无人机健康诊断知识库建立研究

Research on Building of UAV Health Diagnosis Knowledge Base

摘要:

针对无人机健康诊断系统的设计,研究了健康诊断专家知识库的建立方法；介绍了基于规则的专家知识库的含义及其对无人机设计的要求,阐述了故障树与故障模式判据表的形成方法；故障树分析基于故障因果逻辑,逐层找出故障事件的原因,保证专家知识逻辑上的完备性；故障模式判据表将抽象的专家知识具体化为多个能够在工程上应用的要素；提出了一种故障树分析与故障判据规则相结合的建立健康诊断专家知识库的方法；从某型大气数据系统的组成及原理出发,以大气数据系统真空速失效为顶事件,构造了故障树和故障模式判据表；结果表明,结合故障树和故障模式判据表格构造的专家知识库清晰、简洁,具有很高的工程实用价值,能够应用于无人机健康诊断系统的设计。

Abstract:

The way of building health diagnosis knowledge base is researched for designing health diagnosis system of UAV. The signification of expert knowledge base and its demand for UAV is introduced. The method building fault tree and criterion table of failure mode is explained. Fault tree analysis can ensure expert knowledge to be complete in logic by finding reasons of event layer-to-layer through cause-and-effect logic. Criterion table of failure mode translate expert knowledge to several elements that can be used in engineering. A method combining fault tree analysis with fault criterion rules is proposed to build health diagnosis knowledge base. The composition and principle of certain Air Data System are introduced. Then taking true airspeed failure of Air Data System as a top event, fault tree and criterion table of failure mode are constructed. The result indicated that expert knowledge base which is described through fault tree and criterion table of failure mode is clear and succinct. The method can apply to design health diagnosis system for UAV and has practical feasibility in engineering application.