Abstract
A challenging problem encountered in engineering applications is the estimation of a probability-of-failure based on incomplete knowledge of the sources of uncertainty and/or limited sampling. Theories formulated to derive upper probability bounds offer an attractive alternative because first, they avoid postulating the probability laws that are often unknown and second, they substitute numerical optimization for statistical sampling. A critical assessment of one such technique is presented. It derives upper probability bounds from the McDiarmid concentration-of-measure theory, which postulates that fluctuations of a function are more-or-less concentrated about its mean value. Two applications of this theory are presented. The first application analyzes a “toy” polynomial function defined in two dimensions. The upper bounds of probability are calculated and compared to sampling-based estimates of the true-but-unknown probabilities. For this function, the upper bounds obtained are too broad to be useful. These results are confirmed by conducting a similar analysis on a real engineering system, where upper bounds of probability associated with resonant frequencies of a structural system are estimated. A high-fidelity finite element model, previously validated using vibration measurements, is used to predict the frequencies. In this application, the uncertainty is introduced by way of material properties and the effective preload of a beam-to-column connection, modeled explicitly. These applications suggest that the theory not only leads to upper bounds that are inefficient but that can also be sub-optimal if their numerical estimation is based on too few model runs. It is concluded that this particular theory, while mathematically attractive, may not be well suited for engineering applications.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Lucas LJ, Owhadi H, Ortiz M (2008) Rigorous verification, validation, uncertainty quantification and certification through concentration-of-measure inequalities. J Comput Methods Appl Mech Eng 197:4591–4609
Hemez FM, Atamturktur SH, Unal C (2009) Prediction with quantified uncertainty of temperature and rate dependent material behavior. In: 11th AIAA non-deterministic approaches conference, Palm Springs, May 4–7, 2009
Maupin R, Hylok J, Rutherford A, Anderson M (2005) Validation of a threaded assembly, part I: overview. In: 6th European conference on structural dynamics, Paris, Sept 5–7, 2005
Hylok J, Rutherford A, Maupin R, Anderson M, Groethe M (2005) Validation of a threaded assembly, part II: experiments. In: 6th European conference on structural dynamics, Paris, Sept 5–7, 2005
Rutherford A, Maupin R, Hylok J, Anderson M (2005) Validation of a threaded assembly, part III: validation. In: 6th European conference on structural dynamics, Paris, Sept 5–7, 2005
Owhadi H, Sullivan TJ, McKerns M, Ortiz M, Scovel C (2010) Optimal uncertainty quantification. Technical report 2010-03, Applied and Computational Mathematics, California Institute of Technology, Pasadena
McDiarmid C (1989) On the method of bounded differences. In: Siemons J (ed) Surveys in combinatorics. Volume 141 of the london mathematical society lecture. Cambridge University Press, Cambridge, pp 148–188
The MathWorks, Inc. (2011) MATLAB R2011a product help, Natick
Rosenbrock HH (1960) An automatic method for finding the greatest or least value of a function. Comput J 3:175–184
Hemez FM, Atamturktur SH (2011) The dangers of sparse sampling for the quantification of margin and uncertainty. Reliab Eng Syst Saf 96:1220–1231
Hemez FM (2010) Performance of the Morris one-at-a-time sensitivity analysis to explore large-dimensional functions. Technical report LA-UR-10-0069, Los Alamos National Laboratory, Los Alamos
Stull CJ, Hemez FM (2012) Optimal inequalities to bound a performance probability using McDiarmid concentration of measure theory. Technical report LA-UR-12-24769, Los Alamos National Laboratory, Los Alamos
Dassault Systèmes (2010) Abaqus 6.10 online documentation, Providence
Stull CJ, Hemez FM (2012) “On the use of info-gap decision theory to select from among models of varying complexity. Technical report LA-UR-12-0379, Los Alamos National Laboratory, Los Alamos
Sullivan TJ, Owhadi H (2012) Distances and diameters in concentration inequalities: from geometry to optimal assignment of sampling resources. Int J Uncertain Quantif 2(1):21–38
Owhadi H, Scovel C, Sullivan TJ, McKerns M, Ortiz M (2012) Optimal uncertainty quantification. SIAM Rev (submitted, Published at arXiv:1009.0679)
Sullivan TJ, McKerns M, Meyer D, Theil F, Owhadi H, Ortiz M (2012) Optimal uncertainty quantification for legacy data observations of Lipschitz functions. Math Model Numer Anal (submitted, Published at arXiv:1202.1928)
Acknowledgements
This work is performed under the auspices of the Verification and Validation (V&V) program for Advanced Scientific Computing (ASC) at Los Alamos National Laboratory (LANL). The first author is grateful to Frederick J. Wysocki, V&V program manager at LANL, for his continuing support. Funding for the second author was sponsored by the U.S. Department of Energy, Nuclear Energy Division, Advanced Modeling and Simulation Office (NE-71), Nuclear Energy Advanced Modeling and Simulation (NEAMS) Program, Verification, Validation and Uncertainty Quantification (VU) Program Element. The second author is sincerely grateful to Brian J. Williams (CCS-6) for his continued support. LANL is operated by the Los Alamos National Security, LLC for the National Nuclear Security Administration of the U.S. Department of Energy under contract DE-AC52-06NA25396.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 The Society for Experimental Mechanics, Inc.
About this paper
Cite this paper
Hemez, F.M., Stull, C.J. (2013). Optimal Inequalities to Bound a Performance Probability. In: Simmermacher, T., Cogan, S., Moaveni, B., Papadimitriou, C. (eds) Topics in Model Validation and Uncertainty Quantification, Volume 5. Conference Proceedings of the Society for Experimental Mechanics Series. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-6564-5_1
Download citation
DOI: https://doi.org/10.1007/978-1-4614-6564-5_1
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-6563-8
Online ISBN: 978-1-4614-6564-5
eBook Packages: EngineeringEngineering (R0)