputs include three-dimensional time-averaged flow fields, parametric geometry descriptors, and aerodynamic force and moment coefficients. The dataset captures canonical flow features of real-world road vehicles and undergoes rigorous CFD methodology validation. Experiments demonstrate that this dataset substantially improves the generalizability and reliability of ML surrogate models for cross-geometry aerodynamic prediction.

Technology Category

• Application Domains: Mobility, Driving & Flight
• Machine Learning: Hardware-aware ML
• Computer Vision: 3D Computer Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Web data generation and simulation
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

This paper presents a new open-source high-fidelity dataset for Machine Learning (ML) containing 355 geometric variants of the Windsor body, to help the development and testing of ML surrogate models for external automotive aerodynamics. Each Computational Fluid Dynamics (CFD) simulation was run with a GPU-native high-fidelity Wall-Modeled Large-Eddy Simulations (WMLES) using a Cartesian immersed-boundary method using more than 280M cells to ensure the greatest possible accuracy. The dataset contains geometry variants that exhibits a wide range of flow characteristics that are representative of those observed on road-cars. The dataset itself contains the 3D time-averaged volume&boundary data as well as the geometry and force&moment coefficients. This paper discusses the validation of the underlying CFD methods as well as contents and structure of the dataset. To the authors knowledge, this represents the first, large-scale high-fidelity CFD dataset for the Windsor body with a permissive open-source license (CC-BY-SA).

Problem

• Automotive Aerodynamics
• Machine Learning
• Dataset

Innovation

• WindsorML Dataset
• Automotive Aerodynamics
• Machine Learning