Papers
Topics
Authors
Recent
Search
2000 character limit reached

Physics-Assisted Reduced-Order Modeling for Identifying Dominant Features of Transonic Buffet

Published 23 May 2023 in physics.flu-dyn and cs.LG | (2305.13644v1)

Abstract: Transonic buffet is a flow instability phenomenon that arises from the interaction between the shock wave and the separated boundary layer. This flow phenomenon is considered to be highly detrimental during flight and poses a significant risk to the structural strength and fatigue life of aircraft. Up to now, there has been a lack of an accurate, efficient, and intuitive metric to predict buffet and impose a feasible constraint on aerodynamic design. In this paper, a Physics-Assisted Variational Autoencoder (PAVAE) is proposed to identify dominant features of transonic buffet, which combines unsupervised reduced-order modeling with additional physical information embedded via a buffet classifier. Specifically, four models with various weights adjusting the contribution of the classifier are trained, so as to investigate the impact of buffet information on the latent space. Statistical results reveal that buffet state can be determined exactly with just one latent space when a proper weight of classifier is chosen. The dominant latent space further reveals a strong relevance with the key flow features located in the boundary layers downstream of shock. Based on this identification, the displacement thickness at 80% chordwise location is proposed as a metric for buffet prediction. This metric achieves an accuracy of 98.5% in buffet state classification, which is more reliable than the existing separation metric used in design. The proposed method integrates the benefits of feature extraction, flow reconstruction, and buffet prediction into a unified framework, demonstrating its potential in low-dimensional representations of high-dimensional flow data and interpreting the "black box" neural network.

