Session: 34-01 AI for flow field prediction and post-processing

Submission Number: 176099

Generative AI Approaches to Airfoil Flow Field Prediction 

Airfoil flow field prediction is central to turbomachinery design, yet Computational Fluid Dynamics (CFD) imposes a computational bottleneck on iterative design and optimisation. Recent studies have explored deep-learning-based surrogate models to reduce the computational cost associated with aerodynamic analyses. Among these are generative models, a class of models that include diffusion models, Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), which have recently demonstrated remarkable progress in diverse domains, from drug discovery in medicine and the life sciences to materials sciences. With a growing number of generative models in fluid mechanics, there is limited systematic assessment of their performance and suitability for this task. The purpose of this paper is to review the state of the art of generative models for airfoil flow field prediction, providing an overview of recent contributions, methodological advances, and outstanding challenges. We show that despite relatively higher computational costs when compared with alternative deep learning methods, generative models offer a promising approach for obtaining higher-fidelity flow fields and more accurate uncertainty modelling than other deep learning approaches such as Convolutional Neural Networks (CNNs). Our analysis reveals that research in this area remains in its early stages, but applications point towards advancement beyond simple two-dimensional airfoil flow fields towards three-dimensional, rotating, or multistage configurations that more accurately reflect real-world turbomachinery.

Presenting Author: Kenechukwu Ogbuagu University of Lincoln

Presenting Author Biography: Kenechukwu Ogbuagu is a PhD student in Engineering at the University of Lincoln, focusing on applying machine learning to optimise and advance engineering systems.

Authors:

Kenechukwu Ogbuagu University of Lincoln
Sepehr Maleki University of Lincoln
Giuseppe Bruni Siemens Industrial Turbomachinery
Senthil Krishnababu Siemens Industrial Turbomachinery