Probabilistic failure analysis by simulation

S. K. Au

doi:10.1016/B978-008044046-0.50538-8

Probabilistic failure analysis by simulation

S. K. Au^*

^*Corresponding author for this work

Nanyang Technological University

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

A probabilistic approach for failure analysis is presented in this paper, which investigates the probable scenarios that occur in case of failure of systems with uncertainties. This can be carried out by studying the statistics of system behavior corresponding to the 'conditional samples' of uncertain parameters given that the failure event has occurred. This necessitates the efficient generation of conditional samples, which is in general a highly nontrivial task. Two algorithms based on Markov Chain Monte Carlo simulation are presented for efficiently generating asymptotically conditional samples for failure analysis.

Original language	English
Title of host publication	Computational Fluid and Solid Mechanics 2003
Publisher	Elsevier Inc.
Pages	2194-2196
Number of pages	3
ISBN (Electronic)	9780080529479
ISBN (Print)	9780080440460
DOIs	https://doi.org/10.1016/B978-008044046-0.50538-8
Publication status	Published - Jun 2 2003
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2003 Elsevier Science Ltd. All rights reserved.

ASJC Scopus Subject Areas

General Engineering

Keywords

Failure analysis
Importance sampling
Markov Chain Monte Carlo
Rehability
Subset simulation

Access to Document

10.1016/B978-008044046-0.50538-8

Cite this

@inbook{3c5095e05fe14ab2b1f7adfa6f2ece73,

title = "Probabilistic failure analysis by simulation",

abstract = "A probabilistic approach for failure analysis is presented in this paper, which investigates the probable scenarios that occur in case of failure of systems with uncertainties. This can be carried out by studying the statistics of system behavior corresponding to the 'conditional samples' of uncertain parameters given that the failure event has occurred. This necessitates the efficient generation of conditional samples, which is in general a highly nontrivial task. Two algorithms based on Markov Chain Monte Carlo simulation are presented for efficiently generating asymptotically conditional samples for failure analysis.",

keywords = "Failure analysis, Importance sampling, Markov Chain Monte Carlo, Rehability, Subset simulation",

author = "Au, {S. K.}",

year = "2003",

month = jun,

day = "2",

doi = "10.1016/B978-008044046-0.50538-8",

language = "English",

isbn = "9780080440460",

pages = "2194--2196",

booktitle = "Computational Fluid and Solid Mechanics 2003",

publisher = "Elsevier Inc.",

address = "United States",

}

TY - CHAP

T1 - Probabilistic failure analysis by simulation

AU - Au, S. K.

PY - 2003/6/2

Y1 - 2003/6/2

N2 - A probabilistic approach for failure analysis is presented in this paper, which investigates the probable scenarios that occur in case of failure of systems with uncertainties. This can be carried out by studying the statistics of system behavior corresponding to the 'conditional samples' of uncertain parameters given that the failure event has occurred. This necessitates the efficient generation of conditional samples, which is in general a highly nontrivial task. Two algorithms based on Markov Chain Monte Carlo simulation are presented for efficiently generating asymptotically conditional samples for failure analysis.

AB - A probabilistic approach for failure analysis is presented in this paper, which investigates the probable scenarios that occur in case of failure of systems with uncertainties. This can be carried out by studying the statistics of system behavior corresponding to the 'conditional samples' of uncertain parameters given that the failure event has occurred. This necessitates the efficient generation of conditional samples, which is in general a highly nontrivial task. Two algorithms based on Markov Chain Monte Carlo simulation are presented for efficiently generating asymptotically conditional samples for failure analysis.

KW - Failure analysis

KW - Importance sampling

KW - Markov Chain Monte Carlo

KW - Rehability

KW - Subset simulation

UR - http://www.scopus.com/inward/record.url?scp=84941729248&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84941729248&partnerID=8YFLogxK

U2 - 10.1016/B978-008044046-0.50538-8

DO - 10.1016/B978-008044046-0.50538-8

M3 - Chapter

AN - SCOPUS:84941729248

SN - 9780080440460

SP - 2194

EP - 2196

BT - Computational Fluid and Solid Mechanics 2003

PB - Elsevier Inc.

ER -

Probabilistic failure analysis by simulation

Abstract

Bibliographical note

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this