摘要
为了提高复杂系统优化的效率、降低优化成本,提出一种基于多态多值决策图的多态故障树重要度计算方法:通过将不同事件转化为相应变量状态,实现了多态故障树分析向多态多值决策图的转化;基于多态多值决策图模型,给出了5步骤的重要度计算方法;通过集成重要度计算案例的分析对比验证了所提方法的正确性和有效性,并通过算法复杂度比较,证明了基于决策图的系统重要度计算方法比基于马氏贝叶斯网络方法的多态故障树的集成重要度计算方法效率更高。
To improve the optimization efficiency and reduce the optimization cost of complex system, an Integrated Importance Measures （IIM） method for Multi-state Fault Tree Analysis （MFTA） was developed based on Multi- state Multi-valued Decision Diagram （MMDD）. Through converting the different events into corresponding varia- bles, MFTA was transformed into MMDD. Based on MMDD model, five step integrated importance measure meth- od was given. Two case studies were implemented to demonstrate the effectiveness of presented method. The com- plexity analysis of cases showed that MMDD-based method was more computationally efficient than Markov Bayes- ian Networks-based method.
出处
《计算机集成制造系统》
EI
CSCD
北大核心
2015年第5期1301-1308,共8页
Computer Integrated Manufacturing Systems
基金
国家自然科学基金资助项目(71101116)
中央高校基本科研业务费专项资金资助项目(CHD2011TD015
0009-2014G1221016)~~
关键词
多态多值决策图
集成重要度
多态系统
多态故障树分析
复杂度分析
multi-state multi-valued decision diagram
integrated importance
multi-state system
multi-state fault tree analysis
complexity analysis
