Efficient procedure for failure probability function estimation in augmented space

Research output: Contribution to journalArticleResearchpeer review

Authors

Research Organisations

External Research Organisations

  • Xiamen University
  • Universidad Adolfo Ibanez
  • University of Liverpool
  • Tongji University
View graph of relations

Details

Original languageEnglish
Article number102104
JournalStructural Safety
Volume92
Early online date24 May 2021
Publication statusPublished - Sept 2021

Abstract

An efficient procedure is proposed to estimate the failure probability function (FPF) with respect to design variables, which correspond to distribution parameters of basic structural random variables. The proposed procedure is based on the concept of an augmented reliability problem, which assumes the design variables as uncertain by assigning a prior distribution, transforming the FPF into an expression that includes the posterior distribution of those design variables. The novel contribution of this work consists of expressing this target posterior distribution as an integral, allowing it to be estimated by means of sampling, and no distribution fitting is needed, leading to an efficient estimation of FPF. The proposed procedure is implemented within three different simulation strategies: Monte Carlo simulation, importance sampling and subset simulation; for each of these cases, expressions for the coefficient of variation of the FPF estimate are derived. Numerical examples illustrate performance of the proposed approaches.

Keywords

    Bayesian theory, Failure probability function, Reliability analysis, Reliability-based optimization

ASJC Scopus subject areas

Cite this

Efficient procedure for failure probability function estimation in augmented space. / Yuan, Xiukai; Liu, Shaolong; Valdebenito, M. A. et al.
In: Structural Safety, Vol. 92, 102104, 09.2021.

Research output: Contribution to journalArticleResearchpeer review

Yuan X, Liu S, Valdebenito MA, Gu J, Beer M. Efficient procedure for failure probability function estimation in augmented space. Structural Safety. 2021 Sept;92:102104. Epub 2021 May 24. doi: 10.1016/j.strusafe.2021.102104
Yuan, Xiukai ; Liu, Shaolong ; Valdebenito, M. A. et al. / Efficient procedure for failure probability function estimation in augmented space. In: Structural Safety. 2021 ; Vol. 92.
Download
@article{4b1ed50028b747d7b0f6539c4c0d52b1,
title = "Efficient procedure for failure probability function estimation in augmented space",
abstract = "An efficient procedure is proposed to estimate the failure probability function (FPF) with respect to design variables, which correspond to distribution parameters of basic structural random variables. The proposed procedure is based on the concept of an augmented reliability problem, which assumes the design variables as uncertain by assigning a prior distribution, transforming the FPF into an expression that includes the posterior distribution of those design variables. The novel contribution of this work consists of expressing this target posterior distribution as an integral, allowing it to be estimated by means of sampling, and no distribution fitting is needed, leading to an efficient estimation of FPF. The proposed procedure is implemented within three different simulation strategies: Monte Carlo simulation, importance sampling and subset simulation; for each of these cases, expressions for the coefficient of variation of the FPF estimate are derived. Numerical examples illustrate performance of the proposed approaches.",
keywords = "Bayesian theory, Failure probability function, Reliability analysis, Reliability-based optimization",
author = "Xiukai Yuan and Shaolong Liu and Valdebenito, {M. A.} and Jian Gu and Michael Beer",
note = "Funding Information: The authors would like to acknowledge financial support from NSAF (Grant No. U1530122 ), the Aeronautical Science Foundation of China (Grant No. ASFC-20170968002 ), the Fundamental Research Funds for the Central Universities of China ( XMU-20720180072 ) and ANID (National Agency for Research and Development, Chile) under its program FONDECYT , grant number 1180271 . ",
year = "2021",
month = sep,
doi = "10.1016/j.strusafe.2021.102104",
language = "English",
volume = "92",
journal = "Structural Safety",
issn = "0167-4730",
publisher = "Elsevier",

}

Download

TY - JOUR

T1 - Efficient procedure for failure probability function estimation in augmented space

AU - Yuan, Xiukai

AU - Liu, Shaolong

AU - Valdebenito, M. A.

AU - Gu, Jian

AU - Beer, Michael

N1 - Funding Information: The authors would like to acknowledge financial support from NSAF (Grant No. U1530122 ), the Aeronautical Science Foundation of China (Grant No. ASFC-20170968002 ), the Fundamental Research Funds for the Central Universities of China ( XMU-20720180072 ) and ANID (National Agency for Research and Development, Chile) under its program FONDECYT , grant number 1180271 .

PY - 2021/9

Y1 - 2021/9

N2 - An efficient procedure is proposed to estimate the failure probability function (FPF) with respect to design variables, which correspond to distribution parameters of basic structural random variables. The proposed procedure is based on the concept of an augmented reliability problem, which assumes the design variables as uncertain by assigning a prior distribution, transforming the FPF into an expression that includes the posterior distribution of those design variables. The novel contribution of this work consists of expressing this target posterior distribution as an integral, allowing it to be estimated by means of sampling, and no distribution fitting is needed, leading to an efficient estimation of FPF. The proposed procedure is implemented within three different simulation strategies: Monte Carlo simulation, importance sampling and subset simulation; for each of these cases, expressions for the coefficient of variation of the FPF estimate are derived. Numerical examples illustrate performance of the proposed approaches.

AB - An efficient procedure is proposed to estimate the failure probability function (FPF) with respect to design variables, which correspond to distribution parameters of basic structural random variables. The proposed procedure is based on the concept of an augmented reliability problem, which assumes the design variables as uncertain by assigning a prior distribution, transforming the FPF into an expression that includes the posterior distribution of those design variables. The novel contribution of this work consists of expressing this target posterior distribution as an integral, allowing it to be estimated by means of sampling, and no distribution fitting is needed, leading to an efficient estimation of FPF. The proposed procedure is implemented within three different simulation strategies: Monte Carlo simulation, importance sampling and subset simulation; for each of these cases, expressions for the coefficient of variation of the FPF estimate are derived. Numerical examples illustrate performance of the proposed approaches.

KW - Bayesian theory

KW - Failure probability function

KW - Reliability analysis

KW - Reliability-based optimization

UR - http://www.scopus.com/inward/record.url?scp=85104959492&partnerID=8YFLogxK

U2 - 10.1016/j.strusafe.2021.102104

DO - 10.1016/j.strusafe.2021.102104

M3 - Article

AN - SCOPUS:85104959492

VL - 92

JO - Structural Safety

JF - Structural Safety

SN - 0167-4730

M1 - 102104

ER -

By the same author(s)