Abstract
In the design of real-world complex engineering systems and infrastructure, one typically deals with scarce data. When only scarce data are available, convexity approaches are widely used to construct the uncertainty model in terms of bounds. Convex models estimate the uncertainty bounds using different bounding geometries that seek minimum volume with the available points. Chebyshev inequality in conjunction with geometries such as convex hull allows accounting for unobserved future data points by inflating the initially constructed geometry. Since the Chebyshev inequality is independent of underlying distribution, the inflated convex geometry is often highly conservative. To address the conservativeness, we propose constructing a convex hull with a modified inflation coefficient that uses information on input dimension and spread of data. Since conventional metrics for spread of data such as kurtosis is volatile when sample is scarce, we use L-moments which are known to be robust to sample size. The initial convex hull built using samples from a distribution characterized by L-kurtosis, is inflated incrementally until allowable number of points corresponding to target probability are violated. The corresponding inflation coefficient is considered the modified coefficient. This exercise is repeated for different L-kurtosis and dimensions, and the modified inflation coefficient are obtained for different target probability as well to construct an empirical relationship between L-kurtosis, number of dimensions, and modified inflation coefficient. The proposed approach is demonstrated on three design examples, and the results reveal that the design from the proposed approach is less conservative compared to the classical approach while solving the probabilistic formulation deterministically with scarce samples. The performance also indicates that the proposed approach has good generalization and prediction capability.
Similar content being viewed by others
References
Ayyasamy S, Ramu P, Elishakoff I (2021) Chebyshev inequality-based inflated convex hull for uncertainty quantification and optimization with scarce samples. Struct Multidisc Optim 64(4):2267–2285
Barber CB, Dobkin DP, Huhdanpaa H (1996) The quickhull algorithm for convex hulls. ACM Trans Math Softw (TOMS) 22(4):469–483
Ben-Haim Y (1994) A non-probabilistic concept of reliability. Struct Saf 14(4):227–245
Ben-Haim Y, Elishakoff I (2013) Convex models of uncertainty in applied mechanics. Elsevier, New York
Cao L, Liu J, Xie L, Jiang C, Bi R (2021) Non-probabilistic polygonal convex set model for structural uncertainty quantification. Appl Math Model 89:504–518
Chan TM (1996) Optimal output-sensitive convex hull algorithms in two and three dimensions. Discret Comput Geom 16(4):361–368
Chen X (2007) A new generalization of Chebyshev inequality for random vectors. arXiv:0707.0805
Cho H, Choi KK, Gaul NJ, Lee I, Lamb D, Gorsich D (2016) Conservative reliability-based design optimization method with insufficient input data. Struct Multidisc Optim 54(6):1609–1630
Dempster AP (2008) Upper and lower probabilities induced by a multivalued mapping. In: Classic works of the Dempster-Shafer theory of belief functions. Springer, Berlin, pp 57-72
Elishakoff I, Elettro F (2014) Interval, ellipsoidal, and super-ellipsoidal calculi for experimental and theoretical treatment of uncertainty: which one ought to be preferred? Int J Solids Struct 51(7–8):1576–1586
Elishakoff I, Sarlin N (2016) Uncertainty quantification based on pillars of experiment, theory, and computation. Part I: data analysis. Mech Syst Signal Process 74:29–53
Elishakoff I, Fang T, Sarlin N, Jiang C (2021) Uncertainty quantification and propagation based on hybrid experimental, theoretical, and computational treatment. Mech Syst Signal Process 147:107058
Faes M, Moens D (2020) Recent trends in the modeling and quantification of non-probabilistic uncertainty. Arch Comput Methods Eng 27(3):633–671
Graham RL (1972) An efficient algorithm for determining the convex hull of a finite planar set. Info Pro Lett 1:132–133
Hosking JR (1990) L-moments: Analysis and estimation of distributions using linear combinations of order statistics. J R Stat Soc 52(1):105–124
Jarvis RA (1973) On the identification of the convex hull of a finite set of points in the plane. Inf Process Lett 2(1):18–21
Jayaraman D, Ramu P (2021) L-moments-based uncertainty quantification for scarce samples including extremes. Struct Multidisc Optim 64(2):505–539
Jayaraman D, Ramu P, Suresh SK, Ramanath V (2022) A dual surrogate driven L-moments based robust design with scarce samples in the presence of extremes. Struct Multidisc Optim 65(3):1–23
Jiang C, Han X, Lu GY, Liu J, Zhang Z, Bai YC (2011) Correlation analysis of non-probabilistic convex model and corresponding structural reliability technique. Comput Methods Appl Mech Eng 200(33–36):2528–2546
Jiang C, Ni BY, Han X, Tao YR (2014a) Non-probabilistic convex model process: a new method of time-variant uncertainty analysis and its application to structural dynamic reliability problems. Comput Methods Appl Mech Eng 268:656–676
