基于云模型与证据理论的故障诊断方法

A Fault Diagnosis Method Based on Cloud Theory and Evidential Theory

针对单一传感器无法对复杂设备进行故障诊断和证据理论难以合理获取BPA的问题,提出了一种基于云模型与证据理论的多传感器数据融合故障诊断方法;首先求取每个故障模型下各个特征参数的云模型参数,建立故障诊断云模型知识库;然后结合云模型知识库,求取各个测量参数的隶属度值,并转换为各个诊断证据体;最后通过证据理论组合规则将各个证据进行融合,在融合决策条件下求出诊断结果。实验结果表明,该方法能合理并有效地对复杂设备进行故障诊断。

Aiming to the problem of single sensor cannot make a fault diagnosis for complex equipment and evidence theory is difficult to make a reasonable BPA,the paper proposed a multi sensor data fusion fault diagnosis method based on cloud model and evidence theory.Firstly,taking the cloud model parameters of various characteristics under each fault model,and establishing the cloud model knowledge base for fault diagnosis; Then combining with the cloud model knowledge base to obtaining the membership values of various measurement parameters,and transform it as each diagnosis evidence; finally,all the evidence is fused by the combination rule of evidence theory,and the diagnosis results are obtained under the condition of fusion decision.Experimental results showthat the method is effective and accurate for the fault diagnosis of complex equipment.