Papers
Topics
Authors
Recent
Search
2000 character limit reached

Two-Stage Surrogate Modeling for Data-Driven Design Optimization with Application to Composite Microstructure Generation

Published 4 Jan 2024 in cs.LG and cs.CE | (2401.02008v1)

Abstract: This paper introduces a novel two-stage machine learning-based surrogate modeling framework to address inverse problems in scientific and engineering fields. In the first stage of the proposed framework, a machine learning model termed the "learner" identifies a limited set of candidates within the input design space whose predicted outputs closely align with desired outcomes. Subsequently, in the second stage, a separate surrogate model, functioning as an "evaluator," is employed to assess the reduced candidate space generated in the first stage. This evaluation process eliminates inaccurate and uncertain solutions, guided by a user-defined coverage level. The framework's distinctive contribution is the integration of conformal inference, providing a versatile and efficient approach that can be widely applicable. To demonstrate the effectiveness of the proposed framework compared to conventional single-stage inverse problems, we conduct several benchmark tests and investigate an engineering application focused on the micromechanical modeling of fiber-reinforced composites. The results affirm the superiority of our proposed framework, as it consistently produces more reliable solutions. Therefore, the introduced framework offers a unique perspective on fostering interactions between machine learning-based surrogate models in real-world applications.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (70)
  1. M. Kalsi, K. Hacker, and K. Lewis, “A comprehensive robust design approach for decision trade-offs in complex systems design,” in International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, vol. 19715, pp. 1343–1354, 1999.
  2. G. Padmanabha and N. Zabaras, “Solving inverse problems using conditional invertible neural networks,” Journal of Computational Physics, vol. 433, p. 110194, 2021.
  3. A. Gallet, S. Rigby, T. Tallman, X. Kong, I. Hajirasouliha, A. Liew, D. Liu, L. Chen, A. Hauptmann, and D. Smyl, “Structural engineering from an inverse problems perspective,” Proceedings of the Royal Society A, vol. 478, no. 2257, p. 20210526, 2022.
  4. J. Liu, J. Low, Q. Han, M. Lim, D. Lu, C. Yeow, and Z. Liu, “Simulation data driven design optimization for reconfigurable soft gripper system,” IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 5803–5810, 2022.
  5. M. Hariri-Ardebili and F. Pourkamali-Anaraki, “An automated machine learning engine with inverse analysis for seismic design of dams,” Water, vol. 14, no. 23, p. 3898, 2022.
  6. D. Morgan and R. Jacobs, “Opportunities and challenges for machine learning in materials science,” Annual Review of Materials Research, vol. 50, pp. 71–103, 2020.
  7. L. Chen, G. Pilania, R. Batra, T. Huan, C. Kim, C. Kuenneth, and R. Ramprasad, “Polymer informatics: Current status and critical next steps,” Materials Science and Engineering: R: Reports, vol. 144, p. 100595, 2021.
  8. A. Sharma, T. Mukhopadhyay, S. Rangappa, S. Siengchin, and V. Kushvaha, “Advances in computational intelligence of polymer composite materials: machine learning assisted modeling, analysis and design,” Archives of Computational Methods in Engineering, vol. 29, no. 5, pp. 3341–3385, 2022.
  9. J. Noh, G. Gu, S. Kim, and Y. Jung, “Machine-enabled inverse design of inorganic solid materials: promises and challenges,” Chemical Science, vol. 11, no. 19, pp. 4871–4881, 2020.
  10. S. Kim and F. Boukouvala, “Machine learning-based surrogate modeling for data-driven optimization: a comparison of subset selection for regression techniques,” Optimization Letters, vol. 14, no. 4, pp. 989–1010, 2020.
  11. F. Pourkamali-Anaraki and M. Hariri-Ardebili, “Neural networks and imbalanced learning for data-driven scientific computing with uncertainties,” IEEE Access, vol. 9, pp. 15334–15350, 2021.
