Data-driven design exploration method using conditional variational autoencoder for airfoil design

Yonekura, Kazuo; Suzuki, Katsuyuki

doi:10.1007/s00158-021-02851-0

Cited by 46 publications

(14 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to GANs, conditional VAE (CVAE) has also been investigated in the inverse design of airfoils [487]. Yonekura and Suzuki [486] used CVAE in the inverse design of NACA four-digit airfoils with the conditon of C l at α = 5.0 • (same with that in [485]). They concluded that using a moderate latent dimension (no more than 16) was preferable to compromise influences of the error of matching the condition (C l at α = 5.0 • ) and the airfoil shape variation.…”

Section: Generative Inverse Designmentioning

confidence: 99%

“…They concluded that using a moderate latent dimension (no more than 16) was preferable to compromise influences of the error of matching the condition (C l at α = 5.0 • ) and the airfoil shape variation. Yonekura and Suzuki [486] also applied CVAE to the inverse design of turbine blade airfoils, where the flow outlet angle and aerodynamic loss coefficient were two performance conditions of interest and 50,621 sample airfoils were generated based on the Pak-B turbine blade shape to train the model. With such a large volume of training data, the mean absolute error of the flow outlet angle in airfoils generated by the CVAE model was 0.609 • , where the absolute angle was approximately 62.9 • .…”

Section: Generative Inverse Designmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Generative Inverse Designmentioning

confidence: 99%

Section: Generative Inverse Designmentioning

confidence: 99%

Machine Learning in Aerodynamic Shape Optimization

Li¹,

Martins²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In the field of feature extractions of airfoils, the Auto-Encoders are commonly used to re-built airfoils because of their ability to extract features from geometrical shape of airfoils and represent the airfoils as latent feature vectors [37], [38]. In addition, the Auto-Encoders reflect the accuracy of extracted features by calculating the similarities between rebuilt airfoils and real airfoils [39], [40].…”

Section: B Experiments I: Geometric-features Comparation Experimentsmentioning

confidence: 99%

An airfoil geometric-feature extraction and discrepant data fusion learning method

Xiang

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

The perception of geometric-features of airfoils is the basis in aerodynamic area for performance prediction, parameterization, aircraft inverse design, etc. There are three approaches to percept the geometric shape of airfoils, namely manual design of airfoil geometry parameters, polynomial definition and deep learning. The first two methods directly define geometric-features or polynomials of airfoil curves, but the number of extracted features is limited. Deep learning algorithms can extract a large number of potential features (called latent features). However, the features extracted by deep learning lack explicit geometrical meaning. Motivated by the advantages of polynomial definition and deep learning, we propose a geometric-feature extraction method (named Bézier-based feature extraction, BFE) for airfoils, which consists of two parts: manifold metric feature extraction and geometric-feature fusion encoder (GF encoder). Manifold metric feature extraction, with the help of the Bézier curve, captures manifold metrics (a sort of geometric-features) from tangent space of airfoil curves, and the GF-encoder combines airfoil coordinate data and manifold metrics together to form novel fused geometric-features. To validate the feasibility of the fused geometric-features, two experiments based on the public UIUC airfoil dataset are conducted. Experiment I is used to extract manifold metrics of airfoils and export the fused geometric-features. Experiment II, based on the Multi-task learning (MTL), is used to fuse the discrepant data (i.e., the fused geometric-features and the flight conditions) to predict the aerodynamic performance of airfoils. The results show that the BFE can generate more smooth and realistic airfoils than Auto-Encoder, and the fused geometric-features extracted by BFE can be used to reduce the prediction errors of C L and C D .

show abstract

“…Two-dimensional cross-sections of aerodynamic structures such as aircraft wings or wind turbine blades, also known as airfoils, are critical engineering shapes whose design and manufacturing can have significant impacts on the aerospace and energy industries. Research into AI and ML algorithms involving airfoil design for improved aerodynamic, structural, and acoustic performance is a rapidly growing area of work (Zhang, Sung, and Mavris 2018;Li, Bouhlel, and Martins 2019;Chen, Chiu, and Fuge 2019;Glaws et al 2021;Jing et al 2021;Yonekura and Suzuki 2021;Yang, Lee, and Yee 2021).…”

Section: Introductionmentioning

confidence: 99%

Grassmannian Shape Representations for Aerodynamic Applications

Doronina¹,

Grey²,

Glaws³

2022

Preprint

View full text Add to dashboard Cite

Airfoil shape design is a classical problem in engineering and manufacturing. Our motivation is to combine principled physics-based considerations for the shape design problem with modern computational techniques informed by a datadriven approach. Traditional analyses of airfoil shapes emphasize a flow-based sensitivity to deformations which can be represented generally by affine transformations (rotation, scaling, shearing, translation). We present a novel representation of shapes which decouples affine-style deformations from a rich set of data-driven deformations over a submanifold of the Grassmannian. The Grassmannian representation, informed by a database of physically relevant airfoils, offers (i) a rich set of novel 2D airfoil deformations not previously captured in the data, (ii) improved low-dimensional parameter domain for inferential statistics informing design/manufacturing, and (iii) consistent 3D blade representation and perturbation over a sequence of nominal shapes.

show abstract

Data-driven design exploration method using conditional variational autoencoder for airfoil design

Cited by 46 publications

References 28 publications

Machine Learning in Aerodynamic Shape Optimization

Machine Learning in Aerodynamic Shape Optimization

An airfoil geometric-feature extraction and discrepant data fusion learning method

Grassmannian Shape Representations for Aerodynamic Applications

Contact Info

Product

Resources

About