OptiWing3D: A Diverse Dataset of Optimized Wing Designs

TL;DR

OptiWing3D introduces a comprehensive dataset of 3D wing geometries optimized for aerodynamics, enabling advanced research in inverse design, multi-fidelity analysis, and understanding 3D effects in wing optimization.

Contribution

The paper presents the first publicly available multi-fidelity 3D wing optimization dataset with paired 2D and 3D designs, and demonstrates a constraint-aware diffusion model for inverse wing design.

Findings

3D optimized wings diverge from 2D designs near wingtips due to 3D effects

The dataset enables direct comparison between 2D and 3D aerodynamic simulations

A baseline diffusion model for inverse wing design is established

Abstract

OptiWing3D is the first publicly available dataset of high-fidelity shape optimized 3D wing geometries. Existing aerodynamics datasets are either limited to 2D simulations, lack optimization, or derive diversity solely from perturbations to a single baseline design, constraining their application as benchmarks to inverse design approaches and in the study of design diversity. The OptiWing3D dataset addresses these gaps, consisting of 1552 simulations resulting in 776 wing designs initialized from distinct extruded airfoil cross-sections. Additionally, a majority of the optimized wings in the dataset are paired to 2D counterparts optimized under identical conditions, creating the first multi-fidelity aerodynamic shape optimization dataset. Moreover, this structure allows for a direct comparison between 2D and 3D aerodynamic simulations. It is observed that 3D optimized designs diverge most prominently from the 2D-optimized designs near the wingtip, where three-dimensional effects are strongest, a finding made possible by the paired nature of the dataset. Finally, we demonstrate a constraint-aware conditional latent diffusion model capable of generating optimized wings from flow conditions, establishing a baseline for future inverse design approaches. The dataset, containing wing geometries and surface pressure distributions is publicly released to advance research in data-driven aerodynamic design.