  12. R. Campet, P. Roy, B. Cuenot, E. Riber, and J. Jouhaud, “Design optimization of an heat exchanger using gaussian process,” International Journal of Heat and Mass Transfer, vol. 150, p. 119264, 2020.
  13. M. Hariri-Ardebili and F. Pourkamali-Anaraki, “Matrix completion for cost reduction in finite element simulations under hybrid uncertainties,” Applied Mathematical Modelling, vol. 69, pp. 164–180, 2019.
  14. B. Bischl, M. Binder, M. Lang, T. Pielok, J. Richter, S. Coors, J. Thomas, T. Ullmann, M. Becker, and A. Boulesteix, “Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges,” Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, p. e1484, 2021.
  15. M. Hariri-Ardebili and F. Pourkamali-Anaraki, “Support vector machine based reliability analysis of concrete dams,” Soil Dynamics and Earthquake Engineering, vol. 104, pp. 276–295, 2018.
  16. A. Paleyes, R. Urma, and N. Lawrence, “Challenges in deploying machine learning: a survey of case studies,” ACM Computing Surveys, vol. 55, no. 6, pp. 1–29, 2022.
  17. F. Pourkamali-Anaraki, T. Nasrin, R. Jensen, A. Peterson, and C. Hansen, “Evaluation of classification models in limited data scenarios with application to additive manufacturing,” Engineering Applications of Artificial Intelligence, vol. 126, p. 106983, 2023.
  18. V. Singh and K. Willcox, “Decision-making under uncertainty for a digital thread-enabled design process,” Journal of Mechanical Design, vol. 143, no. 9, p. 091707, 2021.
  19. F. Pourkamali-Anaraki and S. Becker, “A randomized approach to efficient kernel clustering,” in 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 207–211, 2016.
  20. F. Pourkamali-Anaraki, M. Hariri-Ardebili, and L. Morawiec, “Kernel ridge regression using importance sampling with application to seismic response prediction,” in 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 511–518, 2020.
  21. B. Einbinder, Y. Romano, M. Sesia, and Y. Zhou, “Training uncertainty-aware classifiers with conformalized deep learning,” Advances in Neural Information Processing Systems, vol. 35, pp. 22380–22395, 2022.
  22. J. Lei, M. G’Sell, A. Rinaldo, R. Tibshirani, and L. Wasserman, “Distribution-free predictive inference for regression,” Journal of the American Statistical Association, vol. 113, no. 523, pp. 1094–1111, 2018.
  23. A. Angelopoulos and S. Bates, “Conformal prediction: A gentle introduction,” Foundations and Trends in Machine Learning, vol. 16, no. 4, pp. 494–591, 2023.
  24. M. Fontana, G. Zeni, and S. Vantini, “Conformal prediction: a unified review of theory and new challenges,” Bernoulli, vol. 29, no. 1, pp. 1–23, 2023.
  25. E. Schulz, M. Speekenbrink, and A. Krause, “A tutorial on gaussian process regression: Modelling, exploring, and exploiting functions,” Journal of Mathematical Psychology, vol. 85, pp. 1–16, 2018.
  26. P. Izmailov, S. Vikram, M. Hoffman, and A. Wilson, “What are Bayesian neural network posteriors really like?,” in International Conference on Machine Learning, pp. 4629–4640, 2021.
  27. M. Guo, S. McQuarrie, and K. Willcox, “Bayesian operator inference for data-driven reduced-order modeling,” Computer Methods in Applied Mechanics and Engineering, vol. 402, p. 115336, 2022.
  28. M. El Sayed and M. Abo-Sinna, “A novel approach for fully intuitionistic fuzzy multi-objective fractional transportation problem,” Alexandria Engineering Journal, vol. 60, no. 1, pp. 1447–1463, 2021.
  29. M. El Sayed, F. Farahat, and M. Elsisy, “A novel interactive approach for solving uncertain bi-level multi-objective supply chain model,” Computers & Industrial Engineering, vol. 169, p. 108225, 2022.
  30. Z. Zhuang, H. Tao, Y. Chen, V. Stojanovic, and W. Paszke, “An optimal iterative learning control approach for linear systems with nonuniform trial lengths under input constraints,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 53, no. 6, pp. 3461–3473, 2023.
  31. V. Djordjevic, H. Tao, X. Song, S. He, W. Gao, and V. Stojanović, “Data-driven control of hydraulic servo actuator: An event-triggered adaptive dynamic programming approach,” Mathematical biosciences and engineering: MBE, 2023.
