基于案例推理的多故障诊断方法研究

Research on multiple faults diagnosis method based on case reasoning

在分析多故障模式特点的基础上,建立了面向多故障的案例知识库,并提出了一种基于二次检索策略的多故障诊断方法。采用基于权重隶属度的候选案例生成方法对案例库进行初步检索,有效地减少了候选案例的数量;通过灰色关联分析对案例相似度进行计算,获得最有可能发生的故障案例,避免了多故障组合爆炸所带来的大计算量问题。最后通过实例对所提出的方法进行了说明。

After analyzing the characteristics of multiple failure modes, established the case knowledge database for the multiple fault, and proposed a multiple faults diagnosis method based on the two-step case retrieval strategy. Employed the weight membership to generate the initial candidate cases, which reduced the number of candidate cases greatly. Subsequently, obtained the most probable fault case through the calculation of case similarity with the grey relational analysis, which avoided the problem of time-consuming computation resulting from the combination explosion of multiple faults. Finally, embedded an example in the description of the methodology for better understanding.