基于人工免疫与D-S证据理论的故障诊断方法

摘要

In order to solve the problem of basic probability assignment of D-S theory,a fault diagnosis method based on artificial immune system(AIS) and D-S theory is proposed.AIS is used to train classification model in fault spaces generated by sensors.The basic probability assignment can be obtained by immune recognition principle.The recognition radius of centre immune body and general immune body is designed to recognize the unknown samples.At last,D-S theory is used to fuse evidence and believe function is used for decision making.Numeric experiments show that the accuracy and speed of classification are improved,and this method is suitable for practical application.%针对使用信息融合技术进行故障诊断时,基本概率赋值难以确定的问题,提出一种基于人工免疫原理与D-S证据理论相结合的故障诊断方法.该方法使用无类标数据进行人工免疫聚类,构建每一个传感器的故障空间的分类模型,设计了中心抗体和一般抗体的识别半径对未知样本进行免疫识别,计算该样本在各故障分类器下的基本概率赋值,最后通过D-S证据理论将各基本故障概率赋值进行融合诊断,基于信任函数进行故障决策.试验结果表明该方法可以处理多信息源数据,提高了故障识别能力,有一定实践意义.