  32. P. Agrawal, H. Abutarboush, T. Ganesh, and A. Mohamed, “Metaheuristic algorithms on feature selection: A survey of one decade of research (2009-2019),” Ieee Access, vol. 9, pp. 26766–26791, 2021.
  33. S. Zhao, T. Zhang, S. Ma, and M. Chen, “Dandelion optimizer: A nature-inspired metaheuristic algorithm for engineering applications,” Engineering Applications of Artificial Intelligence, vol. 114, p. 105075, 2022.
  34. F. Gholian-Jouybari, O. Hashemi-Amiri, B. Mosallanezhad, and M. Hajiaghaei-Keshteli, “Metaheuristic algorithms for a sustainable agri-food supply chain considering marketing practices under uncertainty,” Expert Systems with Applications, vol. 213, p. 118880, 2023.
  35. M. Hariri-Ardebili and F. Pourkamali-Anaraki, “Structural uncertainty quantification with partial information,” Expert Systems with Applications, vol. 198, p. 116736, 2022.
  36. L. Cai, L. Ren, Y. Wang, W. Xie, G. Zhu, and H. Gao, “Surrogate models based on machine learning methods for parameter estimation of left ventricular myocardium,” Royal Society open science, vol. 8, no. 1, p. 201121, 2021.
  37. B. Lei, T. Kirk, A. Bhattacharya, D. Pati, X. Qian, R. Arroyave, and B. Mallick, “Bayesian optimization with adaptive surrogate models for automated experimental design,” Npj Computational Materials, vol. 7, no. 1, p. 194, 2021.
  38. J. Stuckner, M. Piekenbrock, S. Arnold, and T. Ricks, “Optimal experimental design with fast neural network surrogate models,” Computational Materials Science, vol. 200, p. 110747, 2021.
  39. B. Hearley, S. Arnold, and J. Stuckner, “A robust schema for machine learning data and models within the Granta MI information management system,” in AIAA SCITECH 2023 Forum, p. 1266, 2023.
  40. T. Nasrin, M. Pourali, F. Pourkamali-Anaraki, and A. Peterson, “Active learning for prediction of tensile properties for material extrusion additive manufacturing,” Scientific Reports, vol. 13, no. 1, p. 11460, 2023.
  41. K. Murphy, Probabilistic machine learning: an introduction. MIT press, 2022.
  42. O. Ghattas and K. Willcox, “Learning physics-based models from data: perspectives from inverse problems and model reduction,” Acta Numerica, vol. 30, pp. 445–554, 2021.
  43. S. Puel, E. Khattatov, U. Villa, D. Liu, O. Ghattas, and T. Becker, “A mixed, unified forward/inverse framework for earthquake problems: fault implementation and coseismic slip estimate,” Geophysical Journal International, vol. 230, no. 2, pp. 733–758, 2022.
  44. A. Jagtap, Z. Mao, N. Adams, and G. Karniadakis, “Physics-informed neural networks for inverse problems in supersonic flows,” Journal of Computational Physics, vol. 466, p. 111402, 2022.
  45. S. Weissmann, N. Chada, C. Schillings, and X. Tong, “Adaptive tikhonov strategies for stochastic ensemble kalman inversion,” Inverse Problems, vol. 38, no. 4, p. 045009, 2022.
  46. B. Bischl, M. Binder, M. Lang, T. Pielok, J. Richter, S. Coors, J. Thomas, T. Ullmann, M. Becker, A. Boulesteix, D. Deng, and M. Lindauer, “Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges,” Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, vol. 13, no. 2, p. e1484, 2023.
  47. R. Tibshirani, R. Foygel Barber, E. Candes, and A. Ramdas, “Conformal prediction under covariate shift,” Advances in neural information processing systems, vol. 32, 2019.
  48. S. Bates, T. Hastie, and R. Tibshirani, “Cross-validation: what does it estimate and how well does it do it?,” Journal of the American Statistical Association, pp. 1–12, 2023.
  49. R. Barber, E. Candes, A. Ramdas, and R. Tibshirani, “Conformal prediction beyond exchangeability,” The Annals of Statistics, vol. 51, no. 2, pp. 816–845, 2023.
  50. D. Allaire and K. Willcox, “A variance-based sensitivity index function for factor prioritization,” Reliability Engineering & System Safety, vol. 107, pp. 107–114, 2012.
  51. T. Nasrin, F. Pourkamali-Anaraki, and A. Peterson, “Application of machine learning in polymer additive manufacturing: A review,” Journal of Polymer Science, 2023.
