The effect of model uncertainty on maintenance optimization

T.J. Bedford, C. Bunea

Research output: Contribution to journalArticle

44 Citations (Scopus)

Abstract

Much operational reliability data available, e.g., in the nuclear industry, is heavily right-censored by preventive maintenance. The common methods for dealing with right-censored data (total time on test statistic, Kaplan-Meier estimator, adjusted rank methods) assume the s-independent competing-risk model for the underlying failure process and the censoring process, even though there are, many s-dependent competing-risk models that can also interpret the data. It is not possible to identify the 'correct' competing risk model from censored data. A reasonable question is whether this model uncertainty is of practical importance. This paper considers the impact of this model-uncertainty on maintenance optimization, and shows that it can be substantial. Three competing-risk model classes are presented which can be used to model the data, and determine an optimal maintenance policy. Given these models, then consider the error that is made when optimizing costs using the wrong model. Model uncertainty can be expressed in terms of the 'dependence between competing risks' which can be quantified by expert judgment. This enables reformulating the maintenance optimization problem to account for model uncertainty.
LanguageEnglish
Pages486-493
Number of pages7
JournalIEEE Transactions on Reliability
Volume51
Issue number4
DOIs
Publication statusPublished - 2002

Fingerprint

Uncertainty
Nuclear industry
Preventive maintenance
Statistics
Costs

Keywords

  • failure analysis
  • maintenance engineering
  • probability reliability
  • management theory
  • reliability engineering

Cite this

@article{b3688c4248d243c3afd7375d1f68d548,
title = "The effect of model uncertainty on maintenance optimization",
abstract = "Much operational reliability data available, e.g., in the nuclear industry, is heavily right-censored by preventive maintenance. The common methods for dealing with right-censored data (total time on test statistic, Kaplan-Meier estimator, adjusted rank methods) assume the s-independent competing-risk model for the underlying failure process and the censoring process, even though there are, many s-dependent competing-risk models that can also interpret the data. It is not possible to identify the 'correct' competing risk model from censored data. A reasonable question is whether this model uncertainty is of practical importance. This paper considers the impact of this model-uncertainty on maintenance optimization, and shows that it can be substantial. Three competing-risk model classes are presented which can be used to model the data, and determine an optimal maintenance policy. Given these models, then consider the error that is made when optimizing costs using the wrong model. Model uncertainty can be expressed in terms of the 'dependence between competing risks' which can be quantified by expert judgment. This enables reformulating the maintenance optimization problem to account for model uncertainty.",
keywords = "failure analysis, maintenance engineering, probability reliability, management theory, reliability engineering",
author = "T.J. Bedford and C. Bunea",
year = "2002",
doi = "10.1109/TR.2002.804486",
language = "English",
volume = "51",
pages = "486--493",
journal = "IEEE Transactions on Reliability",
issn = "0018-9529",
number = "4",

}

The effect of model uncertainty on maintenance optimization. / Bedford, T.J.; Bunea, C.

In: IEEE Transactions on Reliability, Vol. 51, No. 4, 2002, p. 486-493.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The effect of model uncertainty on maintenance optimization

AU - Bedford, T.J.

AU - Bunea, C.

PY - 2002

Y1 - 2002

N2 - Much operational reliability data available, e.g., in the nuclear industry, is heavily right-censored by preventive maintenance. The common methods for dealing with right-censored data (total time on test statistic, Kaplan-Meier estimator, adjusted rank methods) assume the s-independent competing-risk model for the underlying failure process and the censoring process, even though there are, many s-dependent competing-risk models that can also interpret the data. It is not possible to identify the 'correct' competing risk model from censored data. A reasonable question is whether this model uncertainty is of practical importance. This paper considers the impact of this model-uncertainty on maintenance optimization, and shows that it can be substantial. Three competing-risk model classes are presented which can be used to model the data, and determine an optimal maintenance policy. Given these models, then consider the error that is made when optimizing costs using the wrong model. Model uncertainty can be expressed in terms of the 'dependence between competing risks' which can be quantified by expert judgment. This enables reformulating the maintenance optimization problem to account for model uncertainty.

AB - Much operational reliability data available, e.g., in the nuclear industry, is heavily right-censored by preventive maintenance. The common methods for dealing with right-censored data (total time on test statistic, Kaplan-Meier estimator, adjusted rank methods) assume the s-independent competing-risk model for the underlying failure process and the censoring process, even though there are, many s-dependent competing-risk models that can also interpret the data. It is not possible to identify the 'correct' competing risk model from censored data. A reasonable question is whether this model uncertainty is of practical importance. This paper considers the impact of this model-uncertainty on maintenance optimization, and shows that it can be substantial. Three competing-risk model classes are presented which can be used to model the data, and determine an optimal maintenance policy. Given these models, then consider the error that is made when optimizing costs using the wrong model. Model uncertainty can be expressed in terms of the 'dependence between competing risks' which can be quantified by expert judgment. This enables reformulating the maintenance optimization problem to account for model uncertainty.

KW - failure analysis

KW - maintenance engineering

KW - probability reliability

KW - management theory

KW - reliability engineering

UR - http://dx.doi.org/10.1109/TR.2002.804486

U2 - 10.1109/TR.2002.804486

DO - 10.1109/TR.2002.804486

M3 - Article

VL - 51

SP - 486

EP - 493

JO - IEEE Transactions on Reliability

T2 - IEEE Transactions on Reliability

JF - IEEE Transactions on Reliability

SN - 0018-9529

IS - 4

ER -