Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
129 tokens/sec
GPT-4o
28 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Parametric Learning of Time-Advancement Operators for Unstable Flame Evolution (2402.10238v1)

Published 14 Feb 2024 in cs.LG

Abstract: This study investigates the application of machine learning, specifically Fourier Neural Operator (FNO) and Convolutional Neural Network (CNN), to learn time-advancement operators for parametric partial differential equations (PDEs). Our focus is on extending existing operator learning methods to handle additional inputs representing PDE parameters. The goal is to create a unified learning approach that accurately predicts short-term solutions and provides robust long-term statistics under diverse parameter conditions, facilitating computational cost savings and accelerating development in engineering simulations. We develop and compare parametric learning methods based on FNO and CNN, evaluating their effectiveness in learning parametric-dependent solution time-advancement operators for one-dimensional PDEs and realistic flame front evolution data obtained from direct numerical simulations of the Navier-Stokes equations.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. X. Guo, W. Li, and F. Iorio, “Convolutional neural networks for steady flow approximation,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016).
  2. Y. Zhu and N. Zabaras, “Bayesian deep convolutional encoder–decoder networks for surrogate modeling and uncertainty quantification,” Journal of Computational Physics 366, 415–447 (2018).
  3. J. Adler and O. Öktem, “Solving ill-posed inverse problems using iterative deep neural networks,” Inverse Problems 33, 124007 (2017).
  4. S. Bhatnagar, Y. Afshar, S. Pan, K. Duraisamy, and S. Kaushik, “Prediction of aerodynamic flow fields using convolutional neural networks,” Computational Mechanics 64, 525–545 (2019).
  5. Y. KHOO, J. LU, and L. YING, ‘‘Solving parametric pde problems with artificial neural networks,” European Journal of Applied Mathematics 32, 421–435 (2021).
  6. O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,”  (2015), arXiv:1505.04597 [cs.CV] .
  7. N. Winovich, K. Ramani, and G. Lin, “Convpde-uq: Convolutional neural networks with quantified uncertainty for heterogeneous elliptic partial differential equations on varied domains,” Journal of Computational Physics 394, 263–279 (2019).
  8. Z. Li, N. Kovachki, K. Azizzadenesheli, B. Liu, K. Bhattacharya, A. Stuart, and A. Anandkumar, “Neural operator: Graph kernel network for partial differential equations,”  (2020a), arXiv:2003.03485 [cs.LG] .
  9. N. Kovachki, Z. Li, B. Liu, K. Azizzadenesheli, K. Bhattacharya, A. Stuart, and A. Anandkumar, “Neural operator: Learning maps between function spaces,” arXiv preprint arXiv:2108.08481  (2021).
  10. L. Lu, P. Jin, and G. Karniadakis, “Deeponet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators,”  (2019), arXiv:1910.03193 [cs.LG] .
  11. Z. Li, N. Kovachki, K. Azizzadenesheli, B. Liu, K. Bhattacharya, A. Stuart, and A. Anandkumar, “Fourier neural operator for parametric partial differential equations,”  (2020b), arXiv:2010.08895 [cs.LG] .
  12. K. N., L. S., and M. S., “On universal approximation and error bounds for fourier neural operators,”  (2021), arXiv:2107.07562 [math.NA] .
  13. C. T. and C. H., “Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems,” IEEE Trans. Neural Netw. 6, 911–917 (1995).
  14. S. Lanthaler, Z. Li, and A. M. Stuart, “The nonlocal neural operator: Universal approximation,” arXiv preprint arXiv:2304.13221  (2023).
  15. L. Lu, P. Jin, G. Pang, Z. Zhang, and G. Karniadakis, “Learning nonlinear operators via deeponet based on the universal approximation theorem of operators,” Nat. Mach. Intell. 3, 218–229 (2021).
  16. L. Lu, X. Meng, S. Cai, Z. Mao, S. Goswami, Z. Zhang, and G. Karniadakis, “A comprehensive and fair comparison of two neural operators (with practical extensions) based on fair data,” Computer Methods in Applied Mechanics and Engineering 393, 114778 (2022).
  17. G. Gupta, X. Xiao, and P. Bogdan, “Multiwavelet-based operator learning for differential equations,” Advances in neural information processing systems 34, 24048–24062 (2021).
  18. T. Tripura and S. Chakraborty, “Wavelet neural operator for solving parametric partial differential equations in computational mechanics problems,” Computer Methods in Applied Mechanics and Engineering 404, 115783 (2023).
  19. G. Chen, X. Liu, Y. Li, Q. Meng, and L. Chen, “Laplace neural operator for complex geometries,” arXiv preprint arXiv:2302.08166  (2023).
  20. J. Pathak, S. Subramanian, P. Harrington, S. Raja, A. Chattopadhyay, M. Mardani, T. Kurth, D. Hall, Z. Li, K. Azizzadenesheli, et al., “Fourcastnet: A global data-driven high-resolution weather model using adaptive fourier neural operators,” arXiv preprint arXiv:2202.11214  (2022).