  52. D. Sodhani, S. Reese, R. Moreira, S. Jochenhovel, P. Mela, and S. Stapleton, “Multi-scale modelling of textile reinforced artificial tubular aortic heart valves,” Meccanica, vol. 52, pp. 677–693, 2017.
  53. D. Sodhani, S. Reese, S. Jochenhovel, P. Mela, and S. Stapleton, “Multi-scale modelling and simulation of a highly deformable embedded biomedical textile mesh composite,” Composites Part B: Engineering, vol. 143, pp. 113–131, 2018.
  54. E. Pineda, B. Bednarcyk, T. Ricks, B. Farrokh, and W. Jackson, “Multiscale failure analysis of a 3d woven composite containing manufacturing induced voids and disbonds,” Composites Part A: Applied Science and Manufacturing, vol. 143, pp. 113–131, 2018.
  55. Springer, 2008.
  56. Y. Qiao, Q. Zhang, T. Nakagawa, and M. Salviato, “A size effect study on the splitting crack initiation and propagation in off-axis layers of composite laminates,” in The American Society for Composites (ASC) 36th Annual Technical Conference (Virtual), 2021.
  57. H. Ghayoor, S. Hoa, and C. Marsden, “A micromechanical study of stress concentrations in composites,” Composites Part B: Engineering, vol. 132, pp. 115–124, 2018.
  58. L. Mishnaevsky Jr and G. Dai, “Hybrid carbon/glass fiber composites: Micromechanical analysis of structure–damage resistance relationships,” Computational Materials Science, vol. 81, pp. 630–640, 2014.
  59. H. Li, B. Zhang, and G. Bai, “Effects of constructing different unit cells on predicting composite viscoelastic properties,” Composite Structures, vol. 125, pp. 459–466, 2015.
  60. V. Bulsara, R. Talreja, and J. Qu, “Damage initiation under transverse loading of unidirectional composites with arbitrarily distributed fibers,” Composites science and technology, vol. 59, no. 5, pp. 673–682, 1999.
  61. S. Elnekhaily and R. Talreja, “Damage initiation in unidirectional fiber composites with different degrees of nonuniform fiber distribution,” Composites Science and Technology, vol. 155, pp. 22–32, 2018.
  62. A. Sudhir and R. Talreja, “Simulation of manufacturing induced fiber clustering and matrix voids and their effect on transverse crack formation in unidirectional composites,” Composites Part A: Applied Science and Manufacturing, vol. 127, p. 105620, 2019.
  63. B. Ripley, “Modelling spatial patterns,” Journal of the Royal Statistical Society: Series B (Methodological), vol. 39, no. 2, pp. 172–192, 1977.
  64. J. Feder, “Random sequential adsorption,” Journal of Theoretical Biology, vol. 87, no. 2, pp. 237–254, 1980.
  65. E. Hinrichsen, J. Feder, and T. Jøssang, “Geometry of random sequential adsorption,” Journal of statistical physics, vol. 44, pp. 793–827, 1986.
  66. V. Buryachenko, N. Pagano, R. Kim, and J. Spowart, “Quantitative description and numerical simulation of random microstructures of composites and their effective elastic moduli,” International journal of solids and structures, vol. 40, no. 1, pp. 47–72, 2003.
  67. L. Yang, Y. Yan, Z. Ran, and Y. Liu, “A new method for generating random fibre distributions for fibre reinforced composites,” Composites Science and Technology, vol. 76, pp. 14–20, 2013.
  68. S. Park, J. Lim, M. Seong, and D. Sohn, “Efficient generator of random fiber distribution with diverse volume fractions by random fiber removal,” Composites Part B: Engineering, vol. 167, pp. 302–316, 2019.
  69. J. Husseini, E. Pineda, and S. Stapleton, “Generation of artificial 2-D fiber reinforced composite microstructures with statistically equivalent features,” Composites Part A: Applied Science and Manufacturing, vol. 164, p. 107260, 2023.
  70. J. Husseini, F. Pourkamali-Anaraki, P. Hajibabaee, and S. Stapleton, “Generation of 2-D fiber reinforced composite microstructures with statistically equivalent features using machine learning and adaptive data generation,” in AIAA SCITECH 2023 Forum, p. 1267, 2023.

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

Collections

Sign up for free to add this paper to one or more collections.

Sign Up