Enhanced data efficiency using deep neural networks and Gaussian processes for aerodynamic design optimization

SA Renganathan, R Maulik, J Ahuja - Aerospace Science and Technology, 2021 - Elsevier
Adjoint-based optimization methods are attractive for aerodynamic shape design primarily
due to their computational costs being independent of the dimensionality of the input space …

A deep learning‒genetic algorithm approach for aerodynamic inverse design via optimization of pressure distribution

A Shirvani, M Nili-Ahmadabadi, MY Ha - Computer Methods in Applied …, 2024 - Elsevier
Conventional aerodynamic inverse design (AID) methods have major limitations in terms of
optimality and actuality of target parameter distribution. In this research, the target pressure …

Unsteady physics-based reduced order modeling for large-scale compressible aerodynamic applications

A Garbo, P Bekemeyer - Computers & Fluids, 2022 - Elsevier
A physics-based reduced order model is presented as a viable approach to accurately
predict unsteady flowfield solutions at a fraction of the computational time that is required by …

[HTML][HTML] A Comparative Study on the Efficiencies of Aerodynamic Reduced Order Models of Rigid and Aeroelastic Sweptback Wings

Ö Özkaya Yılmaz, A Kayran - Aerospace, 2024 - mdpi.com
This paper presents the effect of wing elasticity on the efficiency of a nonintrusive reduced
order model using a three-dimensional sweptback wing. For this purpose, a computationally …

Dynamic mode decomposition analysis of the common research model with adjoint-based gradient optimization

PL Wu, PY Wang, HS Gao - Physics of Fluids, 2021 - pubs.aip.org
Aerodynamic shape refinement optimization for passenger aircraft is difficult and requires a
significant workload. The adjoint-based gradient optimization method can quickly find local …

[HTML][HTML] Generation of a surrogate compartment model for counter-current spray dryer. Fluxes and momentum modeling

B Hernández, MA Pinto, M Martin - Computers & Chemical Engineering, 2022 - Elsevier
This work presents the development of a reduced order compartment model for a counter-
current spray dryer. The compartment model is formulated using adaptable compartments …

Aerodynamic Optimization Framework for a Three-Dimensional Nacelle Based on Deep Manifold Learning-Assisted Geometric Multiple Dimensionality Reduction

C Wang, L Wang, C Cao, G Sun, Y Huang, S Zhou - Aerospace, 2023 - mdpi.com
As a core component of an aero-engine, the aerodynamic performance of the nacelle is
essential for the overall performance of an aircraft. However, the direct design of a three …

Deep convolutional neural network for shape optimization using level-set approach

W Mallik, N Farvolden, J Jelovica… - arXiv preprint arXiv …, 2022 - arxiv.org
This article presents a reduced-order modeling methodology via deep convolutional neural
networks (CNNs) for shape optimization applications. The CNN provides a nonlinear …

Data-Driven Nonintrusive Model-Order Reduction for Aerodynamic Design Optimization

A Moni, W Yao, H Malekmohamadi - AIAA Journal, 2024 - arc.aiaa.org
Fast and accurate evaluation of aerodynamic characteristics is essential for aerodynamic
design optimization because aircraft programs require many years of design and …

[HTML][HTML] Nonintrusive Aerodynamic Shape Optimisation with a POD-DEIM Based Trust Region Method

S Marques, L Kob, TT Robinson, W Yao - Aerospace, 2023 - mdpi.com
This work presents a strategy to build reduced-order models suitable for aerodynamic shape
optimisation, resulting in a multifidelity optimisation framework. A reduced-order model …