Rare event simulation for dynamic fault trees

Enno Jozef Johannes Ruijters (Corresponding Author), D.P. Reijsbergen, Pieter-Tjerk de Boer, Mariëlle Ida Antoinette Stoelinga (Corresponding Author)

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)
30 Downloads (Pure)

Abstract

Fault trees (FT) are a popular industrial method for reliability engineering, for which Monte Carlo simulation is an important technique to estimate common dependability metrics, such as the system reliability and availability. A severe drawback of Monte Carlo simulation is that the number of simulations required to obtain accurate estimations grows extremely large in the presence of rare events, i.e., events whose probability of occurrence is very low, which typically holds for failures in highly reliable systems.

This paper presents a novel method for rare event simulation of dynamic fault trees with complex repairs that requires only a modest number of simulations, while retaining statistically justified confidence intervals. Our method exploits the importance sampling technique for rare event simulation, together with a compositional state space generation method for dynamic fault trees.

We demonstrate our approach using three parameterized sets of case studies, showing that our method can handle fault trees that could not be evaluated with either existing analytical techniques using stochastic model checking, nor with standard simulation techniques.
Original languageEnglish
Pages (from-to)220-231
Number of pages12
JournalReliability engineering & system safety
Volume186
Early online date2 Feb 2019
DOIs
Publication statusPublished - 1 Jun 2019

Fingerprint

Importance sampling
Model checking
Stochastic models
Repair
Availability
Monte Carlo simulation

Cite this

@article{7ad58f4359f7469db14d7aa22116ef0e,
title = "Rare event simulation for dynamic fault trees",
abstract = "Fault trees (FT) are a popular industrial method for reliability engineering, for which Monte Carlo simulation is an important technique to estimate common dependability metrics, such as the system reliability and availability. A severe drawback of Monte Carlo simulation is that the number of simulations required to obtain accurate estimations grows extremely large in the presence of rare events, i.e., events whose probability of occurrence is very low, which typically holds for failures in highly reliable systems.This paper presents a novel method for rare event simulation of dynamic fault trees with complex repairs that requires only a modest number of simulations, while retaining statistically justified confidence intervals. Our method exploits the importance sampling technique for rare event simulation, together with a compositional state space generation method for dynamic fault trees.We demonstrate our approach using three parameterized sets of case studies, showing that our method can handle fault trees that could not be evaluated with either existing analytical techniques using stochastic model checking, nor with standard simulation techniques.",
author = "Ruijters, {Enno Jozef Johannes} and D.P. Reijsbergen and {de Boer}, Pieter-Tjerk and Stoelinga, {Mari{\"e}lle Ida Antoinette}",
year = "2019",
month = "6",
day = "1",
doi = "10.1016/j.ress.2019.02.004",
language = "English",
volume = "186",
pages = "220--231",
journal = "Reliability engineering & system safety",
issn = "0951-8320",
publisher = "Elsevier",

}

Rare event simulation for dynamic fault trees. / Ruijters, Enno Jozef Johannes (Corresponding Author); Reijsbergen, D.P.; de Boer, Pieter-Tjerk ; Stoelinga, Mariëlle Ida Antoinette (Corresponding Author).

In: Reliability engineering & system safety, Vol. 186, 01.06.2019, p. 220-231.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Rare event simulation for dynamic fault trees

AU - Ruijters, Enno Jozef Johannes

AU - Reijsbergen, D.P.

AU - de Boer, Pieter-Tjerk

AU - Stoelinga, Mariëlle Ida Antoinette

PY - 2019/6/1

Y1 - 2019/6/1

N2 - Fault trees (FT) are a popular industrial method for reliability engineering, for which Monte Carlo simulation is an important technique to estimate common dependability metrics, such as the system reliability and availability. A severe drawback of Monte Carlo simulation is that the number of simulations required to obtain accurate estimations grows extremely large in the presence of rare events, i.e., events whose probability of occurrence is very low, which typically holds for failures in highly reliable systems.This paper presents a novel method for rare event simulation of dynamic fault trees with complex repairs that requires only a modest number of simulations, while retaining statistically justified confidence intervals. Our method exploits the importance sampling technique for rare event simulation, together with a compositional state space generation method for dynamic fault trees.We demonstrate our approach using three parameterized sets of case studies, showing that our method can handle fault trees that could not be evaluated with either existing analytical techniques using stochastic model checking, nor with standard simulation techniques.

AB - Fault trees (FT) are a popular industrial method for reliability engineering, for which Monte Carlo simulation is an important technique to estimate common dependability metrics, such as the system reliability and availability. A severe drawback of Monte Carlo simulation is that the number of simulations required to obtain accurate estimations grows extremely large in the presence of rare events, i.e., events whose probability of occurrence is very low, which typically holds for failures in highly reliable systems.This paper presents a novel method for rare event simulation of dynamic fault trees with complex repairs that requires only a modest number of simulations, while retaining statistically justified confidence intervals. Our method exploits the importance sampling technique for rare event simulation, together with a compositional state space generation method for dynamic fault trees.We demonstrate our approach using three parameterized sets of case studies, showing that our method can handle fault trees that could not be evaluated with either existing analytical techniques using stochastic model checking, nor with standard simulation techniques.

U2 - 10.1016/j.ress.2019.02.004

DO - 10.1016/j.ress.2019.02.004

M3 - Article

VL - 186

SP - 220

EP - 231

JO - Reliability engineering & system safety

JF - Reliability engineering & system safety

SN - 0951-8320

ER -