Ezplicit Methods for Incorporating Bayesian Networks into Common Cause Analysis

摘要：

Two explicit methods for incorporating common cause failures (CCF) into reliability analysis based on Bayesian networks are proposed in this paper. CCF are multiple failures due to a common cause (CC) which tend to increase the system unreliability. Two traditional methods are often used for CCF analysis, explicit and implicit methods, both of which have shortcomings especially in handling large fault trees. Our methods provide accurate and efficient reliability analysis by incorporating Bayesian networks (BN) into CCF analysis, which could avoid the disadvantages of traditional methods. Complex dependencies among common causes, which could not be dealt with in traditional methods, can also be solved by properly modifying the Bayesian networks.

关键词： Bayesian networks common cause failures reliability analysis dependency analysis

作者: Zhongbao Zhou Shiying Pan Chaoqun Ma Haitao Li

作者单位: School of Business Administration, Hunan University, Changsha 410082, P.R. China Institute of Career Technology, Hebei Normal University, Shijiazhuang 050031, P.R. China School of Information System & Management, National University of Defense Technology,Changsha 410073

会议类型: 国际会议

会议名称: The First World Congress on Global Optimization in Engineering & Science(第一届工程与科学全局优化国际会议 WCGO2009)

会议地点: 长沙

会议语种:英文

页码: 1062-1070

在线出版日期: 2009-06-01（万方平台首次上网日期，不代表论文的发表时间）