Jiang C, Zhang QF, Han X, Qian YH (2014b) A non-probabilistic structural reliability analysis method based on a multidimensional parallelepiped convex model. Acta Mech 225(2):383–395
Jung Y, Cho H, Lee I (2019) Reliability measure approach for confidence-based design optimization under insufficient input data. Struct Multidisc Optim 60(5):1967–1982
Kang Z, Luo Y, Li A (2011) On non-probabilistic reliability-based design optimization of structures with uncertain-but-bounded parameters. Struct Saf 33(3):196–205
Kang YJ, Noh Y, Lim O (2018) Kernel density estimation with bounded data. Struct Multidisc Optim 57(1):95–113
Lataniotis C (2019) Data-driven uncertainty quantification for high-dimensional engineering problems. Doctoral dissertation, ETH Zurich
Liang J, Mourelatos ZP, Tu J (2004) A single-loop method for reliability-based design optimization. In: International design engineering technical conferences and computers and information in engineering conference, vol 46946, pp 419–430
Liu X, Fu Q, Ye N, Yin L (2019) The multi-objective reliability-based design optimization for structure based on probability and ellipsoidal convex hybrid model. Struct Saf 77:48–56
Meng Z, Hu H, Zhou H (2018) Super parametric convex model and its application for non-probabilistic reliability-based design optimization. Appl Math Model 55:354–370
Meng Z, Zhang Z, Zhou H (2020) A novel experimental data-driven exponential convex model for reliability assessment with uncertain-but-bounded parameters. Appl Math Model 77:773–787
Moore RE, Kearfott RB, Cloud MJ (2009) Introduction to interval analysis. Soc Ind Appl Math
Moshtagh N (2005) Minimum volume enclosing ellipsoid. Convex Optim 111:1–9
Muhanna RL, Mullen RL (2001) Uncertainty in mechanics problems-interval-based approach. J Eng Mech 127(6):557–566
Ni BY, Elishakoff I, Jiang C, Fu CM, Han X (2016) Generalization of the super ellipsoid concept and its application in mechanics. Appl Math Model 40(21–22):9427–9444
Qiu Z, Elishakoff I (1998) Antioptimization of structures with large uncertain-but-non-random parameters via interval analysis. Comput Methods Appl Mech Eng 152(3–4):361–372
Qiu Z, Wang X (2003) Comparison of dynamic response of structures with uncertain-but-bounded parameters using non-probabilistic interval analysis method and probabilistic approach. Int J Solids Struct 40(20):5423–5439
Qiu Z, Wu H, Elishakoff I, Liu D (2021) Data-based polyhedron model for optimization of engineering structures involving uncertainties. Data-Centric Eng 2
Shafer G (1976) A mathematical theory of evidence. Princeton University Press, Princeton
Shu-xiang G, Zhen-zhou L, Li-fu F (2002) Fuzzy arithmetic and solving of the static governing equations of fuzzy finite element method. Appl Math Mech 23(9):1054–1061
Zhao G, Liu J, Wen G, Wang H, Li F (2020) A novel method for non-probabilistic convex modelling based on data from practical engineering. Appl Math Model 80:516–530
Zhu LP, Elishakoff I, Starnes JH Jr (1996) Derivation of multi-dimensional ellipsoidal convex model for experimental data. Math Comput Model 24(2):103–114
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare that they have no conflict of interest.
Replication of results
MATLAB® codes to reproduce the proposed approach results for the examples discussed are made available in this link.
Additional information
Responsible Editor: Tae Hee Lee
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Topical Collection: 14th World Congress of Structural and Multidisciplinary Optimization.
Guest Editors: Y Noh, E Acar, J Carstensen, J Guest, J Norato, P Ramu.
Appendices
Appendix 1
1.1 C-moments and L-moments comparison
L-moments are robust than conventional moments (C-moments) in the presence of extremes and less sensitive to small sample size. Even if there are no extremes L-moments perform as good as C-moments if not better. A comparison between the C-moments and L-moments estimated from a sample size of 10, for medium tail is presented here. The Fig. 11 present the comparisons of ratios of population estimate to sample estimate of the respective quantity. It is clear that the variation of L-moments is low compared to that of the C-moments. Though the presented results are only for medium tail, other types of tails also exhibit similar performance.
Appendix 2
1.1 Optimization flowchart
The optimization framework followed in this work is presented in Fig. 12. In the presented optimization formulations, the objective function is a function of only design variables and the constraints are a function of design variable and random variables. We construct the convex hull in random variable space and estimate the extrema of performance for a given design variable combination and, are used in the constraint evaluation. That is for instance, in cantilever beam example, maximum stress is computed and used in the constraint as \(S_{\text{max}} < S_{\text{allowable}}\).
Rights and permissions
About this article
Cite this article
Jain, N., Ramu, P. L-moments and Chebyshev inequality driven convex model for uncertainty quantification. Struct Multidisc Optim 65, 184 (2022). https://doi.org/10.1007/s00158-022-03247-4
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00158-022-03247-4