Authors (4)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. S. Timme, “Global instability of wing shock-buffet onset,” Journal of Fluid Mechanics 885 (2020).
  2. N. F. Giannelis, G. A. Vio,  and O. Levinski, “A review of recent developments in the understanding of transonic shock buffet,” Progress in Aerospace Sciences 92, 39–84 (2017).
  3. M. Thiery and E. Coustols, “Urans computations of shock-induced oscillations over 2d rigid airfoils: influence of test section geometry,” Flow, Turbulence and Combustion 74, 331–354 (2005).
  4. S. Deck, “Numerical simulation of transonic buffet over a supercritical airfoil,” AIAA Journal 43, 1556–1566 (2005).
  5. J. Dandois, I. Mary,  and V. Brion, “Large-eddy simulation of laminar transonic buffet,” Journal of Fluid Mechanics 850, 156–178 (2018).
  6. J. Crouch, A. Garbaruk, D. Magidov,  and A. Travin, “Origin of transonic buffet on aerofoils,” Journal of fluid mechanics 628, 357–369 (2009).
  7. F. Sartor and S. Timme, “Mach number effects on buffeting flow on a half wing-body configuration,” International Journal of Numerical Methods for Heat & Fluid Flow  (2016).
  8. J. Van Eijndhoven, “Buffet envelope prediction of transport aircraft during the conceptual design phase,”   (2012).
  9. H. Pearcey, “A method for the prediction of the onset of buffeting and other separation effects from wind tunnel tests on rigid models,” Tech. Rep. (ADVISORY GROUP FOR AERONAUTICAL RESEARCH AND DEVELOPMENT PARIS (FRANCE), 1958).
  10. H. Pearcey and D. Holder, Simple methods for the prediction of wing buffeting resulting from bubble type separation (NPL, 1962).
  11. G. Redeker, “Calculation of buffet onset for supercritical airfoils,” in Symposium Transsonicum II (Springer, 1976) pp. 66–74.
  12. G. K. Kenway and J. R. Martins, “Buffet-onset constraint formulation for aerodynamic shape optimization,” AIAA Journal 55, 1930–1947 (2017).
  13. J. Nitzsche, “A numerical study on aerodynamic resonance in transonic separated flow,”   (2009).
  14. M. Iovnovich and D. E. Raveh, “Reynolds-averaged navier-stokes study of the shock-buffet instability mechanism,” AIAA Journal 50, 880–890 (2012).
  15. B. Lee, “Self-sustained shock oscillations on airfoils at transonic speeds,” Progress in Aerospace Sciences 37, 147–196 (2001).
  16. J. Li, S. He, M. Zhang, J. R. Martins,  and B. Cheong Khoo, “Physics-based data-driven buffet-onset constraint for aerodynamic shape optimization,” AIAA Journal , 1–14 (2022).
  17. J. Kou, S. Le Clainche,  and W. Zhang, “A reduced-order model for compressible flows with buffeting condition using higher order dynamic mode decomposition with a mode selection criterion,” Physics of Fluids 30, 016103 (2018).
  18. S. L. Brunton, B. R. Noack,  and P. Koumoutsakos, “Machine learning for fluid mechanics,” Annual review of fluid mechanics 52, 477–508 (2020).
  19. K. Taira, S. L. Brunton, S. T. Dawson, C. W. Rowley, T. Colonius, B. J. McKeon, O. T. Schmidt, S. Gordeyev, V. Theofilis,  and L. S. Ukeiley, “Modal analysis of fluid flows: An overview,” Aiaa Journal 55, 4013–4041 (2017).
  20. L. Sirovich, “Turbulence and the dynamics of coherent structures. i. coherent structures,” Quarterly of applied mathematics 45, 561–571 (1987).
  21. P. J. Schmid, “Dynamic mode decomposition of numerical and experimental data,” Journal of fluid mechanics 656, 5–28 (2010).
  22. X. Zhang, T. Ji, F. Xie, C. Zheng,  and Y. Zheng, “Data-driven nonlinear reduced-order modeling of unsteady fluid–structure interactions,” Physics of Fluids 34, 053608 (2022).
  23. K. Fukami, T. Nakamura,  and K. Fukagata, “Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data,” Physics of Fluids 32, 095110 (2020).
  24. C. L. Rumsey, D. O. Allison, R. T. Biedron, P. G. Buning, T. G. Gainer, J. H. Morrison, S. M. Rivers, S. J. Mysko,  and D. P. Witkowski, “Cfd sensitivity analysis of a modern civil transport near buffet-onset conditions,” Tech. Rep. (2001).
  25. S. L. Krist, CFL3D user’s manual (version 5.0) (National Aeronautics and Space Administration, Langley Research Center, 1998).
  26. F. Menter and C. Rumsey, “Assessment of two-equation turbulence models for transonic flows,” in Fluid Dynamics Conference (1994) p. 2343.
  27. B. Van Leer, “Upwind-difference methods for aerodynamic problems governed by the euler equations,” Large-scale computations in fluid mechanics , 327–336 (1985).
  28. P. L. Roe, “Approximate riemann solvers, parameter vectors, and difference schemes,” Journal of computational physics 43, 357–372 (1981).
  29. S. Yoon and A. Jameson, “Lower-upper symmetric-gauss-seidel method for the euler and navier-stokes equations,” AIAA journal 26, 1025–1026 (1988).
  30. B. Kulfan and J. Bussoletti, “"fundamental" parameteric geometry representations for aircraft component shapes,” in 11th AIAA/ISSMO multidisciplinary analysis and optimization conference (2006) p. 6948.
  31. L. Runze, Y. Zhang,  and C. Haixin, “Pressure distribution feature-oriented sampling for statistical analysis of supercritical airfoil aerodynamics,” Chinese Journal of Aeronautics 35, 134–147 (2022).
  32. H. Eivazi, S. Le Clainche, S. Hoyas,  and R. Vinuesa, “Towards extraction of orthogonal and parsimonious non-linear modes from turbulent flows,” Expert Systems with Applications 202, 117038 (2022).
  33. Y.-E. Kang, S. Yang,  and K. Yee, “Physics-aware reduced-order modeling of transonic flow via β𝛽\betaitalic_β-variational autoencoder,” Physics of Fluids 34, 076103 (2022).
  34. D. P. Kingma and M. Welling, “Auto-encoding variational bayes,” arXiv preprint  (2013).
  35. J. Qu, W. Cai,  and Y. Zhao, “Deep learning method for identifying the minimal representations and nonlinear mode decomposition of fluid flows,” Physics of Fluids 33, 103607 (2021).
  36. Y. Yang, R. Li, Y. Zhang,  and H. Chen, “Flowfield prediction of airfoil off-design conditions based on a modified variational autoencoder,” AIAA Journal 60, 5805–5820 (2022).
  37. C. P. Burgess, I. Higgins, A. Pal, L. Matthey, N. Watters, G. Desjardins,  and A. Lerchner, “Understanding disentangling in beta-vae,” arXiv preprint arXiv:1804.03599  (2018).
  38. J. Wu, “Introduction to convolutional neural networks,” National Key Lab for Novel Software Technology. Nanjing University. China 5, 23 (2017).
  39. R. Han, Y. Wang, Y. Zhang,  and G. Chen, “A novel spatial-temporal prediction method for unsteady wake flows based on hybrid deep neural network,” Physics of Fluids 31, 127101 (2019).
  40. C. Szegedy, S. Ioffe, V. Vanhoucke,  and A. Alemi, “Inception-v4, Inception-Resnet and the impact of residual connections on learning,” in Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 31 (2017).
  41. J. Wang, C. He, R. Li, H. Chen, C. Zhai,  and M. Zhang, “Flow field prediction of supercritical airfoils via variational autoencoder based deep learning framework,” Physics of Fluids 33, 086108 (2021).
  42. L. Agostini, “Exploration and prediction of fluid dynamical systems using auto-encoder technology,” Physics of Fluids 32, 067103 (2020).
  43. T. Murata, K. Fukami,  and K. Fukagata, “Nonlinear mode decomposition with convolutional neural networks for fluid dynamics,” Journal of Fluid Mechanics 882 (2020).
  44. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint  (2014).
  45. A. Gotmare, N. S. Keskar, C. Xiong,  and R. Socher, “A closer look at deep learning heuristics: Learning rate restarts, warmup and distillation,” arXiv preprint  (2018).
  46. L. McInnes, J. Healy,  and J. Melville, “Umap: Uniform manifold approximation and projection for dimension reduction,” arXiv preprint arXiv:1802.03426  (2018).
  47. R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh,  and D. Batra, “Grad-cam: Visual explanations from deep networks via gradient-based localization,” in Proceedings of the IEEE international conference on computer vision (2017) pp. 618–626.
  48. M. T. Ribeiro, S. Singh,  and C. Guestrin, “" why should i trust you?" explaining the predictions of any classifier,” in Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (2016) pp. 1135–1144.
  49. J. Crouch, A. Garbaruk,  and M. Strelets, “Global instability in the onset of transonic-wing buffet,” Journal of Fluid Mechanics 881, 3–22 (2019).
  50. E. Paladini, O. Marquet, D. Sipp, J.-C. Robinet,  and J. Dandois, “Various approaches to determine active regions in an unstable global mode: application to transonic buffet,” Journal of Fluid Mechanics 881, 617–647 (2019).
Citations (8)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now