Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

A Multi-Fidelity Methodology for Reduced Order Models with High-Dimensional Inputs (2402.17061v1)

Published 26 Feb 2024 in cs.LG

Abstract: In the early stages of aerospace design, reduced order models (ROMs) are crucial for minimizing computational costs associated with using physics-rich field information in many-query scenarios requiring multiple evaluations. The intricacy of aerospace design demands the use of high-dimensional design spaces to capture detailed features and design variability accurately. However, these spaces introduce significant challenges, including the curse of dimensionality, which stems from both high-dimensional inputs and outputs necessitating substantial training data and computational effort. To address these complexities, this study introduces a novel multi-fidelity, parametric, and non-intrusive ROM framework designed for high-dimensional contexts. It integrates machine learning techniques for manifold alignment and dimension reduction employing Proper Orthogonal Decomposition (POD) and Model-based Active Subspace with multi-fidelity regression for ROM construction. Our approach is validated through two test cases: the 2D RAE~2822 airfoil and the 3D NASA CRM wing, assessing combinations of various fidelity levels, training data ratios, and sample sizes. Compared to the single-fidelity PCAS method, our multi-fidelity solution offers improved cost-accuracy benefits and achieves better predictive accuracy with reduced computational demands. Moreover, our methodology outperforms the manifold-aligned ROM (MA-ROM) method by 50% in handling scenarios with large input dimensions, underscoring its efficacy in addressing the complex challenges of aerospace design.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (73)
  1. Benner, P., Gugercin, S., and Willcox, K., “A survey of projection-based model reduction methods for parametric dynamical systems,” SIAM review, Vol. 57, No. 4, 2015, pp. 483–531.
  2. Yondo, R., Andrés, E., and Valero, E., “A review on design of experiments and surrogate models in aircraft real-time and many-query aerodynamic analyses,” Progress in aerospace sciences, Vol. 96, 2018, pp. 23–61.
  3. Forrester, A. I., and Keane, A. J., “Recent advances in surrogate-based optimization,” Progress in Aerospace Sciences, Vol. 45, No. 1-3, 2009, pp. 50–79. 10.1016/j.paerosci.2008.11.001.
  4. Xiao, D., Fang, F., Buchan, A. G., Pain, C. C., Navon, I. M., and Muggeridge, A., “Non-intrusive reduced order modelling of the Navier-Stokes equations,” Computer Methods in Applied Mechanics and Engineering, Vol. 293, 2015, pp. 522–541. 10.1016/j.cma.2015.05.015.
  5. Lu, K., Jin, Y., Chen, Y., Yang, Y., Hou, L., Zhang, Z., Li, Z., and Fu, C., “Review for order reduction based on proper orthogonal decomposition and outlooks of applications in mechanical systems,” Mechanical Systems and Signal Processing, Vol. 123, 2019, pp. 264–297.
  6. Fossati, M., “Evaluation of aerodynamic loads via reduced-order methodology,” AIAA Journal, Vol. 53, No. 8, 2015, pp. 2389–2405. 10.2514/1.J053755.
  7. Decker, K., Schwartz, H. D., and Mavris, D., “Dimensionality reduction techniques applied to the design of hypersonic aerial systems,” AIAA Aviation 2020 Forum, 2020, p. 3003.
  8. Rajaram, D., Perron, C., Puranik, T. G., and Mavris, D. N., “Randomized algorithms for non-intrusive parametric reduced order modeling,” AIAA Journal, Vol. 58, No. 12, 2020a, pp. 5389–5407.
  9. Behere, A., Rajaram, D., Puranik, T. G., Kirby, M., and Mavris, D. N., “Reduced order modeling methods for aviation noise estimation,” Sustainability (Switzerland), Vol. 13, No. 3, 2021, pp. 1–19. 10.3390/su13031120.
  10. Chen, L. W., and Thuerey, N., “Towards high-accuracy deep learning inference of compressible flows over aerofoils,” Computers & Fluids, Vol. 250, 2023, p. 105707. 10.1016/J.COMPFLUID.2022.105707.
  11. Kashefi, A., Rempe, D., and Guibas, L. J., “A point-cloud deep learning framework for prediction of fluid flow fields on irregular geometries,” Physics of Fluids, Vol. 33, No. 2, 2021. 10.1063/5.0033376.
