Please use this identifier to cite or link to this item:
標題: An Availability System with General Repair Distribution: Statistical Inference
作者: Ke, J.C.
Su, Z.L.
Wang, K.H.
關鍵字: Hypothesis test;Imperfect coverage;Power function;Simulation;Standby;asymptotic confidence-limits;imperfect coverage;standby;time
Project: Communications in Statistics-Theory and Methods
期刊/報告no:: Communications in Statistics-Theory and Methods, Volume 38, Issue 9, Page(s) 1508-1525.
This article we study the statistical inferences of an availability system with imperfect coverage. The time-to-failure and time-to-repair of the active and standby components are assumed to be exponential and general distribution, respectively. Assume that the coverage factor is the same for an active-component failure as that for a standby-component failure. Firstly, we propose a consistent and asymptotically normal (CAN) estimator of availability for such repairable system. Based on the CAN estimator of the system availability, interval estimation and testing (hypothesis) are performed. To implement the simulation inference for the system availability, we adopt two repair-time distributions, such as lognormal and Weibull distribution, in which three types of Weibull distribution are considered according to the shape parameter . The component holds the decreasing repair rate (DRR), constant repair rate (CRR), and increasing repair rate (IRR) if 1, =1, and 1, respectively. Finally, all simulation results are displayed by appropriate tables and curves for understanding performance of the statistical inference procedures presented in this article.
ISSN: 0361-0926
DOI: 10.1080/03610920802455050
Appears in Collections:應用數學系所

Show full item record

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.