屏蔽数据下BurrXⅡ三部件串联系统的可靠性估计  

Reliability estimation for BurrXⅡ components in three-series system using masked data

作　　者：张萌[1] 师义民[1] 杨扬[1] 

机构地区：[1]西北工业大学应用数学系,陕西西安710129

出　　处：《系统工程与电子技术》2011年第1期222-227,共6页Systems Engineering and Electronics

基　　金：国家自然科学基金(70471057);陕西省教育厅自然科学基金(03JK065)资助课题

摘　　要：在系统失效原因被屏蔽的情形下,讨论三部件串联系统中BurrXⅡ部件的可靠性估计问题。在一般屏蔽情形下,利用迭代法和系统简化法求解极大似然方程组,得到部件参数近似的极大似然估计(maximum likeli-hood estimation,MLE);在完全屏蔽情形下,直接求解方程组得到参数精确的极大似然估计。同时利用贝叶斯方法分别在平方损失、LINEX损失以及熵损失下推导出部件参数和可靠性指标的贝叶斯估计。最后通过数值仿真说明极大似然估计和贝叶斯估计效果良好,并对二者进行了比较。The reliability estimation of components with BurrXⅡ distribution in the three-series system is investigated using masked system life data.Under general masked case,the approximate maximum likelihood estimation（MLE） of parameters is obtained by using iteration method and system simplify method to solve maximum likelihood equations,while the exact MLE is given under complete masked case.Meanwhile,the Bayes estimations of both parameters and reliabilities are obtained using squared error,LINEX and general entropy loss functions.Finally,numerical simulation results show that MLE and Bayes estimations both have a good performance,and a comparison is made between the two estimations.

关 键 词：屏蔽数据 三部件串联系统 BurrXⅡ分布 极大似然估计 贝叶斯估计 

分 类 号：O213.2[理学—概率论与数理统计]