General Multifidelity Surrogate Models: Framework and Active-Learning Strategies for Efficient Rare Event Simulation
Publication: Journal of Engineering Mechanics
Volume 149, Issue 12
Abstract
Estimating the probability of failure for complex real-world systems using high-fidelity computational models is often prohibitively expensive, especially when the probability is small. Exploiting low-fidelity models can make this process more feasible, but merging information from multiple low-fidelity and high-fidelity models poses several challenges. This paper presents a robust multifidelity surrogate modeling strategy in which the multifidelity surrogate is assembled using an active-learning strategy using an on-the-fly model adequacy assessment set within a subset simulation framework for efficient reliability analysis. The multifidelity surrogate is assembled by first applying a Gaussian process correction to each low-fidelity model and assigning a model probability based on the model’s local predictive accuracy and cost. Three strategies are proposed to fuse these individual surrogates into an overall surrogate model based on model averaging and deterministic or stochastic model selection. The strategies also dictate which model evaluations are necessary. No assumptions are made about the relationships between low-fidelity models, while the high-fidelity model is assumed to be the most accurate and most computationally expensive model. Through two analytical and two numerical case studies, including a case study evaluating the failure probability of tristructural isotropic-coated (TRISO) nuclear fuels, the algorithm is shown to be highly accurate while drastically reducing the number of high-fidelity model calls (and hence computational cost).
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
The codes used to apply LFMC on the analytical examples are available on GitHub in the following repository: https://github.com/promitchakroborty/LFMC. All other data, models, or codes that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This research is supported through the INL Laboratory Directed Research and Development (LDRD) Program under DOE Idaho Operations Office Contract DE-AC07-05ID14517. This research made use of the resources of the High-Performance Computing Center at INL, which is supported by the Office of Nuclear Energy of the US DOE and the Nuclear Science User Facilities under Contract No. DE-AC07-05ID14517. Portions of this work were carried out at the Advanced Research Computing at Hopkins (ARCH) core facility (https://www.arch.jhu.edu/), which is supported by the National Science Foundation (NSF) Grant Number OAC1920103. The authors are grateful to Professor Alex Gorodetsky for his feedback and suggestions on the proposed method.
References
Ang, G. L., A. H.-S. Ang, and W. H. Tang. 1992. “Optimal importance-sampling density estimator.” J. Eng. Mech. 118 (6): 1146–1163. https://doi.org/10.1061/(ASCE)0733-9399(1992)118:6(1146).
Au, S., C. Papadimitriou, and J. Beck. 1999. “Reliability of uncertain dynamical systems with multiple design points.” Struct. Saf. 21 (2): 113–133. https://doi.org/10.1016/S0167-4730(99)00009-0.
Au, S.-K., and J. L. Beck. 2001. “Estimation of small failure probabilities in high dimensions by subset simulation.” Probab. Eng. Mech. 16 (4): 263–277. https://doi.org/10.1016/S0266-8920(01)00019-4.
Au, S.-K., and J. L. Beck. 2003. “Important sampling in high dimensions.” Struct. Saf. 25 (2): 139–163. https://doi.org/10.1016/S0167-4730(02)00047-4.
Bichon, B. J., M. S. Eldred, L. P. Swiler, S. Mahadevan, and J. M. McFarland. 2008. “Efficient global reliability analysis for nonlinear implicit performance functions.” AIAA J. 46 (10): 2459–2468. https://doi.org/10.2514/1.34321.
Bucher, C. G. 1988. “Adaptive sampling—An iterative fast Monte Carlo procedure.” Struct. Saf. 5 (2): 119–126. https://doi.org/10.1016/0167-4730(88)90020-3.
Catanach, T. A., and J. L. Beck. 2018. “Bayesian updating and uncertainty quantification using sequential tempered MCMC with the rank-one modified metropolis algorithm.” Preprint, submitted April 23, 2018. https://arxiv.org/abs/1804.08738.
Choi, S. K., R. V. Grandhi, and R. A. Canfield. 2004. “Structural reliability under non-Gaussian stochastic behavior.” Comput. Struct. 82 (13–14): 1113–1121. https://doi.org/10.1016/j.compstruc.2004.03.015.
Der Kiureghian, A., and T. Dakessian. 1998. “Multiple design points in first and second-order reliability.” Struct. Saf. 20 (1): 37–49. https://doi.org/10.1016/S0167-4730(97)00026-X.
