Search papers, labs, and topics across Lattice.
The paper introduces Deeptrans, a deep learning model for predicting airfoil aerodynamic performance, addressing the limitations of traditional methods like wind tunnel tests and CFD simulations. Deeptrans fuses an improved Transformer architecture with a generative adversarial network (GAN) to enable synchronous and high-precision prediction of multiple aerodynamic parameters. Experimental results demonstrate that Deeptrans achieves a mean squared error (MSE) of 5.6*10-6 on the validation set and a single-sample prediction time of 0.0056 seconds, significantly outperforming traditional CFD methods and other deep learning models like standalone Transformers, GANs, and VAEs.
Predict airfoil aerodynamics 700x faster than CFD with a Transformer-GAN hybrid, achieving state-of-the-art accuracy.
Predicting of airfoil aerodynamic performance is a key part of aircraft design optimization, but the traditional methods (such as wind tunnel test and CFD simulation) have the problems of high cost and low efficiency, and the existing data-driven models face the challenges of insufficient accuracy and strong data dependence in multi-objective prediction. Therefore, this study proposes a deep learning model, Deeptrans, based on the fusion of improved Transformer and generative Adversarial network (GAN), which aims to predict the multi-parameter aerodynamic performance of airfoil efficiently. By constructing a large-scale data set and designing a model structure that integrates a Transformer coding-decoding framework and confrontation training, synchronous and high-precision prediction of aerodynamic parameters is realized. Experiments show that the MSE loss of Deeptrans on the verification set is reduced to 5.6*10-6, and the single-sample prediction time is only 0.0056 seconds, which is nearly 700 times more efficient than the traditional CFD method. Horizontal comparison shows that the prediction accuracy is significantly better than the original Transformer, GAN, and VAE models. This study provides an efficient data-driven solution for airfoil aerodynamic performance prediction and a new idea for deep learning modeling complex flow problems.
