Machine learning in aerodynamic shape optimization

J Li, X Du, JRRA Martins - Progress in Aerospace Sciences, 2022 - Elsevier
Abstract Machine learning (ML) has been increasingly used to aid aerodynamic shape
optimization (ASO), thanks to the availability of aerodynamic data and continued …

Complex nonlinear dynamics and vibration suppression of conceptual airfoil models: A state-of-the-art overview

Q Liu, Y Xu, J Kurths, X Liu - Chaos: An Interdisciplinary Journal of …, 2022 - pubs.aip.org
During the past few decades, several significant progresses have been made in exploring
complex nonlinear dynamics and vibration suppression of conceptual aeroelastic airfoil …

Deep neural operators as accurate surrogates for shape optimization

K Shukla, V Oommen, A Peyvan, M Penwarden… - … Applications of Artificial …, 2024 - Elsevier
Deep neural operators, such as DeepONet, have changed the paradigm in high-
dimensional nonlinear regression, paving the way for significant generalization and speed …

Airfoil design and surrogate modeling for performance prediction based on deep learning method

Q Du, T Liu, L Yang, L Li, D Zhang, Y Xie - Physics of Fluids, 2022 - pubs.aip.org
Airfoil design and surrogate modeling for performance prediction based on deep learning
method | Physics of Fluids | AIP Publishing Skip to Main Content Umbrella Alt Text Umbrella Alt …

Design subspace learning: Structural design space exploration using performance-conditioned generative modeling

R Danhaive, CT Mueller - Automation in Construction, 2021 - Elsevier
Designers increasingly rely on parametric design studies to explore and improve structural
concepts based on quantifiable metrics, generally either by generating design variations …

Data-based approach for wing shape design optimization

J Li, M Zhang - Aerospace Science and Technology, 2021 - Elsevier
Aircraft design is a trade-off among different objectives and constraints, so multiple design
rounds are usually required. Aerodynamic shape optimization based on high-fidelity …

Performance prediction and design optimization of turbine blade profile with deep learning method

Q Du, Y Li, L Yang, T Liu, D Zhang, Y Xie - Energy, 2022 - Elsevier
Aerodynamic design optimization of the blade profile is a critical approach to improve
performance of turbomachinery. This paper aims to achieve the performance prediction with …

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

S Yang, S Lee, K Yee - Engineering with Computers, 2023 - Springer
The inverse approach is computationally efficient in aerodynamic design as the desired
target performance distribution is prespecified. However, it has some significant limitations …

Unsteady aerodynamic reduced-order modeling based on machine learning across multiple airfoils

K Li, J Kou, W Zhang - Aerospace Science and Technology, 2021 - Elsevier
Computational-fluid-dynamics-based prediction of unsteady aerodynamics is an essential
research topic in the design of aircraft, which usually requires very high computational cost …

Deep neural operators can serve as accurate surrogates for shape optimization: a case study for airfoils

K Shukla, V Oommen, A Peyvan, M Penwarden… - arXiv preprint arXiv …, 2023 - arxiv.org
Deep neural operators, such as DeepONets, have changed the paradigm in high-
dimensional nonlinear regression from function regression to (differential) operator …