Leading edge vortex formation and wake trajectory: Synthesizing measurements, analysis, and machine learning

Lee, Howon; Simone, Nicholas; Su, Yunxing; Zhu, Yuanhang; Ribeiro, Bernardo Luiz Rocha; Franck, Jennifer A.; Breuer, Kenneth S.

doi:10.1103/physrevfluids.7.074704

Cited by 6 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In these instances, supervised machine learning has played a pivotal role by approximating the intricate connections between input and target data, leveraging its remarkable universal approximation capabilities [28,29]. Lee et al [30], support vector regression is employed within the őeld of ŕuid dynamics to differentiate between diverse ŕow conditions and dynamic regimes. Support vector machines (SVMs) have established themselves as a classical machine learning algorithm for addressing classiőcation challenges.…”

Section: Literature Reviewmentioning

confidence: 99%

A Hybrid Computer Vision and Machine Learning Approach for Robust Vortex Core Detection in Fluid Mechanics Applications

Amran Abolholl,

Teschner,

Moulitsas

2024

Journal of Computing and Information Science in Engineering

View full text Add to dashboard Cite

Vortex core detection remains an unsolved problem in the field of experimental and computational fluid dynamics. Available methods such as the Q, delta and swirling-strength criterion are based on a decomposed velocity gradient tensor but detect spurious vortices (false positives and false negatives), making these methods less robust. To overcome this, we propose a new hybrid machine learning approach in which we used a convolutional neural network to detect vortex regions within surface streamline plots and an additional deep neural network to detect vortex cores within identified vortex regions. Furthermore, we propose an automatic labelling approach based on K-means clustering to pre-process our input images. We show results for two classical test cases in fluid mechanics; the Taylor-Green vortex problem and two rotating blades. We show that our hybrid approach is up to 2.6 times faster than a pure deep neural network-based approach and furthermore show that our automatic K-means clustering labelling approach is within 0.45% mean square error of the more labour-intensive, manual labelling approach. At the same time, using a sufficient number of samples, we show that we are able to reduce false positives and negatives entirely and thus show that our hybrid machine learning approach is a viable alternative to currently used vortex detection tools in fluid mechanics applications.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Hybrid Computer Vision and Machine Learning Approach for Robust Vortex Core Detection in Fluid Mechanics Applications

Amran Abolholl,

Teschner,

Moulitsas

2024

Journal of Computing and Information Science in Engineering

View full text Add to dashboard Cite

show abstract

“…where Q is the second invariant of the velocity gradient tensor, Ω is the vorticity tensor and S is the strain-rate tensor. Connected regions with Q > 0, where rotation is higher than strain, are identified as a vortex (Lee et al, 2022). The position of the vortex core is calculated as the centroid of the top ten Q values within the vortex boundary.…”

Section: Vortex Identification and Trajectory Trackingmentioning

confidence: 99%

Force moment partitioning and scaling analysis of vortices shed by a 2D pitching wing in quiescent fluid

Zhu¹,

Lee²,

Kumar³

et al. 2023

Preprint

View full text Add to dashboard Cite

We experimentally study the dynamics and strength of vortices shed from a NACA 0012 wing undergoing sinusoidal pitching in quiescent water. We characterize the temporal evolution of the vortex trajectory and circulation over a range of pitching frequencies, amplitudes and pivot locations. By employing a physics-based force and moment partitioning method (FMPM), we estimate the vortex-induced aerodynamic moment from the velocity fields measured using particle image velocimetry. The vortex circulation, formation time and vorticity-induced moment are shown to follow scaling laws based on the feeding shear-layer velocity. The vortex dynamics, together with the spatial distribution of the vorticity-induced moment, provide quantitative explanations for the nonlinear behaviors observed in the fluid damping (

show abstract

“…With the rapid development of machine learning tools in fluid mechanics (Brunton et al, 2016;Brenner et al, 2019;Raissi et al, 2019;Brunton et al, 2020;Kou and Zhang, 2021;Menon and Mittal, 2021;Lee et al, 2022;Siddiqui et al, 2022;Mishra et al, 2023;Ribeiro and Franck, 2023;Hickner et al, 2023;Fukami and Taira, 2023;Graff et al, 2023;Chen et al, 2023;Carter and Ganapathisubramani, 2023), we see a possibility of better bridging one-way and two-way coupling FSI problems and substantially reducing the experimental and computational costs of studying nonlinear aeroelastic systems. In the present study, we propose a data-driven approach to model large-amplitude aeroelastic oscillations of pitching wings.…”

Section: Introductionmentioning

confidence: 99%

A Data-Driven Experimental Approach for Modeling Aeroelastic Instabilities of Pitching Wings

Zhu

Breuer

2023

AIAA SCITECH 2023 Forum

View full text Add to dashboard Cite

We propose and validate a data-driven approach for modeling large-amplitude flow-induced oscillations of elastically mounted pitching wings. We first train a neural networks regression model for the nonlinear aerodynamic moment using data obtained from purely prescribed oscillations and static measurements. We then embed this model into an ordinary differential equation solver to solve for the governing equation of the passive aeroelastic system with desired structural parameters. The system dynamics predicted by the proposed data-driven method are characterized and compared with those obtained from physical experiments. The predicted and experimental pitching amplitude, frequency and aerodynamic moment responses are found to be in excellent agreement. Both the structural mode of high-inertia wings and the hydrodynamic mode of lowinertia wings are successfully predicted. The transient growth and saturation of the oscillation amplitude and the aerodynamic moment are also faithfully captured by the proposed method. Additional test cases demonstrate the broad applicability of this approach.

show abstract

Leading edge vortex formation and wake trajectory: Synthesizing measurements, analysis, and machine learning

Cited by 6 publications

References 27 publications

A Hybrid Computer Vision and Machine Learning Approach for Robust Vortex Core Detection in Fluid Mechanics Applications

A Hybrid Computer Vision and Machine Learning Approach for Robust Vortex Core Detection in Fluid Mechanics Applications

Force moment partitioning and scaling analysis of vortices shed by a 2D pitching wing in quiescent fluid

A Data-Driven Experimental Approach for Modeling Aeroelastic Instabilities of Pitching Wings

Contact Info

Product

Resources

About