Tailoring Generative Adversarial Networks for Smooth Airfoil Design
Machine Learning
2024-04-19 v1
Abstract
In the realm of aerospace design, achieving smooth curves is paramount, particularly when crafting objects such as airfoils. Generative Adversarial Network (GAN), a widely employed generative AI technique, has proven instrumental in synthesizing airfoil designs. However, a common limitation of GAN is the inherent lack of smoothness in the generated airfoil surfaces. To address this issue, we present a GAN model featuring a customized loss function built to produce seamlessly contoured airfoil designs. Additionally, our model demonstrates a substantial increase in design diversity compared to a conventional GAN augmented with a post-processing smoothing filter.
Cite
@article{arxiv.2404.11816,
title = {Tailoring Generative Adversarial Networks for Smooth Airfoil Design},
author = {Joyjit Chattoraj and Jian Cheng Wong and Zhang Zexuan and Manna Dai and Xia Yingzhi and Li Jichao and Xu Xinxing and Ooi Chin Chun and Yang Feng and Dao My Ha and Liu Yong},
journal= {arXiv preprint arXiv:2404.11816},
year = {2024}
}