截尾情形下基于屏蔽数据的部件可靠性分析

Reliability analysis for the components under censoring test using masked data

当系统具有屏蔽寿命数据时,研究了串联系统中BurrXⅡ部件的可靠性估计问题.在定数截尾情形下,利用极大似然估计法及Bayes方法给出了部件参数、可靠度函数和失效率函数的极大似然估计及Bayes估计.最后通过随机模拟比较两种估计的效果,给出了工程应用时选择的依据;同时研究屏蔽水平和截尾数对估计效果的影响,结果表明估计的精度随着屏蔽水平的增大而降低,随着截尾数的增大而增高.

In this paper, the reliability estimations of components with BurrX II distribution in the series system using masked data are discussed. The maximum likelihood estimations （MLE） and Bayes estimations of the components＇ unknown parameters, reliability functions and failure rate functions are given by using maximum likelihood method and Bayes method. Finally, numerical simulation is introduced to compare these two estimations, the reference of selection for engineering application is given and the influence of masking level and the fixed number on the accuracy of the estimations is studied. The results show that the accuracy of the estimations decrease with increasing the masking level and increase with increasing the fixed number.