中文摘要：

针对故障知识获取这一瓶颈难题，对基于数据挖掘的数据库技术去实现故障知识规则自动发现的方法进行了研究；在SQLSERVER2005平台上，利用该平台提供的数据挖掘决策树算法，采用了将决策树算法与数据库系统的性能进行高效耦合的数据处理模式，建立了一种利用故障数据集自动获取故障知识规则的数据处理流程；最后利用转子故障实验获得的故障特征数据集进行的验证表明，该流程具有通过对故障数据集进行实时处理，自动建立起一种描述故障知识的决策树模型，并且通过对决策树枝进行结构元素的描述，可自动生成故障知识规则集合的功能；结果表明，SQLSERVER2005数据挖掘平台提供的决策树算法，为基于故障数据资源的驱动挖掘出故障知识提供了一种新途径。

英文摘要：

Knowledge acquisition is a bottleneck for the development of the fault diagnosis system. To solve the problem, a method to acquire fault knowledge based on data mining and database technology is proposed. An efficiency module of data process is built through the couple of decision tree and database on SQL SERVER2005. This process can acquire useful knowledge and diagnostic rule from the fault data base directly. Database of fault feature built with the fault simulation experiments on the rotor--bearing test rig is used to testify the method and the results show that the method can deal with the data in real time and build a decision tree module automatically. Knowledge and diag- nostic rule can be obtained through the description of the decision tree built above. The method provides a new approach for the data driven acquisition of fault knowledge.