Rapid and Accurate Airfoil Aerodynamic Prediction Using a Multi-Fidelity Transfer Learning Approach
Applied Sciences · 09.10.2025 · 15 (19) · 10820
DOI: 10.3390/app151910820 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 09.10.2025. Verfasst von Yuxin Huo und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The high computational cost of high-fidelity CFD simulations forms a major bottleneck in aerodynamic design. This paper introduces a multi-fidelity transfer learning framework to rapidly predict airfoil aerodynamics with high accuracy. Our approach involves pre-training a deep fully connected neural network on a large dataset of low-fidelity Euler simulations. The pre-trained model is then fine-tuned using a limited set of high-fidelity RANS data, enabling efficient knowledge transfer from low- to high-fidelity domains. A specialized logarithmic-exponential normalization method is developed to handle the scale differences between aerodynamic coefficients. The framework demonstrates exceptional performance: after fine-tuning with only 700 high-fidelity samples, the model accurately predicts pressure distributions (lowest RMSE = 0.053) and force coefficients (R2 > 0.947 for lift and drag). This method successfully bridges the gap between computational efficiency and high accuracy, providing a powerful data-driven surrogate model that can significantly accelerate the aerodynamic design and optimization process.
Zitieren
APA
Huo, Y., Che, X., Wang, Y., Jiang, Q., Zhong, Z., Zhang, M., Wang, B., & Ma, X. (2025). Rapid and Accurate Airfoil Aerodynamic Prediction Using a Multi-Fidelity Transfer Learning Approach. Applied Sciences, 15(19), 10820. https://doi.org/10.3390/app151910820
Vancouver
Huo Y, Che X, Wang Y, Jiang Q, Zhong Z, Zhang M, et al. Rapid and Accurate Airfoil Aerodynamic Prediction Using a Multi-Fidelity Transfer Learning Approach. Applied Sciences. 2025;15(19):10820. doi:10.3390/app151910820
BibTeX
@article{Huo2025,
author = {Huo, Yuxin and Che, Xue and Wang, Yiyu and Jiang, Qiang and Zhong, Zhilong and Zhang, Miao and Wang, Bo and Ma, Xiaoping},
title = {Rapid and Accurate Airfoil Aerodynamic Prediction Using a Multi-Fidelity Transfer Learning Approach},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {19},
pages = {10820},
doi = {10.3390/app151910820}
}
EUVIMED