损伤树分析方法中的关键问题研究

Research on key problems in damage tree analysis

研究了损伤定位快速性与底事件发生共因性这两个损伤树分析过程中的关键问题。针对损伤定位的快速性问题,研究了将贝叶斯网络应用于损伤树分析的可行性,通过建立事件与结点、逻辑门与联接强度之间的映射关系,实现了损伤树向贝叶斯网络的转化,依据网络信念更新原理进行快速损伤定位;针对底事件发生的共因性问题,通过设计装备战损仿真试验方案,根据战损试验数据计算装备各部件之间的损伤相关系数,据此合并相关性较大的底事件。最后通过实例介绍了这两项技术在损伤树分析中的应用情况。

The fast damage locating and bottom events occurring together are two key problems in the process of damage tree analysis. In order to solve the problem of fast damage locating, the feasibility of applying Bayesian networks to damage tree analysis is analyzed. The translation from damage tree to Bayesian networks is accomplished based on the event to node mapping and the logic gate to link intensity mapping. The fast damage locating is performed by the theory of network belief updating. In order to solve the problem of bottom events occurring together, the damage correlation coefficient between one part and another part is calculated according to the data that are obtained by the help of battlefield damage simulation experiments, and the bottomevents related to the biggish correlation coefficient constitute one bottom event. The application of the two methods in damage tree analysis is illustrated by an example.