基于案例推理的旋转机械故障诊断系统研究

Research of Rotating Machinery Fault Diagnosis System Based on Case-based Reasoning

针对大型旋转机械结构复杂,故障现象难以用结构化知识表示,故障诊断规则难以提炼的特点,将基于案例推理(CBR)方法应用于旋转机械故障诊断。从旋转机械故障诊断的需求出发,在分析旋转机械故障诊断知识特点的基础上,对故障诊断系统的总体结构、故障案例库的构建、案例相似度匹配、案例调整和学习等CBR方法的关键技术进行了研究。重点设计了故障案例表示方法,采用基于三标度的层次分析法(AHP)确定案例征兆权值。提出了改进的最近邻法计算案例相似度,可以从征兆名称、征兆值、权值三方面对案例进行精确匹配。提出了基于案例审核的学习机制,可以充分发挥不同人员的作用。开发了基于CBR的旋转机械故障诊断系统原型,并给出了应用实例。

Rotating machinery has the characteristics of complex structure, and their fault phenomena are diffi- cult to represent by structural knowledge. Because of this, the case-based reasoning（CBR） is applied to the fault diagnosis of rotating machinery. According to the requirement of fault diagnosis of rotating machinery, the key tech- niques of CBR, including the whole structure of fault diagnosis system, fault case base construction, case matching based on similarity, case adaptation and learning, are investigated. The case representation method is designed in detail. The analytic hierarchy process（AHP） based on three scale is used to calculate the attribute weight of each case. The improved nearest neighbor algorithm is proposed to calculate the similarity degree of cases, by which, cases are matched accurately based on attribute name, attribute value and weight. The prototype system is devel- oped and an application example is given.