基于Copula函数的屏蔽数据并-串联系统可靠性分析  

Reliability Analysis for Parallel-Series System with Masked Data Based on Copula Theory

作　　者：蔡静 师义民[2] 白旭超[2] CAI Jing1,2, SHI Yi-min2, BAI Xiu-chao2(1. College of Data Science and Information Engineering, Guizhou Minzu University, Guiyang 550025, China） （2. Department of Applied Mathematics, Northwestern Polytechnical University, Xi＇an 710072, China)

机构地区：[1]贵州民族大学数据科学与信息工程学院,贵州贵阳550025 [2]西北工业大学应用数学系,陕西西安710072

出　　处：《数学的实践与认识》2018年第17期162-168,共7页Mathematics in Practice and Theory

基　　金：国家自然科学基金(71401134,71571144);贵州省科技计划项目([2016]1073,[2017]1085);陕西省自然科学基础研究计划项目(2015JM1003);教育部人文社会科学研究规划基金(17YJA630135);江西省教育厅基金(GJJ150516)

摘　　要：讨论了失效相依屏蔽数据系统的可靠性分析问题.通过引入Copula函数描述部件寿命变量之间的相依关系,建立屏蔽数据并-串联系统可靠性模型,推导出并-串联系统的一些概率结果.在此基础上,基于逐步Ⅰ型混合截尾的系统失效数据,获得了模型参数及可靠性指标的极大似然估计和bootstrap区间估计.最后,运用蒙特卡罗模拟验证了方法的可行性和有效性.This paper considers the statistical analysis of masked data in a parallel-series system with dependent components, which are linked by a Copula function. Based on type I progressive hybrid censored system lifetime data, we drive some probability results for the hybrid system and then the MLEs as well as the bootstrap confidence intervals of the unknown parameters and the reliability indexes are obtained. Finally, Monte Carlo simulations are employed to illustrate the feasibility and validity of the proposed method.

关 键 词：屏蔽数据 并-串联系统 COPULA函数 Bootstrap置信区间 

分 类 号：O213.2[理学—概率论与数理统计]