Physics-guided training of GAN to improve accuracy in airfoil design synthesis

TL;DR

This paper introduces a physics-guided training method for GANs that enhances the physical validity and novelty of generated airfoil shapes, significantly improving accuracy without relying on training data.

Contribution

The paper proposes a novel physics-guided training approach for GANs that incorporates external physical models, enabling the generation of physically valid and new airfoil shapes without training data.

Findings

Significantly improved accuracy in airfoil performance prediction.

Generated shapes that are physically valid and different from training data.

Overcame limitations of traditional GANs in generating novel shapes.

Abstract

Generative adversarial networks (GAN) have recently been used for a design synthesis of mechanical shapes. A GAN sometimes outputs physically unreasonable shapes. For example, when a GAN model is trained to output airfoil shapes that indicate required aerodynamic performance, significant errors occur in the performance values. This is because the GAN model only considers data but does not consider the aerodynamic equations that lie under the data. This paper proposes the physics-guided training of the GAN model to guide the model to learn physical validity. Physical validity is computed using general-purpose software located outside the neural network model. Such general-purpose software cannot be used in physics-informed neural network frameworks, because physical equations must be implemented inside the neural network models. Additionally, a limitation of generative models is that the output data are similar to the training data and cannot generate completely new shapes. However, because the proposed model is guided by a physical model and does not use a training dataset, it can generate completely new shapes. Numerical experiments show that the proposed model drastically improves the accuracy. Moreover, the output shapes differ from those of the training dataset but still satisfy the physical validity, overcoming the limitations of existing GAN models.