Rapid aerodynamic prediction of swept wings via physics-embedded transfer learning
This work addresses the problem of efficient aerodynamic prediction for swept wings in aerospace engineering, offering a domain-specific incremental improvement.
The paper tackled the high computational cost of generating training data for machine learning models predicting transonic swept wing flow fields by proposing a physics-embedded transfer learning framework that leverages 2D airfoil data and sweep theory. This approach reduced prediction errors by 30% with pretraining and an additional 9% with sweep theory, and required less than half the wing training samples to achieve the same error level as a nontransfer model.
Machine learning-based models provide a promising way to rapidly acquire transonic swept wing flow fields but suffer from large computational costs in establishing training datasets. Here, we propose a physics-embedded transfer learning framework to efficiently train the model by leveraging the idea that a three-dimensional flow field around wings can be analyzed with two-dimensional flow fields around cross-sectional airfoils. An airfoil aerodynamics prediction model is pretrained with airfoil samples. Then, an airfoil-to-wing transfer model is fine-tuned with a few wing samples to predict three-dimensional flow fields based on two-dimensional results on each spanwise cross section. Sweep theory is embedded when determining the corresponding airfoil geometry and operating conditions, and to obtain the sectional airfoil lift coefficient, which is one of the operating conditions, the low-fidelity vortex lattice method and data-driven methods are proposed and evaluated. Compared to a nontransfer model, introducing the pretrained model reduces the error by 30%, while introducing sweep theory further reduces the error by 9%. When reducing the dataset size, less than half of the wing training samples are need to reach the same error level as the nontransfer framework, which makes establishing the model much easier.