  12. Deng, Z., Wang, J., Liu, H., Xie, H., Li, B. K., Zhang, M., Jia, T., Zhang, Y., Wang, Z., and Dong, B., “Prediction of transonic flow over supercritical airfoils using geometric-encoding and deep-learning strategies,” Physics of Fluids, Vol. 35, No. 7, 2023. 10.1063/5.0155383.
  13. Mufti, B., Bhaduri, A., Ghosh, S., Wang, L., and Mavris, D. N., “Shock wave prediction in transonic flow fields using domain-informed probabilistic deep learning,” Physics of Fluids, Vol. 36, No. 1, 2024.
  14. Koch, P. N., Simpson, T. W., Allen, J. K., and Mistree, F., “Statistical Approximations for Multidisciplinary Design Optimization: The Problem of Size,” Journal of Aircraft, Vol. 36, No. 1, 1999, pp. 275–286. 10.2514/2.2435, URL https://arc.aiaa.org/doi/10.2514/2.2435.
  15. Kumari, S., and Jayaram, B., “Measuring Concentration of Distances—An Effective and Efficient Empirical Index,” IEEE Transactions on Knowledge and Data Engineering, Vol. 29, No. 2, 2017, pp. 373–386. 10.1109/TKDE.2016.2622270.
  16. Brunton, S. L., Noack, B. R., and Koumoutsakos, P., “Annual Review of Fluid Mechanics Machine Learning for Fluid Mechanics,” Annu. Rev. Fluid Mech. 2020, Vol. 52, 2019, pp. 477–508. 10.1146/annurev-fluid-010719, URL https://doi.org/10.1146/annurev-fluid-010719-.
  17. Dietrich, F., Künzner, F., Neckel, T., Köster, G., and Bungartz, H.-J., “Fast and flexible uncertainty quantification through a data-driven surrogate model,” International Journal for Uncertainty Quantification, Vol. 8, No. 2, 2018.
  18. Neal, R. M., “Assessing relevance determination methods using DELVE,” Nato Asi Series F Computer And Systems Sciences, Vol. 168, 1998, pp. 97–132.
  19. Bouhlel, M. A., Bartoli, N., Otsmane, A., and Morlier, J., “An Improved Approach for Estimating the Hyperparameters of the Kriging Model for High-Dimensional Problems through the Partial Least Squares Method,” Mathematical Problems in Engineering, Vol. 2016, 2016. 10.1155/2016/6723410.
  20. Constantine, P. G., Dow, E., and Wang, Q., “Active Subspace Methods in Theory and Practice: Applications to Kriging Surfaces,” SIAM Journal on Scientific Computing, Vol. 36, No. 4, 2014, pp. A1500–A1524. 10.1137/130916138, URL http://arxiv.org/abs/1304.2070http://dx.doi.org/10.1137/130916138http://epubs.siam.org/doi/10.1137/130916138.
  21. Berguin, S. H., and Mavris, D. N., “Dimensionality reduction using principal component analysis applied to the gradient,” AIAA Journal, Vol. 53, American Institute of Aeronautics and Astronautics Inc., 2015, pp. 1078–1090. 10.2514/1.J053372.
  22. Berguin, S. H., Rancourt, D., and Mavris, D. N., “Method to facilitate high-dimensional design space exploration using computationally expensive analyses,” AIAA Journal, Vol. 53, American Institute of Aeronautics and Astronautics Inc., 2015, pp. 3752–3765. 10.2514/1.J054035.
  23. Jiang, X., Hu, X., Liu, G., Liang, X., and Wang, R., “A generalized active subspace for dimension reduction in mixed aleatory-epistemic uncertainty quantification,” Computer Methods in Applied Mechanics and Engineering, Vol. 370, 2020. 10.1016/j.cma.2020.113240.
  24. Lukaczyk, T. W., Constantine, P., Palacios, F., and Alonso, J. J., “Active subspaces for shape optimization,” 10th AIAA multidisciplinary design optimization conference, 2014, p. 1171.
  25. Li, J., Cai, J., and Qu, K., “Surrogate-based aerodynamic shape optimization with the active subspace method,” Structural and Multidisciplinary Optimization, Vol. 59, No. 2, 2019, pp. 403–419. 10.1007/s00158-018-2073-5.
