Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AFBench: A Large-scale Benchmark for Airfoil Design

Jian Liu, Jianyu Wu, Hairun Xie, Guoqing Zhang, Jing Wang, Wei Liu, Wanli Ouyang, Junjun Jiang, Xianming Liu, Shixiang Tang, Miao Zhang

TL;DR

The aim is to establish \emph{AFBench} as an ecosystem for training and evaluating airfoil inverse design methods, with a specific focus on data-driven controllable inverse design models by multimodal instructions capable of bridging the gap between ideas and execution, the academic research and industrial applications.

Abstract

Data-driven generative models have emerged as promising approaches towards achieving efficient mechanical inverse design. However, due to prohibitively high cost in time and money, there is still lack of open-source and large-scale benchmarks in this field. It is mainly the case for airfoil inverse design, which requires to generate and edit diverse geometric-qualified and aerodynamic-qualified airfoils following the multimodal instructions, \emph{i.e.,} dragging points and physical parameters. This paper presents the open-source endeavors in airfoil inverse design, \emph{AFBench}, including a large-scale dataset with 200 thousand airfoils and high-quality aerodynamic and geometric labels, two novel and practical airfoil inverse design tasks, \emph{i.e.,} conditional generation on multimodal physical parameters, controllable editing, and comprehensive metrics to evaluate various existing airfoil inverse design methods. Our aim is to establish \emph{AFBench} as an ecosystem for training and evaluating airfoil inverse design methods, with a specific focus on data-driven controllable inverse design models by multimodal instructions capable of bridging the gap between ideas and execution, the academic research and industrial applications. We have provided baseline models, comprehensive experimental observations, and analysis to accelerate future research. Our baseline model is trained on an RTX 3090 GPU within 16 hours. The codebase, datasets and benchmarks will be available at \url{https://hitcslj.github.io/afbench/}.

AFBench: A Large-scale Benchmark for Airfoil Design

TL;DR

The aim is to establish \emph{AFBench} as an ecosystem for training and evaluating airfoil inverse design methods, with a specific focus on data-driven controllable inverse design models by multimodal instructions capable of bridging the gap between ideas and execution, the academic research and industrial applications.

Abstract

Data-driven generative models have emerged as promising approaches towards achieving efficient mechanical inverse design. However, due to prohibitively high cost in time and money, there is still lack of open-source and large-scale benchmarks in this field. It is mainly the case for airfoil inverse design, which requires to generate and edit diverse geometric-qualified and aerodynamic-qualified airfoils following the multimodal instructions, \emph{i.e.,} dragging points and physical parameters. This paper presents the open-source endeavors in airfoil inverse design, \emph{AFBench}, including a large-scale dataset with 200 thousand airfoils and high-quality aerodynamic and geometric labels, two novel and practical airfoil inverse design tasks, \emph{i.e.,} conditional generation on multimodal physical parameters, controllable editing, and comprehensive metrics to evaluate various existing airfoil inverse design methods. Our aim is to establish \emph{AFBench} as an ecosystem for training and evaluating airfoil inverse design methods, with a specific focus on data-driven controllable inverse design models by multimodal instructions capable of bridging the gap between ideas and execution, the academic research and industrial applications. We have provided baseline models, comprehensive experimental observations, and analysis to accelerate future research. Our baseline model is trained on an RTX 3090 GPU within 16 hours. The codebase, datasets and benchmarks will be available at \url{https://hitcslj.github.io/afbench/}.

Paper Structure

This paper contains 26 sections, 4 equations, 10 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Automatic Data Engine
  4. Synthetic Airfoil Generation Stage
  5. Geometric and Aerodynamic Parameter Annotation Stage
  6. Airfoil Filtering Stage
  7. AFBench: Dataset Presentation and Benchmarking Setup
  8. Dataset Presentation
  9. Airfoil Inverse Design Tasks
  10. Baseline Methods
  11. Evaluation Metrics
  12. Benchmarking Results
  13. Comprehensive Method Comparison
  14. Ablation Study
  15. Conclusion
  16. ...and 11 more sections

Figures (10)

  • Figure 1: Our Airfoil Generation and Editing Software. (a) Generating diverse candidate airfoils. (b) Editing Keypoints and Editing Physical Parameters.
  • Figure 2: The overall pipeline of the Automatic data engine
  • Figure 3: Diverse Airfoils Generated by Our Automatic Data Engine. (a) Original airfoil from the UIUC database. (b) Airfoils generated using CST perturbation of the UIUC airfoil. (c) Airfoils generated using our trained model. (d) Combination of generated airfoils.
  • Figure 4: PARSEC physical parameters
  • Figure 5: Dataset presentation: (a) Proportional composition of the datasets within AF-200K. (b) Comparison between AF-200K and existing airfoil datasets.
  • ...and 5 more figures