Bayesian Optimization of a Low-Boom Supersonic Wing Planform

Jim, Timothy Man Shui; Faza, Ghifari Adam; Palar, Pramudita Satria; Shimoyama, Koji

doi:10.2514/1.j060225

Cited by 13 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jim et al [143] concentrated on optimizing the aerodynamics and aeroacoustics of a hypothetical low-drag, low-boom supersonic planform using Kriging-based Bayesian multi-objective optimization and the gradient-free GA algorithm (Figure 2). The authors investigated the use of Euler Computational Fluid Dynamics (CFD) with an enhanced version of the Burgers PDE solver [144,145] and an experimental parasitic drag addition to speed up the design space exploration and multi-objective optimization processes.…”

Section: Optimization Algorithmsmentioning

confidence: 99%

Recent Advances in Airfoil Self-Noise Passive Reduction

Amirsalari,

Rocha

2023

Aerospace

View full text Add to dashboard Cite

Airflow-induced noise prediction and reduction is one of the priorities for both the energy and aviation industries. This review paper provides valuable insights into flow-induced noise computation, prediction, and optimization methods with state-of-the-art efforts in passive noise reduction on airfoils, blades, and wings. This review covers the combination of several approaches in this field, including analytical, numerical, empirical, semi-empirical, artificial intelligence, and optimization methods. Under passive noise reduction techniques, leading and trailing edge treatments, porous materials, controlled diffusion airfoils, morphing wings, surface treatments, and other unique geometries that researchers developed are among the design modification methods discussed here. This work highlights the benefits of incorporating multiple techniques to achieve the best results concerning the desired application and design. In addition, this work provides an overview of the advantages and disadvantages of each tool, with a particular emphasis on the possible challenges when implementing them. The methods and techniques discussed herein will help increase the acoustic efficiency of aerial structures, making them a beneficial resource for researchers, engineers, and other professionals working in aviation noise reduction.

show abstract

Section: Optimization Algorithmsmentioning

confidence: 99%

Recent Advances in Airfoil Self-Noise Passive Reduction

Amirsalari,

Rocha

2023

Aerospace

View full text Add to dashboard Cite

show abstract

“…Most aerodynamic design optimization methods using surrogate models rely on an iterative model refinement [440]. Such surrogate-based optimization strategies have shown to be effective in various aerodynamic shape optimization applications including single-point design [441,442], multipoint design [328,443], massively multipoint design [100], multi-objective design [93,444,445], inverse design [168,446], and robust design [313,[447][448][449]. Optimization using these methods is generally composed of two phases.…”

Section: Surrogate-based Optimizationmentioning

confidence: 99%

Machine Learning in Aerodynamic Shape Optimization

Li¹,

Martins²

2022

Preprint

View full text Add to dashboard Cite

Large volumes of experimental and simulation aerodynamic data have been rapidly advancing aerodynamic shape optimization (ASO) via machine learning (ML), whose effectiveness has been growing thanks to continued developments in deep learning. In this review, we first introduce the state of the art and the unsolved challenges in ASO. Next, we present a description of ML fundamentals and detail the ML algorithms that have succeeded in ASO. Then we review ML applications contributing to ASO from three fundamental perspectives: compact geometric design space, fast aerodynamic analysis, and efficient optimization architecture. In addition to providing a comprehensive summary of the research, we comment on the practicality and effectiveness of the developed methods. We show how cutting-edge ML approaches can benefit ASO and address challenging demands like interactive design optimization. However, practical large-scale design optimizations remain a challenge due to the costly ML training expense. A deep coupling of ML model construction with ASO prior experience and knowledge, such as taking physics into account, is recommended to train ML models effectively.

show abstract