  26. Tezzele, M., Demo, N., and Rozza, G., “Shape optimization through proper orthogonal decomposition with interpolation and dynamic mode decomposition enhanced by active subspaces,” arXiv preprint arXiv:1905.05483, 2019.
  27. Wei, J., An, J., Zhang, Q., Zhou, H., and Ren, Z., “Exploiting Active Subspaces for Geometric Optimization of Cavity-Stabilized Supersonic Flames,” AIAA Journal, 2023, pp. 1–12.
  28. Constantine, P. G., Emory, M., Larsson, J., and Iaccarino, G., “Exploiting active subspaces to quantify uncertainty in the numerical simulation of the HyShot II scramjet,” Journal of Computational Physics, Vol. 302, 2015, pp. 1–20. https://doi.org/10.1016/j.jcp.2015.09.001, URL https://www.sciencedirect.com/science/article/pii/S002199911500580X.
  29. Khatamsaz, D., Molkeri, A., Couperthwaite, R., James, J., Arróyave, R., Srivastava, A., and Allaire, D., “Adaptive active subspace-based efficient multifidelity materials design,” Materials and Design, Vol. 209, 2021. 10.1016/j.matdes.2021.110001.
  30. Constantine, P. G., and Doostan, A., “Time-dependent global sensitivity analysis with active subspaces for a lithium ion battery model,” Statistical Analysis and Data Mining, Vol. 10, No. 5, 2017, pp. 243–262. 10.1002/sam.11347.
  31. Lam, R. R., Zahm, O., Marzouk, Y. M., and Willcox, K. E., “Multifidelity dimension reduction via active subspaces,” SIAM Journal on Scientific Computing, Vol. 42, No. 2, 2020, pp. A929–A956. 10.1137/18M1214123.
  32. Romor, F., Tezzele, M., Mrosek, M., Othmer, C., and Rozza, G., “Multi-fidelity data fusion through parameter space reduction with applications to automotive engineering,” International Journal for Numerical Methods in Engineering, Vol. 124, No. 23, 2023, pp. 5293–5311.
  33. Mufti, B., Chen, M., Perron, C., and Mavris, D. N., “A Multi-Fidelity Approximation of the Active Subspace Method for Surrogate Models with High-Dimensional Inputs,” AIAA AVIATION 2022 Forum, American Institute of Aeronautics and Astronautics Inc, AIAA, 2022. 10.2514/6.2022-3488.
  34. Tripathy, R., Bilionis, I., and Gonzalez, M., “Gaussian processes with built-in dimensionality reduction: Applications to high-dimensional uncertainty propagation,” Journal of Computational Physics, Vol. 321, 2016, pp. 191–223. 10.1016/j.jcp.2016.05.039.
  35. Tsilifis, P., Pandita, P., Ghosh, S., Andreoli, V., Vandeputte, T., and Wang, L., “Bayesian learning of orthogonal embeddings for multi-fidelity Gaussian Processes,” Computer Methods in Applied Mechanics and Engineering, Vol. 386, 2021. 10.1016/j.cma.2021.114147.
  36. Gautier, R., Pandita, P., Ghosh, S., and Mavris, D., “A Fully Bayesian Gradient-Free Supervised Dimension Reduction Method using Gaussian Processes,” International Journal for Uncertainty Quantification, Vol. 12, No. 2, 2022.
  37. Vohra, M., Nath, P., Mahadevan, S., and Tina Lee, Y. T., “Fast surrogate modeling using dimensionality reduction in model inputs and field output: Application to additive manufacturing,” Reliability Engineering and System Safety, Vol. 201, 2020. 10.1016/j.ress.2020.106986.
  38. Guo, Y., Mahadevan, S., Matsumoto, S., Taba, S., and Watanabe, D., “Investigation of Surrogate Modeling Options with High-Dimensional Input and Output,” AIAA Journal, Vol. 61, No. 3, 2023, pp. 1334–1348.
  39. Demo, N., Tezzele, M., and Rozza, G., “A non-intrusive approach for the reconstruction of POD modal coefficients through active subspaces,” Comptes Rendus Mécanique, Vol. 347, No. 11, 2019, pp. 873–881.
