Airfoil Parameterization

Airfoil parameterization focuses on efficiently representing the complex shapes of airfoils using mathematical or data-driven models, aiming to streamline aerodynamic design and optimization. Current research emphasizes developing methods that balance flexibility, parsimony, and intuitive control over airfoil geometry, employing techniques like variational autoencoders, generative adversarial networks, and reinforcement learning integrated with high-fidelity solvers. These advancements improve the efficiency and accuracy of aerodynamic simulations and optimization, leading to better aircraft designs and reduced development costs.

Papers

March 7, 2024

A mechanism-driven reinforcement learning framework for shape optimization of airfoils
Jingfeng Wang, Guanghui Hu
Reinforcement Learning Airfoil Design Shape Optimization Learning Mechanism Airfoil Shape Optimization Airfoil Parameterization

November 18, 2023

Compact and Intuitive Airfoil Parameterization Method through Physics-aware Variational Autoencoder
Yu-Eop Kang, Dawoon Lee, Kwanjung Yee
Physic Informed Embracing CompAct Airfoil Design Airfoil Shape Optimization Airfoil Parameterization

May 28, 2023

A Synergistic Framework Leveraging Autoencoders and Generative Adversarial Networks for the Synthesis of Computational Fluid Dynamics Results in Aerofoil Aerodynamics
Tanishk Nandal, Vaibhav Fulara, Raj Kumar Singh
Generative Adversarial Network Supervised Autoencoder Computational Fluid Dynamic Aerodynamic Force Synergistic Information Airfoil Design Airfoil Parameterization

March 6, 2023

Knowledge-embedded meta-learning model for lift coefficient prediction of airfoils
Hairun Xie, Jing Wang, Miao Zhang
Meta Learning Aerodynamic Force Airfoil Design Coefficient Prediction Floor Lift Aerodynamic Shape Optimization Airfoil Parameterization

May 5, 2022

Parametric Generative Schemes with Geometric Constraints for Encoding and Synthesizing Airfoils
Hairun Xie, Jing Wang, Miao Zhang
Data Encoding Geometric Constraint Airfoil Design Aerodynamic Shape Optimization Learning Based Generative Airfoil Parameterization

Airfoil Parameterization

Papers

A mechanism-driven reinforcement learning framework for shape optimization of airfoils

Compact and Intuitive Airfoil Parameterization Method through Physics-aware Variational Autoencoder

A Synergistic Framework Leveraging Autoencoders and Generative Adversarial Networks for the Synthesis of Computational Fluid Dynamics Results in Aerofoil Aerodynamics

Knowledge-embedded meta-learning model for lift coefficient prediction of airfoils

Parametric Generative Schemes with Geometric Constraints for Encoding and Synthesizing Airfoils