Abstract
The efficient propagation of imprecise probabilities through expensive simulators has emerged to be one of the great challenges for mixed uncertainty quantification in computational mechanics. An active learning method, named Collaborative and Adaptive Bayesian Optimization (CABO), is developed for tackling this challenge by combining Bayesian Probabilistic Optimization and Bayesian Probabilistic Integration. Two learning functions are introduced as engines for CABO, where one is introduced for realizing the adaptive optimization search in the epistemic uncertainty space, and the other one is developed for adaptive integration in the aleatory uncertainty space. These two engines work in a collaborative way to create optimal design points adaptively in the joint uncertainty space, by which a Gaussian process regression model is trained and updated to approach the bounds of model response moments with pre-specified error tolerances. The effectiveness of CABO is demonstrated using a numerical example and two engineering benchmarks.
Similar content being viewed by others
References
Zein S, Laurent A, Dumas D (2019) Simulation of a Gaussian random field over a 3D surface for the uncertainty quantification in the composite structures. Comput Mech 63(6):1083
Ding C, Deokar RR, Cui X, Li G, Cai Y, Tamma KK (2019) Proper orthogonal decomposition and Monte Carlo based isogeometric stochastic method for material, geometric and force multi-dimensional uncertainties. Comput Mech 63(3):521
Der Kiureghian A, Ditlevsen O (2009) Aleatory or epistemic? Does it matter? Struct Saf 31(2):105
Beer M, Ferson S, Kreinovich V (2013) Imprecise probabilities in engineering analyses. Mech Syst Signal Process 37(1–2):4
Faes M, Moens D (2019) Recent trends in the modeling and quantification of non-probabilistic uncertainty. Arch Comput Methods Eng 27:1–39
Wei P, Song J, Bi S, Broggi M, Beer M, Lu Z, Yue Z (2019) Non-intrusive stochastic analysis with parameterized imprecise probability models: I. Performance estimation. Mech Syst Signal Process 124:349
Behmanesh I, Moaveni B, Lombaert G, Papadimitriou C (2015) Hierarchical Bayesian model updating for structural identification. Mech Syst Signal Process 64:360
Hu Z, Mahadevan S, Ao D (2018) Uncertainty aggregation and reduction in structure-material performance prediction. Comput Mech 61(1):237
Wei P, Lu Z, Song J (2015) Variable importance analysis: a comprehensive review. Reliab Eng Syst Saf 142:399
Gao W, Wu D, Song C, Tin-Loi F, Li X (2011) Hybrid probabilistic interval analysis of bar structures with uncertainty using a mixed perturbation Monte-Carlo method. Finite Elem Anal Des 47(7):643
Hurtado JE, Alvarez DA (2012) The encounter of interval and probabilistic approaches to structural reliability at the design point. Comput Methods Appl Mech Eng 225:74
Kang R, Zhang Q, Zeng Z, Zio E, Li X (2016) Measuring reliability under epistemic uncertainty: Review on non-probabilistic reliability metrics. Chin J Aeronaut 29(3):571
Hurtado JE (2013) Assessment of reliability intervals under input distributions with uncertain parameters. Probab Eng Mech 32:80
Crespo LG, Kenny SP, Giesy DP (2014) The NASA Langley multidisciplinary uncertainty quantification challenge. In: 16th AIAA non-deterministic approaches conference, p 1347
Crespo LG, Kenny SP, Giesy DP (2013) Reliability analysis of polynomial systems subject to p-box uncertainties. Mech Syst Signal Process 37(1–2):121
Agarwal H, Renaud JE, Preston EL, Padmanabhan D (2004) Uncertainty quantification using evidence theory in multidisciplinary design optimization. Reliab Eng Syst Saf 85(1–3):281
Stein M, Beer M, Kreinovich V (2013) Bayesian approach for inconsistent information. Inf Sci 245:96
Sankararaman S, Mahadevan S (2013) Distribution type uncertainty due to sparse and imprecise data. Mech Syst Signal Process 37(1–2):182
Helton JC, Johnson JD, Oberkampf WL, Sallaberry CJ (2010) Representation of analysis results involving aleatory and epistemic uncertainty. Int J Gen Syst 39(6):605
Papaioannou I, Daub M, Drieschner M, Duddeck F, Ehre M, Eichner L, Eigel M, Götz M, Graf W, Grasedyck L et al (2019) Assessment and design of an engineering structure with polymorphic uncertainty quantification. GAMM-Mitteilungen 42(2):e201900009
de Angelis M, Patelli E, Beer M (2015) Advanced line sampling for efficient robust reliability analysis. Struct Saf 52:170
Pedroni N, Zio E (2015) Hybrid uncertainty and sensitivity analysis of the model of a twin-jet aircraft. J Aerosp Inf Syst 12(1):73
Zhang H, Mullen RL, Muhanna RL (2010) Interval Monte Carlo methods for structural reliability. Struct Saf 32(3):183
Zhang H, Dai H, Beer M, Wang W (2013) Structural reliability analysis on the basis of small samples: an interval quasi-Monte Carlo method. Mech Syst Signal Process 37(1–2):137
Alvarez DA, Uribe F, Hurtado JE (2018) Estimation of the lower and upper bounds on the probability of failure using subset simulation and random set theory. Mech Syst Signal Process 100:782
