摘要
本文讨论了当系统的强度和系统所受的应力服从独立的、不同的二项式指数2分布时系统的可靠性问题.采用了不同的方法来估计可靠性.在估计过程中使用了极大似然(ML)方法、基于Wilson-Hilferty(WH)的正态近似方法和贝叶斯方法.同时,基于正态近似方法、贝叶斯法和Bootstrap法(Boot-p和Boot-t)提出了应力–强度可靠度的置信区间.通过蒙特卡罗模拟比较了不同的方法和相应的置信区间.最后,给出了一个真实数据集的分析进行说明.
In this paper,the reliability of a system is discussed when the strength of the system and the stress imposed on it are independent,non-identical binomial exponential 2 distributed random variables.Different methods for estimating the reliability are applied.The maximum likelihood(ML),Wilson-Hilferty(WH)normal-based approximation and Bayesian methods are used in the estimation procedure.Also,we propose confidence intervals of the stress-strength reliability based on the approximate method,Bayesian method and Bootstrap methods(Boot-p and Boot-t).Different methods and the corresponding confidence intervals are compared using Monte-Carlo simulations.Finally,analysis of a real data set is presented for illustrative purposes.
作者
焦君君
程维虎
JIAO Junjun;CHENG Weihu(Faculty of Science,Beijing University of Technology,Beijing,100124,China;School of Mathematics and Statistics,Henan University of Science and Technology,Luoyang,471023,China)
出处
《应用概率统计》
CSCD
北大核心
2023年第2期178-196,共19页
Chinese Journal of Applied Probability and Statistics
关键词
二项指数2分布
应力强度可靠性
极大似然估计
WH正态近似
贝叶斯估计
binomial exponential 2 distribution
stress-strength reliabilty
maximum likelihood estimation
WH normal-based approximation
Bayesian estimation