  40. Ji, Y., Xiao, N. C., and Zhan, H., “High dimensional reliability analysis based on combinations of adaptive Kriging and dimension reduction technique,” Quality and Reliability Engineering International, Vol. 38, No. 5, 2022, pp. 2566–2585. 10.1002/qre.3091.
  41. Rajaram, D., Gautier, R. H., Perron, C., Pinon-Fischer, O. J., and Mavris, D., “Non-intrusive parametric reduced order models with high-dimensional inputs via gradient-free active subspace,” AIAA AVIATION 2020 FORUM, 2020b, p. 3184.
  42. O’Leary-Roseberry, T., Villa, U., Chen, P., and Ghattas, O., “Derivative-informed projected neural networks for high-dimensional parametric maps governed by PDEs,” Computer Methods in Applied Mechanics and Engineering, Vol. 388, 2022. 10.1016/j.cma.2021.114199.
  43. Forrester, A. I., Sóbester, A., and Keane, A. J., “Multi-fidelity optimization via surrogate modelling,” Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 463, No. 2088, 2007. 10.1098/rspa.2007.1900.
  44. Peherstorfer, B., Willcox, K., and Gunzburger, M., “Survey of multifidelity methods in uncertainty propagation, inference, and optimization,” Siam Review, Vol. 60, No. 3, 2018, pp. 550–591.
  45. Bertram, A., Othmery, C., and Zimmermannz, R., “Towards real-time vehicle aerodynamic design via multi-fidelity data-driven reduced order modeling,” AIAA/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference, 2018, Vol. 0, American Institute of Aeronautics and Astronautics Inc, AIAA, 2018. 10.2514/6.2018-0916.
  46. Wang, C., Krafft, P., Mahadevan, S., Ma, Y., and Fu, Y., “Manifold alignment,” Manifold Learning: Theory and Applications, Vol. 510, 2011.
  47. Perron, C., “Multi-fidelity reduced-order modeling applied to fields with inconsistent representations,” Ph.D. thesis, Atlanta: Georgia Institute of Technology, 2020.
  48. Perron, C., Rajaram, D., and Mavris, D. N., “Multi-fidelity non-intrusive reduced-order modelling based on manifold alignment,” Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 477, No. 2253, 2021. 10.1098/rspa.2021.0495.
  49. Perron, C., Sarojini, D., Rajaram, D., Corman, J., and Mavris, D., “Manifold alignment-based multi-fidelity reduced-order modeling applied to structural analysis,” Structural and Multidisciplinary Optimization, Vol. 65, No. 8, 2022. 10.1007/s00158-022-03274-1.
  50. Decker, K., Iyengar, N., Rajaram, D., Perron, C., and Mavris, D., “Manifold Alignment-Based Nonintrusive and Nonlinear Multifidelity Reduced-Order Modeling,” AIAA Journal, Vol. 61, No. 1, 2023, pp. 454–474. 10.2514/1.J061720.
  51. Li, J., Du, X., and Martins, J. R., “Machine learning in aerodynamic shape optimization,” Progress in Aerospace Sciences, Vol. 134, 2022, p. 100849.
  52. Wang, C., and Mahadevan, S., “A general framework for manifold alignment,” 2009 AAAI Fall Symposium Series, 2009.
  53. Guerrero, R., Ledig, C., and Rueckert, D., “Manifold alignment and transfer learning for classification of Alzheimer’s disease,” International Workshop on Machine Learning in Medical Imaging, Springer, 2014, pp. 77–84.
  54. Bousmalis, K., Trigeorgis, G., Silberman, N., Krishnan, D., and Erhan, D., “Domain separation networks,” Advances in neural information processing systems, Vol. 29, 2016.
  55. Wang, C., and Mahadevan, S., “Manifold alignment using procrustes analysis,” Proceedings of the 25th international conference on Machine learning, 2008, pp. 1120–1127.
  56. Pinnau, R., “Model reduction via proper orthogonal decomposition,” Model order reduction: theory, research aspects and applications, Springer, 2008, pp. 95–109.
  57. Gower, J. C., “Procrustes methods,” Wiley Interdisciplinary Reviews: Computational Statistics, Vol. 2, No. 4, 2010, pp. 503–508.
