A generalized "max-min" sample for reliability assessment with dependent variables

Sylvain Lacaze, Samy Missoum

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper introduces a novel approach for reliability assessment with dependent variables. In this work, the boundary of the failure domain, for a computational problem with expensive function evaluations, is approximated using a Support Vector Machine and an adaptive sampling scheme. The approximation is sequentially refined using a new adaptive sampling scheme referred to as generalized "max-min". This technique efficiently targets high probability density regions of the random space. This is achieved by modifying an adaptive sampling scheme originally tailored for deterministic spaces (Explicit Space Design Decomposition). In particular, the approach can handle any joint probability density function, even if the variables are dependent. In the latter case, the joint distribution might be obtained from copula. In addition, uncertainty on the probability of failure estimate are estimated using bootstrapping. A bootstrapped coefficient of variation of the probability of failure is used as an estimate of the true error to determine convergence. The proposed method is then applied to analytical examples and a beam bending reliability assessment using copulas.

Original languageEnglish (US)
Title of host publication34th Computers and Information in Engineering Conference
PublisherAmerican Society of Mechanical Engineers (ASME)
Volume1A
ISBN (Print)9780791846285
DOIs
StatePublished - 2014
EventASME 2014 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2014 - Buffalo, United States
Duration: Aug 17 2014Aug 20 2014

Other

OtherASME 2014 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2014
CountryUnited States
CityBuffalo
Period8/17/148/20/14

Fingerprint

Adaptive Sampling
Reliability Assessment
Min-max
Copula
Sampling
Dependent
Function evaluation
Coefficient of variation
Bootstrapping
Evaluation Function
Probability Density
Joint Distribution
Estimate
Probability density function
Support vector machines
Support Vector Machine
Decomposition
Uncertainty
Decompose
Target

ASJC Scopus subject areas

  • Mechanical Engineering
  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Modeling and Simulation

Cite this

Lacaze, S., & Missoum, S. (2014). A generalized "max-min" sample for reliability assessment with dependent variables. In 34th Computers and Information in Engineering Conference (Vol. 1A). American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/DETC201434051

A generalized "max-min" sample for reliability assessment with dependent variables. / Lacaze, Sylvain; Missoum, Samy.

34th Computers and Information in Engineering Conference. Vol. 1A American Society of Mechanical Engineers (ASME), 2014.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lacaze, S & Missoum, S 2014, A generalized "max-min" sample for reliability assessment with dependent variables. in 34th Computers and Information in Engineering Conference. vol. 1A, American Society of Mechanical Engineers (ASME), ASME 2014 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2014, Buffalo, United States, 8/17/14. https://doi.org/10.1115/DETC201434051
Lacaze S, Missoum S. A generalized "max-min" sample for reliability assessment with dependent variables. In 34th Computers and Information in Engineering Conference. Vol. 1A. American Society of Mechanical Engineers (ASME). 2014 https://doi.org/10.1115/DETC201434051
Lacaze, Sylvain ; Missoum, Samy. / A generalized "max-min" sample for reliability assessment with dependent variables. 34th Computers and Information in Engineering Conference. Vol. 1A American Society of Mechanical Engineers (ASME), 2014.
@inproceedings{2eb7028ba02543b98214efb25d33fd2a,
title = "A generalized {"}max-min{"} sample for reliability assessment with dependent variables",
abstract = "This paper introduces a novel approach for reliability assessment with dependent variables. In this work, the boundary of the failure domain, for a computational problem with expensive function evaluations, is approximated using a Support Vector Machine and an adaptive sampling scheme. The approximation is sequentially refined using a new adaptive sampling scheme referred to as generalized {"}max-min{"}. This technique efficiently targets high probability density regions of the random space. This is achieved by modifying an adaptive sampling scheme originally tailored for deterministic spaces (Explicit Space Design Decomposition). In particular, the approach can handle any joint probability density function, even if the variables are dependent. In the latter case, the joint distribution might be obtained from copula. In addition, uncertainty on the probability of failure estimate are estimated using bootstrapping. A bootstrapped coefficient of variation of the probability of failure is used as an estimate of the true error to determine convergence. The proposed method is then applied to analytical examples and a beam bending reliability assessment using copulas.",
author = "Sylvain Lacaze and Samy Missoum",
year = "2014",
doi = "10.1115/DETC201434051",
language = "English (US)",
isbn = "9780791846285",
volume = "1A",
booktitle = "34th Computers and Information in Engineering Conference",
publisher = "American Society of Mechanical Engineers (ASME)",

}

TY - GEN

T1 - A generalized "max-min" sample for reliability assessment with dependent variables

AU - Lacaze, Sylvain

AU - Missoum, Samy

PY - 2014

Y1 - 2014

N2 - This paper introduces a novel approach for reliability assessment with dependent variables. In this work, the boundary of the failure domain, for a computational problem with expensive function evaluations, is approximated using a Support Vector Machine and an adaptive sampling scheme. The approximation is sequentially refined using a new adaptive sampling scheme referred to as generalized "max-min". This technique efficiently targets high probability density regions of the random space. This is achieved by modifying an adaptive sampling scheme originally tailored for deterministic spaces (Explicit Space Design Decomposition). In particular, the approach can handle any joint probability density function, even if the variables are dependent. In the latter case, the joint distribution might be obtained from copula. In addition, uncertainty on the probability of failure estimate are estimated using bootstrapping. A bootstrapped coefficient of variation of the probability of failure is used as an estimate of the true error to determine convergence. The proposed method is then applied to analytical examples and a beam bending reliability assessment using copulas.

AB - This paper introduces a novel approach for reliability assessment with dependent variables. In this work, the boundary of the failure domain, for a computational problem with expensive function evaluations, is approximated using a Support Vector Machine and an adaptive sampling scheme. The approximation is sequentially refined using a new adaptive sampling scheme referred to as generalized "max-min". This technique efficiently targets high probability density regions of the random space. This is achieved by modifying an adaptive sampling scheme originally tailored for deterministic spaces (Explicit Space Design Decomposition). In particular, the approach can handle any joint probability density function, even if the variables are dependent. In the latter case, the joint distribution might be obtained from copula. In addition, uncertainty on the probability of failure estimate are estimated using bootstrapping. A bootstrapped coefficient of variation of the probability of failure is used as an estimate of the true error to determine convergence. The proposed method is then applied to analytical examples and a beam bending reliability assessment using copulas.

UR - http://www.scopus.com/inward/record.url?scp=84961323878&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961323878&partnerID=8YFLogxK

U2 - 10.1115/DETC201434051

DO - 10.1115/DETC201434051

M3 - Conference contribution

AN - SCOPUS:84961323878

SN - 9780791846285

VL - 1A

BT - 34th Computers and Information in Engineering Conference

PB - American Society of Mechanical Engineers (ASME)

ER -