Data-Driven Aerodynamic Modeling

A special issue of Aerospace (ISSN 2226-4310). This special issue belongs to the section "Aeronautics".

Deadline for manuscript submissions: closed (30 April 2024) | Viewed by 12896

Special Issue Editors


E-Mail Website
Guest Editor
Team Leader Surrogates and Uncertainty Management, Institute of Aerodynamics and Flow Technology, German Aerospace Center (DLR), 38108 Braunschweig, Germany
Interests: data-driven modeling; aerodynamics; reduced-order modeling; machine learning; computational fluid dynamics; uncertainty management; numerical simulation; fluid–structure interaction; aeroelasticity; robust design; intrusive methods; data fusion

E-Mail Website
Guest Editor
Head of C2A2S2E Department (Center for Computer Applications in AeroSpace Science and Engineering), Institute of Aerodynamics and Flow Technology, German Aerospace Center (DLR), 38108 Braunschweig, Germany
Interests: aerodynamics; computational fluid dynamics; multidisciplinary analysis and multidisciplinary optimization; shape optimization; uncertainties; robust design; machine learning; surrogate and reduced-order modeling; data fusion; physics-informed neural networks; expert systems

Special Issue Information

Dear Colleagues,

Data-driven modeling in general and machine learning techniques in particular have transformed our everyday life over the past few years. In areas for which vast amounts of data are available, the aforementioned techniques have achieved remarkable success, especially when mathematical models are lacking. Instead, aerodynamic tools such as computational fluid dynamics solvers rely on first principles that directly enable us to describe and investigate system behavior. Numerical simulation tools derived from these principles have become invaluable in aircraft design and are about to significantly contribute to the green transformation of the aviation sector. However, such tools are far from perfect and suffer from several shortcomings, e.g., computational cost may become prohibitive once a large number of simulations are required, or there is the problem of deriving accurate and reliable turbulence models to describe small-scale turbulent flow behavior. Data-driven modeling is generally regarded as a promising approach to enhance and complement existing aerodynamic methods and tools to circumvent some of these shortcomings and to improve physical modeling. This Aerospace Special Issue covers recent advances in data-driven aerodynamic modeling including surrogate and reduced-order modeling; machine learning for aerodynamics; data fusion; uncertainty propagation and management; aerodynamic shape optimization, physics-informed neural networks, and data-driven turbulence modeling. The Guest Editors of this Special Issue invite authors to submit papers addressing topics in the aforementioned areas of data-driven modeling, with a special focus on aerodynamic applications. 

Dr. Philipp Bekemeyer
Prof. Dr. Stefan Görtz
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Aerospace is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (7 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

22 pages, 8430 KiB  
Article
A Comparative Study on the Efficiencies of Aerodynamic Reduced Order Models of Rigid and Aeroelastic Sweptback Wings
by Özge Özkaya Yılmaz and Altan Kayran
Aerospace 2024, 11(8), 616; https://doi.org/10.3390/aerospace11080616 - 27 Jul 2024
Cited by 3 | Viewed by 1190
Abstract
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 low-cost but highly accurate nonintrusive reduced order method is constructed utilizing proper orthogonal decomposition (POD) coupled [...] Read more.
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 low-cost but highly accurate nonintrusive reduced order method is constructed utilizing proper orthogonal decomposition (POD) coupled with radial basis function (RBF) interpolation. The results are evaluated in terms of order reduction and prediction capability of rigid and aeroelastic ROMs. Our results show that compared to the rigid wing, reduced order modeling is more effectively applied to the aeroelastic sweptback wing due to the postponement of flow separation caused by bending–torsion coupling, when the pressure coefficient (Cp) is considered as the output. We further show that for flexible wings, utilizing rigid nodes is not sufficient for presenting the Cp distribution accurately; hence, separate ROMs must be generated for the deformed positions of the nodes. Moreover, the RBF method is also exploited for prediction of the results with direct interpolation of the data ensemble by generating a surrogate model. Finally, the proposed methods are compared in terms of accuracy, computational cost and practicality. Full article
(This article belongs to the Special Issue Data-Driven Aerodynamic Modeling)
Show Figures

Figure 1

24 pages, 2640 KiB  
Article
Nonlinear Surrogate Model Design for Aerodynamic Dataset Generation Based on Artificial Neural Networks
by Guillermo Suarez, Emre Özkaya, Nicolas R. Gauger, Hans-Jörg Steiner, Michael Schäfer and David Naumann
Aerospace 2024, 11(8), 607; https://doi.org/10.3390/aerospace11080607 - 24 Jul 2024
Cited by 1 | Viewed by 1603
Abstract
In this work we construct a surrogate model using artificial neural networks (ANN) to predict the steady-state behavior of an unmanned combat aircraft. We employ various strategies to improve the model’s accuracy, including the consideration of design tolerances, creating independent surrogate models for [...] Read more.
In this work we construct a surrogate model using artificial neural networks (ANN) to predict the steady-state behavior of an unmanned combat aircraft. We employ various strategies to improve the model’s accuracy, including the consideration of design tolerances, creating independent surrogate models for the different flow regimes and encoding non-numeric input features. We also explore alternative machine learning models, albeit they demonstrated a lower reliability than ANNs. Two scenarios are considered for the target variable: one focusing solely on predicting the pitching moment coefficient, and the other incorporating the roll moment coefficient as well. We investigate different methods for handling multiple targets, finding that constructing a single model with multiple outputs consistently outperforms developing separate models for each target variable. Overall, the ANN provides predictions that show excellent agreement with the experimental data, demonstrating its effectiveness and reliability in aerodynamic modeling. Full article
(This article belongs to the Special Issue Data-Driven Aerodynamic Modeling)
Show Figures

