Reliability assessment for systems suffering common cause failure based on Bayesian networks and proportional hazards model
Reliability assessment for systems suffering common cause failure based on Bayesian networks and proportional hazards model
复制标题
基于贝叶斯网络和比例风险模型的共因故障系统可靠性评估
DOI：
10.1002/qre.2713
复制
发表时间：
2020
影响因子：
2.3
通讯作者：
Mi Jinhua
中科院分区：
文献类型：
--
作者：
Li Yan-Feng;Liu Yang;Huang Tudi;Huang Hong-Zhong;Mi Jinhua
贝叶斯网络是一种有效的概率建模和因果推理工具，在可靠性评估领域得到了广泛的关注。共因失效是指系统中多个元件在共同原因下同时失效，是工程系统中元件间相互依赖的一种常见现象。针对复杂系统的CCF建模与评估，提出了几种模型和方法。本文针对动态环境下发生CCF的系统，提出了一种新的可靠性评估方法。组件之间的CCF的特征在于BN，其允许双向推理。采用比例风险模型来描述系统各部件的动态工作环境，从而得到系统的可靠度函数。通过一个示例验证了所提出的方法，并进行了比较研究。
The Bayesian network (BN) is an efficient tool for probabilistic modeling and causal inference, and it has gained considerable attentions in the field of reliability assessment. The common cause failure (CCF) is simultaneous failure of multiple elements in a system under a common cause, and it is a common phenomenon in engineering systems with dependent elements. Several models and methods have been proposed for modeling and assessment of complex systems with CCF. In this paper, a new reliability assessment method is proposed for the systems suffering from CCF in a dynamic environment. The CCF among components is characterized by a BN, which allows for bidirectional reasoning. A proportional hazards model is applied to capture the dynamic working environment of components and then the reliability function of the system is obtained. The proposed method is validated through an illustrative example, and some comparative studies are also presented.