AI-based method of vortex core tracking as an alternative for Lambda2

• Autorzy: Majchrzak Maciej , Jakubowski Mateusz , Starosta Roman

Identyfikatory

DOI

10.21008/j.0860-6897.2020.3.19

• Języki publikacji: EN

Abstrakty

EN

The paper presents a new method of vortex core detection developed for use in CFD simulation result analysis. Apart from the conventional approach involving vector algebra, mainly the Lambda2 method, it focuses on the identification of certain features in a graphic representation of the velocity field. It is done by generating a series of slices of the said field in the postprocessing software and training a Convolutional Neural Network (AI) to recognize vortex cores. The neural network can be integrated into a simple python program and used to quickly identify vortex cores on a large number of images and translate their locations to coordinates of a CFD model for visualisation.

Słowa kluczowe

EN

vortex core tracking; Lambda2; AI; neural network

PL

rdzeń wiru; Lambda2; AI; sieć neuronowa

• Wydawca: Poznan University of Technology. Institute of Applied Mechanics
• Czasopismo: Vibrations in Physical Systems
• Rocznik: 2020
• Tom: Vol. 31, nr 3
• Strony: art. no. 2020319
• Opis fizyczny: Bibliogr. 10 poz., il. kolor., fot., rys.

Twórcy

autor

Majchrzak Maciej

• Konstrubowski Engineering Group, ul. 28 Czerwca 1956r. 406, 61-441 Poznań, Poland

autor

Jakubowski Mateusz

• Institute of Applied Mechanics, Poznan University of Technology, ul. Jana Pawła II 24, 60-965 Poznań, Poland

autor

Starosta Roman

• Institute of Applied Mechanics, Poznan University of Technology, ul. Jana Pawła II 24, 60-965 Poznań, Poland

Bibliografia

• 1. D. Aljure, I. Rodriguez, O. Lehmkuhl, R.Borrell, A.Oliva, Flow and turbulent structures around simplified cars models, Conference Paper: Conference on Modelling Fluid Flow (CMFF’12), Budapest, Hungary, September 4-7, 2012.
• 2. J. Jeong and F. Hussain. On the Identification of a Vortex. J. Fluid Mechanics, 285 (1995) 69 - 94.
• 3. Z.J. Taylor, E. Palombi, R. Gurka, G.A. Kopp, Features of the turbulent flow around symmetric elongated bluff bodies, J. Fluid Struct., 27(2) (2011) 250 - 265.
• 4. Z. Khatir, A boundary element method for the numerical investigation of near-wall fluid flow with vortex method simulation, Eng. Anal. Bound. Elem., 28 (2004) 1405-1416.
• 5. Y. Zhang, K. Liu, H. Xian, X. Du, A review of methods for vortex identification in hydroturbines, Renew.Sust.Energ. Rev., 81 (2018) 1269-1285.
• 6. M. Matsumoto, Vortex shedding of bluff bodies: a review, J. Fluid Struct., 13 (1999) 791 - 811.
• 7. TY Lin, P. Goyal, R. Girshick, K. He, P. Dollar, Focal Loss for Dense Object Detection, arXiv.org 1708.02002 (2017).
• 8. Q. Ji, J. Huang, W. He, Y. Sun, Optimized Deep Convolutional Neural Networks for Identification of Macular Diseases from Optical Coherence Tomography Images, Algorithms (2019) 12(3) 51.
• 9. F.R. Menter, Two-equation Eddy-Viscosity Turbulence Models for Engineering Applications, AIAA Journal. 32(8) (1994) 1598 - 1605.
• 10. V.H. Phung, E.J. Rhee, A Deep Learning Approach for Classification of Cloud Image Patches on Small Datasets, Journal of information and communication convergence engineering, 16(3) (2018) 173 - 178.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).