  21. R. Yu, “Deep learning of nonlinear flame fronts development due to darrieus–landau instability,” APL APL Machine Learning 1, 026106 (2023).
  22. A. Ghadami and B. I. Epureanu, “Deep learning for centre manifold reduction and stability analysis in nonlinear systems,” Philosophical Transactions of the Royal Society A 380, 20210212 (2022).
  23. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” in Proceedings of the IEEE conference on computer vision and pattern recognition (2016) pp. 2818–2826.
  24. D. M. Michelson and G. I. Sivashinsky, “Nonlinear analysis of hydrodynamic instability in laminar flames—ii. numerical experiments,” Acta astronautica 4, 1207–1221 (1977).
  25. G.I.Sivashinsky, ‘‘Nonlinear analysis of hydrodynamic instability in laminar flames—i. derivation of basic equations,” Acta Astronautica 4, 1177–1206 (1977).
  26. Y. Kuramoto, “Diffusion-induced chaos in reaction systems,” Progress of Theoretical Physics Supplement 64, 346–367 (1978).
  27. G. Darrieus, “Propagation d’un front de flamme,” Unpublished work presented at La Technique Moderne  (1938).
  28. L. Landau, “On the theory of slow combustion,” in Dynamics of curved fronts (Elsevier, 1988) pp. 403–411.
  29. Y. Zeldovich, “Theory of combustion and detonation of gases,” in Selected Works of Yakov Borisovich Zeldovich, Volume I: Chemical Physics and Hydrodynamics (Princeton University Press, 1944).
  30. G. Sivashinsky, “Diffusional-thermal theory of cellular flames,” Combustion Science and Technology 15, 137–145 (1977).
  31. R. Yu, X. S. Bai, and V. Bychkov, “Fractal flame structure due to the hydrodynamic darrieus-landau instability,” Phys. Rev. E 92, 063028 (2015).
  32. O. Thual, U. Frisch, and M. Hénon, “Application of pole decomposition to an equation governing the dynamics of wrinkled flame fronts,” Journal de Physique 46, 1485–1494 (1985).
  33. D. Vaynblat and M. Matalon, “Stability of pole solutions for planar propagating flames: I. exact eigenvalues and eigenfunctions,” SIAM J. Appl. Math. 60, 679–702 (2000a).
  34. D. Vaynblat and M. Matalon, “Stability of pole solutions for planar propagating flames: Ii. properties of eigenvalues/eigenfunctions and implications to stability,” SIAM J. Appl. Math. 60, 703–728 (2000b).
  35. Z. Olami, B. Galanti, O. Kupervasser, and I. Procaccia, “Random noise and pole dynamics in unstable front propagation,” Physical Review E 55, 2649 (1997).
  36. B. Denet, “Stationary solutions and neumann boundary conditions in the sivashinsky equation,” Physical Review E 74, 036303 (2006).
  37. O. Kupervasser, Pole Solutions for Flame Front Propagation (Springer International Publishing, 2015).
  38. V. Karlin, “Cellular flames may exhibit a non-modal transient instability,” Proceedings of the Combustion Institute 29, 1537–1542 (2002).
  39. F. Creta, P. E. Lapenna, R. Lamioni, N. Fogla, and M. Matalon, “Propagation of premixed flames in the presence of darrieus–landau and thermal diffusive instabilities,” Combustion and Flame 216, 256–270 (2020).
  40. F. Creta, N. Fogla, and M. Matalon, “Turbulent propagation of premixed flames in the presence of darrieus–landau instability,” Combustion Theory and Modelling 15, 267–298 (2011).
  41. R. Yu, J. Yu, and X. Bai, ‘‘An improved high-order scheme for DNS of low Mach number turbulent reacting flows based on stiff chemistry solver,” J. Comput. Phys. 231, 5504 (2012).
  42. R. Yu and X. S. Bai, “A fully divergence-free method for generation of inhomogeneous and anisotropic turbulence with large spatial variation,” J. Comput. Phys. 256, 234 (2014).
  43. R. Yu and X. S. Bai, “A semi-implicit scheme for large Eddy simulation of piston engine flow and combustion,” Int. J. Numer. Methods Fluids 71, 13 (2013).
  44. J. Yu, R. Yu, X. Bai, M. Sun, and J.-G. Tan, “Nonlinear evolution of 2d cellular lean hydrogen/air premixed flames with varying initial perturbations in the elevated pressure environment,” International Journal of Hydrogen Energy 42, 3790–3803 (2017).
  45. R. Yu and A. N. Lipatnikov, “Surface-averaged quantities in turbulent reacting flows and relevant evolution equations,” Phys. Rev. E 100, 013107 (2019).
  46. R. Yu, T. Nillson, X. Bai, and A. N. Lipatnikov, “Evolution of averaged local premixed flame thickness in a turbulent flow,” Combust. Flame 207, 232–249 (2019).
  47. R. Yu, T. Nilsson, C. Fureby, and A. Lipatnikov, “Evolution equations for the decomposed components of displacement speed in a reactive scalar field,” Journal of Fluid Mechanics 911 (2021).
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets