Accelerating High‐Fidelity Airfoil Design via Physics‐Informed Video Diffusion Model
6 affiliations
- 1City University of Hong Kong Hong Kong China
- 2National Key Laboratory for Multimedia Information Processing Peking University Beijing China
- 3The Hong Kong Polytechnic University Hong Kong China
- 4Central South University Changsha China
- 5Zhejiang University Hangzhou China
- 6National Biomedical Imaging Center Peking University Beijing China
Abstract
Airfoil design remains a challenging multi‐objective optimization problem requiring precise geometric control for optimal aerodynamic performance. Data‐driven inverse design methods mitigate this complexity but often yield non‐physical results when physical constraints are not explicitly incorporated. Here, we construct a high‐fidelity NACA–Nek1000 datasets with 53 400 samples from direct numerical simulations to train a dual physics‐informed video diffusion model (PVDM). The governing equations of incompressible flow are intrinsically coupled with the diffusion learning process, enabling the reconstruction of full‐field velocity and pressure distributions from lift‐to‐drag response sequences. The PVDM achieves accurate low‐Reynolds number airfoil reconstruction and real‐time flow generation within 30 s per case, approximately 600 times faster than conventional simulations, while maintaining over 90% fidelity. The reconstructed airfoils are further modeled as propeller geometries and experimentally validated, which well fit the simulated lift‐to‐drag response, establishing a rapid and generalizable framework for high‐fidelity, physics‐informed inverse aerodynamic design.
Related
- Physics-informed neural networks for shock capturing in inviscid flows around an airfoil
- Accelerating noisy variational quantum algorithms with physics-informed denoising networks
- Passage of particles through matter and the effective straggling-function: High-fidelity accelerated simulation via Physics-Informed Machine Learning
- High-fidelity quantum gate learning via physics-informed neural networks
- Accelerating high-fidelity gyrokinetic fusion simulations with iGENE
BibTeX
@article{ai2026accelerating,
title = {{Accelerating High‐Fidelity Airfoil Design via Physics‐Informed Video Diffusion Model}},
author = {Yifeng Ai and Yijia Guo and Hongfu Zhang and Lei Zhou and Tiejun Huang and Weiqiu Chen and Xuhui He and Peng Guo and C. W. Lim and Lei Ma},
journal = {Advanced Science},
year = {2026},
month = nov,
doi = {10.1002/advs.78532},
url = {https://doi.org/10.1002/advs.78532},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Accelerating High‐Fidelity Airfoil Design via Physics‐Informed Video Diffusion Model
AU - Yifeng Ai
AU - Yijia Guo
AU - Hongfu Zhang
AU - Lei Zhou
AU - Tiejun Huang
AU - Weiqiu Chen
AU - Xuhui He
AU - Peng Guo
AU - C. W. Lim
AU - Lei Ma
PY - 2026
DA - 2026/11/03
JO - Advanced Science
DO - 10.1002/advs.78532
UR - https://doi.org/10.1002/advs.78532
AB - Airfoil design remains a challenging multi‐objective optimization problem requiring precise geometric control for optimal aerodynamic performance. Data‐driven inverse design methods mitigate this complexity but often yield non‐physical results when physical constraints are not explicitly incorporated. Here, we construct a high‐fidelity NACA–Nek1000 datasets with 53 400 samples from direct numerical simulations to train a dual physics‐informed video diffusion model (PVDM). The governing equations of incompressible flow are intrinsically coupled with the diffusion learning process, enabling the reconstruction of full‐field velocity and pressure distributions from lift‐to‐drag response sequences. The PVDM achieves accurate low‐Reynolds number airfoil reconstruction and real‐time flow generation within 30 s per case, approximately 600 times faster than conventional simulations, while maintaining over 90% fidelity. The reconstructed airfoils are further modeled as propeller geometries and experimentally validated, which well fit the simulated lift‐to‐drag response, establishing a rapid and generalizable framework for high‐fidelity, physics‐informed inverse aerodynamic design.
SN - 2198-3844
ER -