Dhulipala, S. L., Z. M. Prince, A. E. Slaughter, L. B. Munday, W. Jiang, B. W. Spencer, and J. D. Hales. 2022a. “Monte Carlo variance reduction in MOOSE stochastic tools module: Accelerating the failure analysis of nuclear reactor technologies.” In Proc., Int. Conf. on Physics of Reactors 2022 (PHYSOR 2022), 2470–2479. Pittsburgh: American Nuclear Society.
Dhulipala, S. L., M. D. Shields, P. Chakroborty, W. Jiang, B. W. Spencer, J. D. Hales, V. M. Labouré, Z. M. Prince, C. Bolisetti, and Y. Che. 2022b. “Reliability estimation of an advanced nuclear fuel using coupled active learning, multifidelity modeling, and subset simulation.” Reliab. Eng. Syst. Saf. 226 (Oct): 108693. https://doi.org/10.1016/j.ress.2022.108693.
Dhulipala, S. L., M. D. Shields, B. W. Spencer, C. Bolisetti, A. E. Slaughter, V. M. Labouré, and P. Chakroborty. 2022c. “Active learning with multifidelity modeling for efficient rare event simulation.” J. Comput. Phys. 468 (Nov): 111506. https://doi.org/10.1016/j.jcp.2022.111506.
Dhulipala, S. L. N., W. Jiang, B. W. Spencer, J. D. Hales, M. D. Shields, A. E. Slaughter, Z. M. Prince, V. M. Labouré, C. Bolisetti, and P. Chakroborty. 2022d. “Accelerated statistical failure analysis of multifidelity TRISO fuel models.” J. Nucl. Mater. 563 (May): 153604. https://doi.org/10.1016/j.jnucmat.2022.153604.
Ditlevsen, O., and H. O. Madsen. 1996. In Vol. 178 of Structural reliability methods. New York: Wiley.
DOE. 2019. TRISO particles: The most robust nuclear fuel on earth. Washington, DC: DOE.
Echard, B., N. Gayton, and M. Lemaire. 2011. “AK-MCS: An active learning reliability method combining kriging and Monte Carlo simulation.” Struct. Saf. 33 (2): 145–154. https://doi.org/10.1016/j.strusafe.2011.01.002.
Fishman, G. S. 1996. Monte Carlo: Concepts, algorithms, and applications. New York: Springer.
Gorodetsky, A. A., G. Geraci, M. S. Eldred, and J. D. Jakeman. 2020a. “A generalized approximate control variate framework for multifidelity uncertainty quantification.” J. Comput. Phys. 408 (May): 109257. https://doi.org/10.1016/j.jcp.2020.109257.
Gorodetsky, A. A., J. D. Jakeman, and G. Geraci. 2021. “MFNets: Data efficient all-at-once learning of multifidelity surrogates as directed networks of information sources.” Comput. Mech. 68 (May): 741–758. https://doi.org/10.1007/s00466-021-02042-0.
Gorodetsky, A. A., J. D. Jakeman, G. Geraci, and M. S. Eldred. 2020b. “MFNets: Multi-fidelity data-driven networks for Bayesian learning and prediction.” Int. J. Uncertainty Quantif. 10 (6): 595–622. https://doi.org/10.1615/Int.J.UncertaintyQuantification.2020032978.
Hales, J. D., R. L. Williamson, S. R. Novascone, D. M. Perez, B. W. Spencer, and G. Pastore. 2013. “Multidimensional multiphysics simulation of triso particle fuel.” J. Nucl. Mater. 443 (May): 531–543. https://doi.org/10.1016/j.jnucmat.2013.07.070.
Huang, X., J. Chen, and H. Zhu. 2016. “Assessing small failure probabilities by AK–SS: An active learning method combining kriging and subset simulation.” Struct. Saf. 59 (Mar): 86–95. https://doi.org/10.1016/j.strusafe.2015.12.003.
Hurtado, J. E., and D. A. Alvarez. 2001. “Neural-network-based reliability analysis: A comparative study.” Comput. Methods Appl. Mech. Eng. 191 (1): 113–132. https://doi.org/10.1016/S0045-7825(01)00248-1.
Jiang, W., J. D. Hales, B. W. Spencer, B. P. Collin, A. E. Slaughter, S. R. Novascone, A. Toptan, K. A. Gamble, and R. Gardner. 2021. “Triso particle fuel performance and failure analysis with BISON.” J. Nucl. Mater. 548 (May): 152795. https://doi.org/10.1016/j.jnucmat.2021.152795.
