Evaluation of multivariate normal integrals for general systems by sequential compounding
Evaluation of multivariate normal integrals for general systems by sequential compounding
复制标题
DOI：
10.1016/j.strusafe.2009.06.001
复制
发表时间：
2010
影响因子：
5.8
通讯作者：
W. Kang;Junho Song
中科院分区：
文献类型：
--
作者：
W. Kang;Junho Song
系统可靠性分析通常需要对多元正态积分进行高效且准确的评估。尽管系统可靠性分析方法最近取得了进展，但它仍然是一项具有挑战性的任务，特别是当系统事件的定义很复杂时；系统组件数量较多；和/或组成事件具有显着的统计依赖性。本文提出了一种新方法，用于评估为一般系统事件（包括串联、并联、割集和链接集系统）定义的多元正态积分。该方法将两个通过并集或交集耦合的组件顺序复合，直到系统成为单个复合事件。开发了有效的数值程序，用于在顺序复合的每个步骤中获得新复合事件的可靠性指数以及复合事件与其余组成事件之间的相关系数。通过数值算例证明了该方法的准确性和效率，及其对各种类型和大小的多元正态积分的适用性。
System reliability analysis often requires efficient and accurate evaluation of a multivariate normal integral. Despite recent advances in system reliability analysis methods, it is still a challenging task especially when the definition of the system event is complex; the system has a large number of components; and/or the component events have significant statistical dependence. This paper presents a new method developed for evaluating multivariate normal integrals defined for general system events including series, parallel, cut-set and link-set systems. The method compounds two components coupled by union or intersection sequentially until the system becomes a single compound event. Efficient numerical procedures are developed for obtaining the reliability index of the new compound event, and the correlation coefficients between the compound event and the remaining component events, at each step of the sequential compounding. The accuracy and efficiency of the proposed method, and its applicability to various types and sizes of multivariate normal integrals are demonstrated by numerical examples.