Grant: Discovery Grants Program - Individual
Simon Fraser University
$22,000.00
Estimation and optimization of imperfectly repaired systems
EF 2007-08
Résumé
This research will focus on the reliability of systems subject to imperfect repair upon failure. My research in this area has been motivated by two concerns: how to develop improved estimation models to predict system failure; and how to utilize these estimated models to improve (optimize) system reliability. While the proposed research applies to engineering systems, it is also more broadly applicable in areas of medical and production systems. Since most systems are neither perfectly nor minimally repaired upon failure, previous research on estimation has focused on identifying parameters of basic failure models, such as Weibull, log-normal and non-parametric procedures, while incorporating imperfect repair parameters into these frameworks. Utilizing the concept of virtual age (Kijima), estimation has typically followed maximum likelihood procedures. Recognizing the inherent difficulty of a virtual age concept, more recently we have begun to utilize fuzzy logic to model failure/repair processes. This appears to be a much more natural approach to capture the engineering sense of such processes. Generation of density functions from the estimated logic functions appears possible, thus enabling the determination of more usable system parameters. The second issue to be tackled in the proposed research is how to utilize these estimated models to optimize system reliability. Typically the approach I have taken has been the development of Markov and semi-Markov models to optimize repair/replacement times, often conditional on the state (virtual age) of the system. This includes interesting work on when to skip planned maintenance because an unexpected failure had only recently sufficiently repaired the system. More recently, we have begun utilizing vacation queuing models in failure processes. These are most useful in modeling systems with multiple failure modes when the system operator can go off (on vacation) and perform other repair tasks that can serve to maintain the overall system reliability. The proposed extensions to imperfect repair of failure modes appears feasible and it is expected to lead to new forms of maintenance policy improvement.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
18305-2006
Name nom
Love, Ernest
Department département
Business Administration, Faculty of
Organization id
5
Institution établissement
Simon Fraser University
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2007
Competition year année de concours
2006
Award amount
22000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
20
Committee name en
Industrial Engineering
Committee name fr
Génie industriel
Area of application code
1205
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Mathematical sciences
Area of application fr
Sciences mathématiques
Research subject code
1600
Research subject group en
Industrial engineering
Research subject group fr
Génie industriel
Research subject en
Industrial engineering
Research subject fr
Génie industriel
Partie
2
Nb partie
5
Application title
Estimation and optimization of imperfectly repaired systems
Keyword
NA
Application summary
This research will focus on the reliability of systems subject to imperfect repair upon failure. My research in this area has been motivated by two concerns: how to develop improved estimation models to predict system failure; and how to utilize these estimated models to improve (optimize) system reliability. While the proposed research applies to engineering systems, it is also more broadly applicable in areas of medical and production systems. Since most systems are neither perfectly nor minimally repaired upon failure, previous research on estimation has focused on identifying parameters of basic failure models, such as Weibull, log-normal and non-parametric procedures, while incorporating imperfect repair parameters into these frameworks. Utilizing the concept of virtual age (Kijima), estimation has typically followed maximum likelihood procedures. Recognizing the inherent difficulty of a virtual age concept, more recently we have begun to utilize fuzzy logic to model failure/repair processes. This appears to be a much more natural approach to capture the engineering sense of such processes. Generation of density functions from the estimated logic functions appears possible, thus enabling the determination of more usable system parameters. The second issue to be tackled in the proposed research is how to utilize these estimated models to optimize system reliability. Typically the approach I have taken has been the development of Markov and semi-Markov models to optimize repair/replacement times, often conditional on the state (virtual age) of the system. This includes interesting work on when to skip planned maintenance because an unexpected failure had only recently sufficiently repaired the system. More recently, we have begun utilizing vacation queuing models in failure processes. These are most useful in modeling systems with multiple failure modes when the system operator can go off (on vacation) and perform other repair tasks that can serve to maintain the overall system reliability. The proposed extensions to imperfect repair of failure modes appears feasible and it is expected to lead to new forms of maintenance policy improvement.