Statistical inference for dependent stress–strength reliability of multi-state system using generalized survival signature
Statistical inference for dependent stress–strength reliability of multi-state system using generalized survival signature
复制标题
使用广义生存特征对多状态系统的依赖应力强度可靠性进行统计推断
DOI：
10.1016/j.cam.2020.113316
复制
发表时间：
2021
影响因子：
2.4
通讯作者：
Mu He
中科院分区：
文献类型：
--
作者：
Xuchao Bai;Xiangrong Li;Narayanaswamy Balakrishnan;Mu He
在应力-强度模型的可靠性分析中，通常假设个体只有一种强度。然而，在某些情况下，一个人，其中有几种类型的独立或依赖的优势，受到几种类型的独立应力在工作环境中。因此，我们定义了一个新的多状态应力-强度模型的多状态系统组成的n个多状态组件与几种类型的强度。在本文中，我们讨论了两种情况下，即，独立优势和依赖优势。在假设强度和应力变量均服从指数分布的基础上，导出了强度独立时系统在不同状态下的应力-强度可靠度的精确表达式。当强度依赖时，我们利用Gumbel Copula来描述强度的依赖结构。此外，两个半参数方法，即，矩量法和最大伪似然估计，用于估计的依赖参数。然后，分别给出了基于上述两种半参数方法的相依参数的极大似然估计、渐近置信区间估计和Bootstrap百分位数置信区间估计，用于不同状态下系统应力-强度可靠度的估计。蒙特卡罗模拟进行比较所提出的估计方法的性能。最后，一个真实的数据分析来说明所提出的程序。
In reliability analysis of the stress–strength models, it is generally assumed that an individual only has one type of strength. However, in some situation, an individual, which has several types of independent or dependent strengths, is subjected several types of independent stresses in the working environment. Hence, we define a new multi-state stress–strength model for multi-state system consisting of n multi-state components with several types of strengths. In this paper, we discuss inferential procedures for stress–strength reliability of such multi-state system using generalized survival signature in two cases, viz., independent strengths and dependent strengths. Based on the assumption that the strengths and stresses variables follow exponential distributions, the exact expressions for stress–strength reliability of system in different states are derived in case of independent strengths. When the strengths are dependent, we utilize the Gumbel copula to depict the dependence structure of strengths. Additionally, two semiparametric methods, viz., method-of-moment and maximum pseudo-likelihood estimation, are used to estimate the dependence parameter. Then, maximum likelihood estimation, asymptotic confidence interval estimation and bootstrap percentile confidence interval estimation based on the aforementioned two semiparametric methods for the dependence parameter are provided, separately, to estimate the stress–strength reliability of system in different states. Monte Carlo simulations are performed to compare the performances of the proposed estimation methods. Finally, a real data analysis is provided to illustrate the proposed procedures.