Gao W, Wu D, Gao K, Chen X, Tin-Loi F (2018) Structural reliability analysis with imprecise random and interval fields. Appl Math Model 55:49
Patelli E, Alvarez DA, Broggi M, Angelis Md (2015) Uncertainty management in multidisciplinary design of critical safety systems. J Aerosp Inf Syst 12(1):140
Schöbi R, Sudret B (2017) Structural reliability analysis for p-boxes using multi-level meta-models. Probab Eng Mech 48:27
Schöbi R, Sudret B (2017) Uncertainty propagation of p-boxes using sparse polynomial chaos expansions. J Comput Phys 339:307
Sofi A, Muscolino G, Giunta F (2020) Propagation of uncertain structural properties described by imprecise Probability Density Functions via response surface method. Probab Eng Mech 60:103020
Yang X, Liu Y, Zhang Y, Yue Z (2015) Hybrid reliability analysis with both random and probability-box variables. Acta Mech 226(5):1341
Wei P, Lu Z, Song J (2014) Extended Monte Carlo simulation for parametric global sensitivity analysis and optimization. AIAA J 52(4):867
Zhang J, Shields MD (2018) On the quantification and efficient propagation of imprecise probabilities resulting from small datasets. Mech Syst Signal Process 98:465
Faes MG, Valdebenito MA, Moens D, Beer M (2020) Bounding the first excursion probability of linear structures subjected to imprecise stochastic loading. Comput Struct 239:106320
Song J, Wei P, Valdebenito M, Bi S, Broggi M, Beer M, Lei Z (2019) Generalization of non-intrusive imprecise stochastic simulation for mixed uncertain variables. Mech Syst Signal Process 134:106316
Wei P, Song J, Bi S, Broggi M, Beer M, Lu Z, Yue Z (2019) Non-intrusive stochastic analysis with parameterized imprecise probability models: II. Reliability and rare events analysis. Mech Syst Signal Process 126:227
Song J, Valdebenito M, Wei P, Beer M, Lu Z (2020) Non-intrusive imprecise stochastic simulation by line sampling. Struct Saf 84:101936
Song J, Wei P, Valdebenito M, Beer M (2020) Adaptive reliability analysis for rare events evaluation with global imprecise line sampling. Comput Methods Appl Mech Eng 372:113344113344
Cockayne J, Oates CJ, Sullivan TJ, Girolami M (2019) Bayesian probabilistic numerical methods. SIAM Rev 61(4):756
Hennig P, Schuler CJ (2012) Entropy search for information-efficient global optimization. J Mach Learn Res 13(1):1809
Briol FX, Oates CJ, Girolami M, Osborne MA, Sejdinovic D et al (2019) Probabilistic integration: a role in statistical computation? Stat Sci 34(1):1
Wei P, Zhang X, Beer M (2020) Adaptive experiment design for probabilistic integration. Comput Methods Appl Mech Eng 365:113035
Chkrebtii OA, Campbell DA, Calderhead B, Girolami MA et al (2016) Bayesian solution uncertainty quantification for differential equations. Bayesian Anal 11(4):1239
Wei P, Liu F, Valdebenito M, Beer M (2021) Bayesian probabilistic propagation of imprecise probabilities with large epistemic uncertainty. Mech Syst Signal Process 149:107219
Lebrun R, Dutfoy A (2009) Do Rosenblatt and Nataf isoprobabilistic transformations really differ? Probab Eng Mech 24(4):577
Rasmussen CE, Williams C (2006) Gaussian processes for machine learning, vol 39. MIT Press, p 40
Schölkopf B, Smola AJ, Bach F, et al (2002) Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT Press
Duvenaud D (2014) Automatic model construction with Gaussian processes
Rasmussen CE, Ghahramani Z (2003) Bayesian Monte Carlo. In: Advances in neural information processing systems, vol 15, p 505
Huang D, Allen TT, Notz WI, Zeng N (2006) Global optimization of stochastic black-box systems via sequential kriging meta-models. J Glob Optim 34(3):441
Williams BJ, Santner TJ, Notz WI (2000) Sequential design of computer experiments to minimize integrated response functions. Stat Sin 10:1133–1152
Shields MD, Zhang J (2016) The generalization of Latin hypercube sampling. Reliab Eng Syst Saf 148:96
Tripathy R, Bilionis I, Gonzalez M (2016) Gaussian processes with built-in dimensionality reduction: applications to high-dimensional uncertainty propagation. J Comput Phys 321:191
Acknowledgements
This work is supported by the National Natural Science Foundation of China (NSFC 51905430) and the grant number of the mobility programme 2020 of Sino-German Center is M-0175. The first author is also supported by the Alexander von Humboldt Foundation of Germany and the Top International University Visiting Program for Outstanding Young Scholars of Northwestern Polytechnical University. The third author extends his appreciation to the Institute for Risk and Reliability, Leibniz University, and the Humboldt award from the Alexander von Humboldt Foundation for providing the support to complete this paper. The authors would also like to thank Assist. Prof. Dr. Jingwen Song for the extensive and helpful discussions.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wei, P., Hong, F., Phoon, KK. et al. Bounds optimization of model response moments: a twin-engine Bayesian active learning method. Comput Mech 67, 1273–1292 (2021). https://doi.org/10.1007/s00466-021-01977-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00466-021-01977-8