基于Bayes和Fiducial方法的指数分布区间估计

Exponential Distribution Interval Estimation Based on Bayes and Fiducial Methodology

在已知产品失效率不超过某个值的条件下,对定时截尾寿命试验,采用Bayes方法进行可靠性评估;对定数截尾寿命试验,采用参数受限制的Fiducial方法进行可靠性评估。根据这两种方法,分别给出了平均寿命单侧置信下限计算公式,同时讨论了先验分布参数的取值方法。最后,通过算例验证了这两种方法的有效性,算例表明两种方法均能够减少试验时间、提高可靠性评估精度。

In this paper, Bayes method is used to estimate the reliability of products subject to the fixed time life test and Fiducial method is used for products subject to the fixed failure number test when the failure rate of the products is known not to exceed some value. The calculation formulas of one-sided mean lifetime lower confidence limit for these two methods are given respectively. The determination of the prior distribution parameters is discussed. Finally, the validity of these two methods is demonstrated with some cases, and it is shown that they can reduce the test time and improve the accuracy of reliability estimation.