Jiang, W., B. W. Spencer, and J. E. Dolbow. 2020. “Ceramic nuclear fuel fracture modeling with the extended finite element method.” Eng. Fract. Mech. 223 (May): 106713. https://doi.org/10.1016/j.engfracmech.2019.106713.
Kramer, B., A. N. Marques, B. Peherstorfer, U. Villa, and K. Willcox. 2019. “Multifidelity probability estimation via fusion of estimators.” J. Comput. Phys. 392 (Sep): 385–402. https://doi.org/10.1016/j.jcp.2019.04.071.
Lelièvre, N., P. Beaurepaire, C. Mattrand, and N. Gayton. 2018. “AK-MCSi: A kriging-based method to deal with small failure probabilities and time-consuming models.” Struct. Saf. 73 (Jul): 1–11. https://doi.org/10.1016/j.strusafe.2018.01.002.
Lemaire, M. 2013. Structural reliability. New York: Wiley.
Lindsay, A., et al. 2022. “2.0-MOOSE: Enabling massively parallel multiphysics simulation.” SoftwareX 20 (Dec): 101202. https://doi.org/10.1016/j.softx.2022.101202.
Maki, J. T., D. A. Petti, D. L. Knudson, and G. K. Miller. 2007. “The challenges associated with high burnup, high temperature and accelerated irradiation for triso-coated particle fuel.” J. Nucl. Mater. 371 (1–3): 270–280. https://doi.org/10.1016/j.jnucmat.2007.05.019.
Melchers, R. 1989. “Importance sampling in structural systems.” Struct. Saf. 6 (1): 3–10. https://doi.org/10.1016/0167-4730(89)90003-9.
Mishra, S., O. A. Vanli, B. P. Alduse, and S. Jung. 2017. “Hurricane loss estimation in wood-frame buildings using Bayesian model updating: Assessing uncertainty in fragility and reliability analyses.” Eng. Struct. 135 (Mar): 81–94. https://doi.org/10.1016/j.engstruct.2016.12.063.
Morio, J., and M. Balesdent. 2015. Estimation of rare event probabilities in complex aerospace and other systems: A practical approach. Sawston, UK: Woodhead.
Papadrakakis, M., V. Papadopoulos, and N. D. Lagaros. 1996. “Structural reliability analysis of elastic-plastic structures using neural networks and Monte Carlo simulation.” Comput. Methods Appl. Mech. Eng. 136 (1): 145–163. https://doi.org/10.1016/0045-7825(96)01011-0.
Papaioannou, I., W. Betz, L. Zwirglmaier, and D. Straub. 2015. “MCMC algorithms for subset simulation.” Probab. Eng. Mech. 41 (Jul): 89–103. https://doi.org/10.1016/j.probengmech.2015.06.006.
Peherstorfer, B., T. Cui, Y. Marzouk, and K. Willcox. 2016. “Multifidelity importance sampling.” Comput. Methods Appl. Mech. Eng. 300 (Mar): 490–509. https://doi.org/10.1016/j.cma.2015.12.002.
Peherstorfer, B., K. Willcox, and M. Gunzburger. 2018. “Survey of multifidelity methods in uncertainty propagation, inference, and optimization.” SIAM Rev. 60 (3): 550–591. https://doi.org/10.1137/16M1082469.
Pham, T., and A. A. Gorodetsky. 2021. “Ensemble approximate control variate estimators: Applications to multi-fidelity importance sampling.” SIAM/ASA J. Uncertainty Quantif. 10 (3): 1250–1292. https://doi.org/10.1137/21M1390426.
Rasmussen, C. E., and C. K. I. Williams. 2005. Gaussian processes for machine learning. Cambridge, MA: MIT Press.
Razaaly, N., and P. Congedo. 2020. “Extension of AK-MCS for the efficient computation of very small failure probabilities.” Reliab. Eng. Syst. Saf. 203 (Nov): 107084. https://doi.org/10.1016/j.ress.2020.107084.
Rubinstein, R. Y. 1981. Simulation and the Monte Carlo method. New York: Wiley.
Schöbi, R., and B. Sudret. 2014. “Combining polynomial chaos expansions and kriging for solving structural reliability problems.” In Proc., 7th Computational Stochastic Mechanics Conf. Zürich, Switzerland: ETH Zürich.
Schuëller, G. I., H. J. Pradlwarter, and P. S. Koutsourelakis. 2004. “A critical appraisal of reliability estimation procedures for high dimensions.” Probab. Eng. Mech. 19 (4): 463–474. https://doi.org/10.1016/j.probengmech.2004.05.004.