Figure 1

19 pages, 12208 KiB  
Article
On the Generalization Capability of a Data-Driven Turbulence Model by Field Inversion and Machine Learning
by Yasunari Nishi, Andreas Krumbein, Tobias Knopp, Axel Probst and Cornelia Grabe
Aerospace 2024, 11(7), 592; https://doi.org/10.3390/aerospace11070592 - 20 Jul 2024
Cited by 1 | Viewed by 1656
Abstract
This paper discusses the generalizability of a data-augmented turbulence model with a focus on the field inversion and machine learning approach. It is highlighted that the augmented model based on two-dimensional (2D) separated airfoil flows gives poor predictive capability for a different class [...] Read more.
This paper discusses the generalizability of a data-augmented turbulence model with a focus on the field inversion and machine learning approach. It is highlighted that the augmented model based on two-dimensional (2D) separated airfoil flows gives poor predictive capability for a different class of separated flows (NASA wall-mounted hump) compared to the baseline model due to extrapolation. We demonstrate a sensor-based approach to localize the data-driven model correction to tackle this generalizability issue. Furthermore, the applicability of the augmented model to a more complex aeronautical three-dimensional case, the NASA Common Research Model configuration, is studied. Observations on the pressure coefficient predictions and the model correction field suggest that the present 2D-based augmentation is to some extent applicable to a three-dimensional aircraft flow. Full article
(This article belongs to the Special Issue Data-Driven Aerodynamic Modeling)
Show Figures

Figure 1

20 pages, 2475 KiB  
Article
Multi-Fidelity Adaptive Sampling for Surrogate-Based Optimization and Uncertainty Quantification
by Andrea Garbo, Jigar Parekh, Tilo Rischmann and Philipp Bekemeyer
Aerospace 2024, 11(6), 448; https://doi.org/10.3390/aerospace11060448 - 31 May 2024
Cited by 2 | Viewed by 1776
Abstract
Surrogate-based algorithms are indispensable in the aerospace engineering field for reducing the computational cost of optimization and uncertainty quantification analyses, particularly those involving computationally intensive solvers. This paper presents a novel approach for enhancing the efficiency of surrogate-based algorithms through a new multi-fidelity [...] Read more.
Surrogate-based algorithms are indispensable in the aerospace engineering field for reducing the computational cost of optimization and uncertainty quantification analyses, particularly those involving computationally intensive solvers. This paper presents a novel approach for enhancing the efficiency of surrogate-based algorithms through a new multi-fidelity sampling technique. Unlike existing multi-fidelity methods which are based on a single multiplicative acquisition function, the proposed technique decouples the identification of the new infill sample from the selection of the fidelity level. The location of the infill sample is determined by leveraging the highest fidelity surrogate model, while the fidelity level used for its performance evaluation is chosen as the cheapest one within the “accurate enough” models at the infill location. Moreover, the methodology introduces the application of the Jensen–Shannon divergence to quantify the accuracy of the different fidelity levels. Overall, the resulting technique eliminates some of the drawbacks of existing multiplicative acquisition functions such as the risk of continuous sampling from lower and cheaper fidelity levels. Experimental validation conducted in surrogate-based optimization and uncertainty quantification scenarios demonstrates the efficacy of the proposed approach. In an aerodynamic shape optimization task focused on maximizing the lift-to-drag ratio, the multi-fidelity strategy achieved comparable results to standard single-fidelity sampling but with approximately a five-fold improvement in computational efficiency. Likewise, a similar reduction in computational costs was observed in the uncertainty quantification problem, with the resulting statistical values aligning closely with those obtained using traditional single-fidelity sampling. Full article
(This article belongs to the Special Issue Data-Driven Aerodynamic Modeling)
Show Figures

