Purpose:To propose a new method for determining the membership functions of parameter estimates and the reliability functions of multi-parameter lifetime distributions.Summary:Reliability estimating methods are based on precise (crisp) lifetime data. The observed lifetime data are assumed to take precise real numbers. Owing to the lack, inaccuracy, and fluctuation of data, some collected lifetime data may be in the form of fuzzy values, necessitating to characterize estimation methods along a continuum, ranging from crisp to fuzzy. Bayesian methods are useful for small data samples. Bayesian reliability estimation based on fuzzy reliability data have not been widely reported and most of the reports deal with single-parameter lifetime distributions. This article proposes a new method for determining the membership functions of parameter estimates and the reliability functions of multi-parameter lifetime distributions. A preventive maintenance policy is formulated using a fuzzy reliability framework and an artificial neural network is used for parameter estimation, reliability prediction, and evaluation of the expected maintenance cost. A genetic algorithm is used to find the boundary values for the membership function of the estimate of interest at any cut level. (48 refs.)
展开▼
