Aerodynamic Shape Design Space Exploration with Deep Latent Diffusion Model

2026-09-01

AI Summary

本文提出DiffGeo，一种基于潜在空间扩散的生成框架，用于在数据极其稀缺的情况下探索气动设计空间，通过自动形状参数化和条件采样生成高质量、多样化的几何设计。

Abstract

We propose DiffGeo, a latent space diffusion-based generative framework for aerodynamic design space exploration under extreme data scarcity. DiffGeo combines a learned latent space model for automatic shape parameterization, with a diffusion sampler to directly generate novel, geometry-valid and controllable designs. We validate the approach on a series of case studies: (i) a 2D airfoil generation benchmark, where DiffGeo's latent diffusion model is compared against GAN- and VAE-based baselines in terms of sample quality, diversity and constraint adherence under limited data; (ii) integration into a surrogate-based optimization pipeline, where DiffGeo's conditional sampling produces task-informed airfoil data that improve both surrogate modeling and optimization performance; and (iii) extension to 3D turbomachinery blade prototyping, where DiffGeo generates realistic and high-performance blade geometries from a small set of reference designs. Throughout these investigations, DiffGeo achieves high-quality and diverse shape generation with at least an order of magnitude less data than alternatives, decouples geometry representation from design targets for flexible reuse, and seamlessly incorporates complex design constraints via energy-based conditioning. These capabilities demonstrate DiffGeo's potential to enhance early-stage design by automating design space exploration--improving efficiency, expanding design diversity and embedding engineering knowledge through controllable guidance.

Problem

• aerodynamic shape design
• data scarcity
• design space exploration

Innovation

• latent space diffusion model
• aerodynamic design space exploration
• data scarcity
• geometry-valid designs
• energy-based conditioning