Figure 1

21 pages, 1985 KiB  
Article
Improvements in Probabilistic Strategies and Their Application to Turbomachinery
by Andriy Prots, Matthias Voigt and Ronald Mailach
Aerospace 2024, 11(5), 355; https://doi.org/10.3390/aerospace11050355 - 29 Apr 2024
Viewed by 1650
Abstract
This paper discusses various strategies for probabilistic analysis, with a focus on typical engineering applications. The emphasis is on sampling methods and sensitivity analysis. A new sampling method, Latinized particle sampling, is introduced and compared to existing sampling methods. While it can increase [...] Read more.
This paper discusses various strategies for probabilistic analysis, with a focus on typical engineering applications. The emphasis is on sampling methods and sensitivity analysis. A new sampling method, Latinized particle sampling, is introduced and compared to existing sampling methods. While it can increase the quality of surrogate models, an optimized Latin hypercube sampling is mostly preferable as it shows slightly better results. In sensitivity analysis, the difficulty lies in correlated input variables, which are typical in engineering applications. First, the Sobol indices and the Shapley values are explained using an intuitive example. Then, the modified coefficient of importance is introduced as a new sensitivity measure, which can be used to reliably identify input variables without functional influence. Finally, these results are applied to a turbomachinery test case. In this case, the flow field of a compressor row is investigated, where the blades are subjected to geometric variability. The profile parameters used to describe the geometric variability are correlated. It is shown that the variability of the maximum camber and the thickness of the leading edge have a decisive influence on the variability of the isentropic efficiency. Full article
(This article belongs to the Special Issue Data-Driven Aerodynamic Modeling)
Show Figures

Figure 1

22 pages, 1815 KiB  
Article
A Python Toolbox for Data-Driven Aerodynamic Modeling Using Sparse Gaussian Processes
by Hugo Valayer, Nathalie Bartoli, Mauricio Castaño-Aguirre, Rémi Lafage, Thierry Lefebvre, Andrés F. López-Lopera and Sylvain Mouton
Aerospace 2024, 11(4), 260; https://doi.org/10.3390/aerospace11040260 - 27 Mar 2024
Viewed by 2090
Abstract
In aerodynamics, characterizing the aerodynamic behavior of aircraft typically requires a large number of observation data points. Real experiments can generate thousands of data points with suitable accuracy, but they are time-consuming and resource-intensive. Consequently, conducting real experiments at new input configurations might [...] Read more.
In aerodynamics, characterizing the aerodynamic behavior of aircraft typically requires a large number of observation data points. Real experiments can generate thousands of data points with suitable accuracy, but they are time-consuming and resource-intensive. Consequently, conducting real experiments at new input configurations might be impractical. To address this challenge, data-driven surrogate models have emerged as a cost-effective and time-efficient alternative. They provide simplified mathematical representations that approximate the output of interest. Models based on Gaussian Processes (GPs) have gained popularity in aerodynamics due to their ability to provide accurate predictions and quantify uncertainty while maintaining tractable execution times. To handle large datasets, sparse approximations of GPs have been further investigated to reduce the computational complexity of exact inference. In this paper, we revisit and adapt two classic sparse methods for GPs to address the specific requirements frequently encountered in aerodynamic applications. We compare different strategies for choosing the inducing inputs, which significantly impact the complexity reduction. We formally integrate our implementations into the open-source Python toolbox SMT, enabling the use of sparse methods across the GP regression pipeline. We demonstrate the performance of our Sparse GP (SGP) developments in a comprehensive 1D analytic example as well as in a real wind tunnel application with thousands of training data points. Full article
(This article belongs to the Special Issue Data-Driven Aerodynamic Modeling)
Show Figures

Figure 1

18 pages, 15675 KiB  
Article
Adaptive Turbulence Model for Leading Edge Vortex Flows Preconditioned by a Hybrid Neural Network
by Moritz Zieher and Christian Breitsamter
Aerospace 2024, 11(3), 238; https://doi.org/10.3390/aerospace11030238 - 18 Mar 2024
Cited by 1 | Viewed by 1569
Abstract
Eddy-viscosity-based turbulence models provide the most commonly used modeling approach for computational fluid dynamics simulations in the aerospace industry. These models are very accurate at a relatively low cost for many cases but lack accuracy in the case of highly rotational leading edge [...] Read more.
Eddy-viscosity-based turbulence models provide the most commonly used modeling approach for computational fluid dynamics simulations in the aerospace industry. These models are very accurate at a relatively low cost for many cases but lack accuracy in the case of highly rotational leading edge vortex flows for mid to low aspect-ratio wings. An enhanced adaptive turbulence model based on the one-equation Spalart–Allmaras turbulence model is fundamental to this work. This model employs several additional coefficients and source terms, specifically targeting vortex-dominated flow regions, where these coefficients can be calibrated by an optimization procedure based on experimental or high-fidelity numerical data. To extend the usability of the model from single or cluster-wise calibrated cases, this work presents a preconditioning approach of the turbulence model via a neural network. The neural network provides a case-unspecific calibration approach, enabling the use of the model for many known or unknown cases. This extension enables aircraft design teams to perform low-cost Reynolds-averaged Navier–Stokes simulations with increased accuracy instead of complex and costly high-fidelity simulations. Full article
(This article belongs to the Special Issue Data-Driven Aerodynamic Modeling)
Show Figures

Figure 1

Back to TopTop