量化特征关系用于不完备故障诊断的知识获取方法

Knowledge Discovery Method of Incomplete Fault Diagnosis Information via Valued Characteristic Relation

为了从包含多种未知属性值的不完备故障诊断信息中获取决策规则,提出一种量化特征关系用于不完备故障诊断的知识获取方法。首先,结合不完备故障诊断信息产生的原因,确定未知属性值的类型;然后,利用量化特征关系对不完备故障诊断信息进行分析;最后,利用量化特征关系下属性约简算法获取故障诊断决策规则。结合故障齿轮箱的诊断实例验证了该方法的有效性,结果表明此方法可以从包含三种未知属性值的不完备故障诊断决策表中直接获取准确的故障诊断决策规则。

In order to discover decision rules from incomplete fault diagnosis information containing multiple unknown attribute values, a knowledge discovery method of incomplete fault diagnosis information by using valued characteristic relation is proposed. Firstly, the unknown attribute value types are determined according to the reasons for incomplete information. Secondly, the incomplete fault diagnosis information is analyzed by using the valued characteristic relation. Finally, the decision rules for fault diagnosis are discovered according to the attribute reduction algorithm based on the valued characteristic relation. The effectiveness of the method is demonstrated with the diagnosis case of faulty gearbox. The experimental results show that the present method can directly discover the accurate decision rules from incomplete fault diagnosis information with three categories of unknown attribute values.