复杂机械系统故障分析模型研究

Research on Failure Analysis Model of Complex Mechanical System

将动态故障概率与面向对象贝叶斯网络(OOBN)相结合,在系统结构功能关系和故障模式影响分析(FMEA)的基础上,建立一种适合于复杂机械系统的动态面向对象贝叶斯网络(DOOBN)故障分析模型,该方法考虑了组件故障概率随时间的变化及组件可靠性退化对系统功能状态的影响,诊断模型具有层次性、动态性,利用该模型可以方便的对复杂系统进行故障传播的分析和关联故障的定位。在ISG-发动机上的应用表明该方法既可以简化系统的故障分析模型,又使模型描述更符合系统的实时状态。

Combining dynamic fault probability with object oriented Bayesian network（ OOBN）,we propose a fault diagnosis model based on dynamic object oriented Bayesian network（ DOOBN） with both the functional analysis and the failure mode effect analysis（ FMEA）. This methodology can adapt to construct fault diagnosis model of complex system. Considering the fault probability of component increases with the working time,the system function state is influenced by degradation of component reliability. This model is hierarchical and dynamic,it can be used to analyze failure propagation of,and it also facilitates the isolation of dependent failure. The proposed method was applied to ISG-engineand results suggest that this method can not only simplify the diagnosis model but also describe the actual state of the system.