DrivAer Transformer: A high-precision and fast prediction method for vehicle aerodynamic drag coefficient based on the DrivAerNet++ dataset

Abstract

At the current stage, deep learning-based methods have demonstrated excellent capabilities in evaluating aerodynamic performance, significantly reducing the time and cost required for traditional computational fluid dynamics (CFD) simulations. However, when faced with the task of processing extremely complex three-dimensional (3D) vehicle models, the lack of large-scale datasets and training resources, coupled with the inherent diversity and complexity of the geometry of different vehicle models, means that the prediction accuracy and versatility of these networks are still not up to the level required for current production. In view of the remarkable success of Transformer models in the field of natural language processing and their strong potential in the field of image processing, this study innovatively proposes a point cloud learning framework called DrivAer Transformer (DAT). The DAT structure uses the DrivAerNet++ dataset, which contains high-fidelity CFD data of industrial-standard 3D vehicle shapes. enabling accurate estimation of air drag directly from 3D meshes, thus avoiding the limitations of traditional methods such as 2D image rendering or signed distance fields (SDF). DAT enables fast and accurate drag prediction, driving the evolution of the aerodynamic evaluation process and laying the critical foundation for introducing a data-driven approach to automotive design. The framework is expected to accelerate the vehicle design process and improve development efficiency.

14 pages

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• PCT: Point cloud transformer
• Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
• Learning to Simulate Complex Physics with Graph Networks
• Physics-informed PointNet: A deep learning solver for steady-state incompressible flows and thermal fields on multiple sets of irregular geometries
• CFDNet: a deep learning-based accelerator for fluid simulations
• DeepCFD: Efficient Steady-State Laminar Flow Approximation with Deep Convolutional Neural Networks
• Learning Mesh-Based Simulation with Graph Networks
• Geodesic Convolutional Shape Optimization
• Deep Learning for Real-Time Aerodynamic Evaluations of Arbitrary Vehicle Shapes
• MeshSDF: Differentiable Iso-Surface Extraction
• Transolver: A Fast Transformer Solver for PDEs on General Geometries
• Activate or Not: Learning Customized Activation
• DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks
• Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training
• Surrogate Modeling of Car Drag Coefficient with Depth and Normal Renderings
• Transolver++: An Accurate Neural Solver for PDEs on Million-Scale Geometries