  58. Choi, S., Alonso, J. J., and Kroo, H. M., “Two-level multifidelity design optimization studies for supersonic jets,” Journal of Aircraft, Vol. 46, No. 3, 2009, pp. 776–790. 10.2514/1.34362.
  59. Han, Z. H., Zimmermann, and Görtz, S., “Alternative cokriging model for variable-fidelity surrogate modeling,” AIAA Journal, Vol. 50, No. 5, 2012, pp. 1205–1210. 10.2514/1.J051243.
  60. Han, Z. H., and Görtz, S., “Hierarchical kriging model for variable-fidelity surrogate modeling,” AIAA Journal, Vol. 50, 2012, pp. 1885–1896. 10.2514/1.J051354.
  61. Mufti, B., Perron, C., Gautier, R., and Mavris, D. N., “Design Space Reduction using Multi-Fidelity Model-Based Active Subspaces,” AIAA AVIATION 2023 Forum, 2023, p. 3592.
  62. Han, Z. H., and Görtz, S., “Hierarchical kriging model for variable-fidelity surrogate modeling,” AIAA Journal, Vol. 50, No. 9, 2012, pp. 1885–1896. 10.2514/1.J051354.
  63. Economon, T. D., Palacios, F., Copeland, S. R., Lukaczyk, T. W., and Alonso, J. J., “SU2: An open-source suite for multiphysics simulation and design,” AIAA Journal, Vol. 54, No. 3, 2016, pp. 828–846.
  64. Lee, C., Koo, D., Telidetzki, K., Buckley, H., Gagnon, H., and Zingg, D. W., “Aerodynamic shape optimization of benchmark problems using jetstream,” 53rd AIAA Aerospace Sciences Meeting, 2015, p. 0262.
  65. Poole, D. J., Allen, C. B., and Rendall, T., “Control point-based aerodynamic shape optimization applied to AIAA ADODG test cases,” 53rd AIAA Aerospace Sciences Meeting, 2015, p. 1947.
  66. Mufti, B., Khan, T., Masud, J., and Toor, Z., “Flow field analysis of a diverterless supersonic inlet using embedded les methodology,” 2019 IEEE 10th International Conference on Mechanical and Aerospace Engineering (ICMAE), IEEE, 2019, pp. 79–84.
  67. Toor, Z., Masud, J., Irfan, T., Mufti, B., and Khan, O., “Comparative Analysis of Aerodynamic Characteristics of a Transport Aircraft and its AWACS Variant,” AIAA Scitech 2020 Forum, 2020, p. 2227.
  68. Lyu, Z., Kenway, G. K. W., and Martins, J. R. R. A., “Aerodynamic Shape Optimization Investigations of the Common Research Model Wing Benchmark,” AIAA Journal, Vol. 53, No. 4, 2015, pp. 968–985. 10.2514/1.J053318, URL https://arc.aiaa.org/doi/10.2514/1.J053318.
  69. Kulfan, B. M., “Universal Parametric Geometry Representation Method,” Journal of Aircraft, Vol. 45, No. 1, 2008, pp. 142–158. 10.2514/1.29958.
  70. Masters, D. A., Poole, D. J., Taylor, N. J., Rendall, T., and Allen, C. B., “Impact of shape parameterisation on aerodynamic optimisation of benchmark problem,” 54th AIAA Aerospace Sciences Meeting, 2016, p. 1544.
  71. Hicks, R. M., and Henne, P. A., “Wing Design By Numerical Optimization,” Journal of Aircraft, Vol. 15, No. 7, 1978, pp. 407–412. 10.2514/3.58379.
  72. Masters, D. A., Taylor, N. J., Rendall, T. C., Allen, C. B., and Poole, D. J., “Geometric comparison of aerofoil shape parameterization methods,” AIAA Journal, Vol. 55, No. 5, 2017, pp. 1575–1589. 10.2514/1.J054943.
  73. Kenway, G., Kennedy, G., and Martins, J., “A CAD-Free Approach to High-Fidelity Aerostructural Optimization,” 13th AIAA/ISSMO Multidisciplinary Analysis Optimization Conference, American Institute of Aeronautics and Astronautics, Reston, Virigina, 2010, pp. 1–18. 10.2514/6.2010-9231, URL http://arc.aiaa.org/doi/10.2514/6.2010-9231.

Summary

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

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