Inverse design optimization framework via a two-step deep learning approach: application to a wind turbine airfoil

TL;DR

This paper introduces a two-step deep learning inverse design framework that enhances aerodynamic shape optimization, demonstrated on wind turbine airfoils, by improving accuracy, efficiency, and flexibility over traditional methods.

Contribution

A novel inverse design optimization framework combining variational autoencoders and multi-layer perceptrons with active and transfer learning, addressing limitations of existing approaches.

Findings

Framework achieves high accuracy in wind turbine airfoil design

Method significantly reduces computational time compared to traditional approaches

Flexible application potential to other inverse design problems

Abstract

The inverse approach is computationally efficient in aerodynamic design as the desired target performance distribution is prespecified. However, it has some significant limitations that prevent it from achieving full efficiency. First, the iterative procedure should be repeated whenever the specified target distribution changes. Target distribution optimization can be performed to clarify the ambiguity in specifying this distribution, but several additional problems arise in this process such as loss of the representation capacity due to parameterization of the distribution, excessive constraints for a realistic distribution, inaccuracy of quantities of interest due to theoretical/empirical predictions, and the impossibility of explicitly imposing geometric constraints. To deal with these issues, a novel inverse design optimization framework with a two-step deep learning approach is proposed. A variational autoencoder and multi-layer perceptron are used to generate a realistic target distribution and predict the quantities of interest and shape parameters from the generated distribution, respectively. Then, target distribution optimization is performed as the inverse design optimization. The proposed framework applies active learning and transfer learning techniques to improve accuracy and efficiency. Finally, the framework is validated through aerodynamic shape optimizations of the wind turbine airfoil. Their results show that this framework is accurate, efficient, and flexible to be applied to other inverse design engineering applications.