• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1997.10a
• /
• pp.193-196
• /
• 1997

In this paper we consider a Bayesian theoretic approach to periodic incomplete preventive maintenance with minimal repair at failure. We assume that the system failure rate is increasing as the frequency of PM increases and that the system is replaced at the K-th PM under this maintenance strategy. The optimal policies which minimize the expected cost rates are discussed. We seek the optimal periodic PM interval x and replacement time K under a Weibull failure intensity. Assuming suitable prior distribution for the Weibull parameters, we derive the posterior distribution incorporating failure data and obtain the updated optimal replacement strategies.

• Journal of Applied Reliability
• /
• v.16 no.4
• /
• pp.280-286
• /
• 2016

Purpose: Recently, Jiang defines the tradeoff B life to minimize a sum of life lost by preventive maintenance (PM) and corrective maintenance (CM) contribution parts and sets up an optimal replacement age of age replacement policy as this tradeoff life. In this paper, Jiang's model only considering the known lifetime distribution is extended by assigning different weights to two parts of PM and CM in order to reflect the practical maintenance situations in application. Methods: The new age replacement model is formulated and the meaning of a weight factor is expressed with the implied cost of failure under asymptotic expected cost model and also discussed with one-cycle expected cost criterion. Results: The proposed model is applied to Weibull and lognormal lifetime distributions and optimum PM replacement ages are derived with corresponding implied cost of failure. Conclusion: The new age replacement policy to escape the estimation of cost of failure in classical asymptotic expected cost criterion based on the renewal process is provided.

• Communications for Statistical Applications and Methods
• /
• v.13 no.1
• /
• pp.191-204
• /
• 2006

This paper develops a Bayesian method to derive the optimal sequential preventive maintenance(PM) policy by determining the PM schedules which minimize the mean cost rate. Such PM schedules are derived based on a general sequential imperfect PM model proposed by Lin, Zuo and Yam(2000) and may have unequal length of PM intervals. To apply the Bayesian approach in this problem, we assume that the failure times follow a Weibull distribution and consider some appropriate prior distributions for the scale and shape parameters of the Weibull model. The solution is proved to be finite and unique under some mild conditions. Numerical examples for the proposed optimal sequential PM policy are presented for illustrative purposes.

• Proceedings of the Korean Reliability Society Conference
• /
• 2005.06a
• /
• pp.131-137
• /
• 2005

In this paper, we propose a Bayesian approach to determine the adaptive preventive maintenance(PM) policy for a general sequential imperfect PM model proposed by Lin, Zuo and Yam(2000) that PM not only reduces the effective age of the system but also changes the hazard rate function. Assuming that the failure times follow Weibull distribution, we adopt a Bayesian approach to update unknown parameters and determine the Bayesian optimal sequential PM policies. Finally, numerical examples of the optimal adaptive PM policy are presented for illustrative purposes.

• Structural Engineering and Mechanics
• /
• v.63 no.6
• /
• pp.703-712
• /
• 2017

The composite blades of offshore wind turbines accumulate structural damage such as fatigue cracking due to harsh operation environments during their service time, leading to premature structural failures. This paper investigates various fatigue crack models for reproducing crack development in composite blades and proposes a stochastic approach to predict fatigue crack evolution and to analyse failure probability for the composite blades. Three typical fatigue models for the propagation of fatigue cracks, i.e., Miner model, Paris model and Reifsnider model, are discussed to reproduce the fatigue crack evolution in composite blades subjected to cyclical loadings. The lifetime probability of fatigue failure of the composite blades is estimated by stochastic deterioration modelling such as gamma process. Based on time-dependent reliability analysis and lifecycle cost analysis, an optimised maintenance policy is determined to make the optimal decision for the composite blades during the service time. A numerical example is employed to investigate the effectiveness of predicting fatigue crack growth, estimating the probability of fatigue failure and evaluating an optimal maintenance policy. The results from the numerical study show that the stochastic gamma process together with the proper fatigue models can provide a useful tool for remaining useful life predictions and optimum maintenance strategies of the composite blades of offshore wind turbines.

