证据相关下的并发故障诊断方法

Simultaneous faults diagnosis under dependent evidence

基于Dezert-Smarandache理论(DSmT)给出了一种证据相关情况下的并发故障诊断方法.首先,结合并发故障的特点,给出了能够涵盖单发和并发故障的辨识框架,并介绍了适用于并发故障诊断的DSmT组合规则;然后,按照传感器、故障特征以及故障特征提取方法的不同,对证据的相关性进行了分类,并给出了证据解相关的方法;接着,应用DSmT组合规则对解相关后的证据进行组合,得到融合结果;最后,以多功能转子试验台的故障诊断为例验证了本文所提方法的有效性.

A method based on Dezert-Smarandache theory(DSmT) for simultaneous faults diagnosis when evidence is dependent was provided in this paper.Firstly,according to the characteristics of simultaneous faults,a frame of discernment was given for both single fault and simultaneous faults diagnosis,and the DSmT combination rule applicable to simultaneous faults diagnosis was introduced.Then,the dependence of evidence was classified according to three factors: sensors,types of fault features,methods for extracting of fault feature,and a method for evidence decorrelation was provided.Next,DSmT combination rule was used to aggregate the decorrelated evidence.Finally,an example of rotor faults diagnosis was given to illustrate the effectiveness of the proposed method.