Schuëller, G. I., H. J. Pradlwarter, and M. D. Pandey. 1993. “Methods for reliability assessment of nonlinear systems under stochastic dynamic loading—A review.” In Vol. 93 of Proc., EURODYN, 751–759. Porto, Portugal: European Association for Structural Dynamics.
Shields, M. D., D. G. Giovanis, and V. S. Sundar. 2021. “Subset simulation for problems with strongly non-Gaussian, highly anisotropic, and degenerate distributions.” Comput. Struct. 245 (Mar): 106431. https://doi.org/10.1016/j.compstruc.2020.106431.
Sundar, V. S., and M. D. Shields. 2019. “Reliability analysis using adaptive kriging surrogates with multimodel inference.” ASCE-ASME J. Risk Uncertainty Eng. Syst. Part A: Civ. Eng. 5 (2): 04019004. https://doi.org/10.1061/AJRUA6.0001005.
Tsagris, M., C. Beneki, and H. Hassani. 2014. “On the folded normal distribution.” Mathematics 2 (1): 12–28. https://doi.org/10.3390/math2010012.
Williamson, R. L., et al. 2021. “Bison: A flexible code for advanced simulation of the performance of multiple nuclear fuel forms.” Nucl. Technol. 207 (7): 954–980. https://doi.org/10.1080/00295450.2020.1836940.
Williamson, R. L., J. D. Hales, S. R. Novascone, M. R. Tonks, D. R. Gaston, C. J. Permann, D. Andrs, and R. C. Martineau. 2012. “Multidimensional multiphysics simulation of nuclear fuel behavior.” J. Nucl. Mater. 423 (1–3): 149–163. https://doi.org/10.1016/j.jnucmat.2012.01.012.
Xiao, S., S. Reuschen, G. Köse, S. Oladyshkin, and W. Nowak. 2019. “Estimation of small failure probabilities based on thermodynamic integration and parallel tempering.” Mech. Syst. Signal Process. 133 (Nov): 106248. https://doi.org/10.1016/j.ymssp.2019.106248.
Xu, C., W. Chen, J. Ma, Y. Shi, and S. Lu. 2020. “AK-MSS: An adaptation of the AK-MCS method for small failure probabilities.” Struct. Saf. 86 (Sep):101971. https://doi.org/10.1016/j.strusafe.2020.101971.
Yang, X., D. Barajas-Solano, G. Tartakovsky, and A. M. Tartakovsky. 2019. “Physics-informed cokriging: A Gaussian-process-regression-based multifidelity method for data-model convergence.” J. Comput. Phys. 395 (Oct): 410–431. https://doi.org/10.1016/j.jcp.2019.06.041.
Yi, J., F. Wu, Q. Zhou, Y. Cheng, H. Ling, and J. Liu. 2021. “An active-learning method based on multi-fidelity kriging model for structural reliability analysis.” Struct. Multidiscip. Optim. 63 (Jan): 173–195. https://doi.org/10.1007/s00158-020-02678-1.
Zhang, C., C. Song, and A. Shafieezadeh. 2022. “Adaptive reliability analysis for multi-fidelity models using a collective learning strategy.” Struct. Saf. 94 (Jan): 102141. https://doi.org/10.1016/j.strusafe.2021.102141.
Zhang, J., J. Man, G. Lin, L. Wu, and L. Zeng. 2018. “Inverse modeling of hydrologic systems with adaptive multifidelity Markov chain Monte Carlo simulations.” Water Resour. Res. 54 (7): 4867–4886. https://doi.org/10.1029/2018WR022658.
Zhang, X., M. Xiao, and L. Gao. 2019. “An active learning reliability method combining kriging constructed with exploration and exploitation of failure region and subset simulation.” Reliab. Eng. Syst. Saf. 188 (Aug): 90–102. https://doi.org/10.1016/j.ress.2019.03.002.
Zio, E., and R. B. Duffey. 2021. “The risk of the electrical power grid due to natural hazards and recovery challenge following disasters and record floods: What next?” In Climate change and extreme events. Amsterdam, Netherlands: Elsevier.
Information & Authors
Information
Published In
Journal of Engineering Mechanics
Volume 149 • Issue 12 • December 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Dec 7, 2022
Accepted: Jul 10, 2023
Published online: Sep 22, 2023
Published in print: Dec 1, 2023
Discussion open until: Feb 22, 2024
ASCE Technical Topics:
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.