• Journal of Korean Society for Quality Management
• /
• v.25 no.3
• /
• pp.86-95
• /
• 1997

This paper considers a repairable system, which is maintained preventively at periodic times and is minimally repaired at each failure. Most preventive maintenance policies for such repairable systems assume that the cost of minimal repair is constant regardless of its age at failure. However, it is more practical to consider the situations where the cost of minimal repair is dependent not only on its age at failue, but also on the number of preventive maintenance carried out prior to its failure. We consider the preventive maintenance carried out prior to its failure. We consider the preventive maintenance policy with age-dependent minimal repair cost. The optimal policies which minimize the expected cost rate over an infinite time span are discussed. We obtain the optimal period and number of preventive maintenance prior to replacement of the system.

• Journal of Applied Reliability
• /
• v.17 no.1
• /
• pp.58-65
• /
• 2017

Different from general operating policies applied for various waiting line situations, two complementary dyadic operating policies are applied alternatingly to a single server maintenance service center model. That is, either of the two dyadic Min (N, T) or Max (N, T) policy is applied to operate such center first and the other operating policy should be applied later, and then the same sequence of both operating policies is followed repeatedly. This operating policy is denoted by the Minimax (N, T) policy. Purpose: Because of the newly introduced operating policy, important system characteristics of the considered service center model such as the expected busy and idle periods, the expected number of customers in the service center and so on should be derived to provide necessary information for determination of the optimal operating policy. Methods: Based on concepts of the newly introduced Minimax (N, T) policy, all necessary system characteristics should be redefined and then derived by constructing appropriate relations between complementary two dyadic operating policies. Results: Desired system characteristics are obtained successfully using simple procedures developed by utilizing peculiar structure of the Minimax (N, T) policy. Conclusion: Applying Minimax (N, T) operating policy is equivalent to applying the simple N and T operating policies alternatingly.

• Journal of Applied Reliability
• /
• v.18 no.2
• /
• pp.114-121
• /
• 2018

Purpose: This study proposes a process for evaluating the preventive maintenance policy for a system with degradation characteristics and for calculating the appropriate preventive maintenance cycle using time- and condition-based maintenance. Methods: First, the collected data is divided into the maintenance history lifetime and degradation lifetime, and analysis datasets are extracted through preprocessing. Particle filter algorithm is used to estimate the degradation lifetime from analysis datasets and prior information is obtained using LSE. The suitability and cost of the existing preventive maintenance policy are each evaluated based on the degradation lifetime and by using a minimum repair block replacement model of time-based maintenance. Results: The process is applied to the degradation of the reverse osmosis (RO) membrane in a seawater reverse osmosis (SWRO) plant to evaluate the existing preventive maintenance policy. Conclusion: This method can be used for facilities or systems that undergo degradation, which can be evaluated in terms of cost and time. The method is expected to be used in decision-making for devising the optimal preventive maintenance policy.

• Journal of Applied Reliability
• /
• v.17 no.3
• /
• pp.188-196
• /
• 2017

Purpose: The purpose of this research is to determine optimal replacement age using non-informative prior information and Bayesian method. Methods: We propose a novel approach using Bayesian method to determine the optimal replacement age in block replacement policy by defining the prior probability with data on failure time and repair time. The Marcov Chain Monte Carlo simulation is used to investigate the asymptotic distribution of posterior parameters. Results: An optimal replacement age of block replacement policy is determined which minimizes cost and nonoperating time when no information on prior distribution of parameters is given. Conclusion: We find the posterior distribution of parameters when lack of information on prior distribution, so that the optimal replacement age which minimizes the total cost and maximizes the total values is determined.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.11 no.18
• /
• pp.35-39
• /
• 1988

In general, the characteristics of components which consist of multi component system can not be the same. This paper proposes a maintenance model of multi-component system according to the characteristics of each component. In this paper multi-component system is divided into three components-critical component, major component and minor component, respectively. Then we determine the optimal age replacement time of the system which minimizes total maintenance cost. Numerical examples are shown to illustrate the result.