Article ID: | iaor20082917 |
Country: | United Kingdom |
Volume: | 23 |
Issue: | 4 |
Start Page Number: | 359 |
End Page Number: | 371 |
Publication Date: | Jul 2007 |
Journal: | Applied Stochastic Models in Business and Industry |
Authors: | Frostig Esther, Kenzin Moshe |
Keywords: | probability, statistics: distributions, stochastic processes |
We examine the long-run average availability and cost rate of a maintained system which deteriorates according to a random-shock process. Shocks arrive according to a Poisson process. The system fails whenever the cumulative damage exceeds a given threshold. The system's failures are not self-announcing, hence, failures must be detected via inspections. The system is inspected at periodic or exponentially distributed intervals. Systems are replaced by preventive maintenance or after failure (corrective maintenance), whichever occurs first. When the distribution function of the shock magnitudes belongs to the class of subexponential distributions, we obtain simple approximations for the availability and the cost rate.