基于多标签学习的旋转机械分级复合故障诊断

Hierarchical compound fault diagnosis of rotating machinery based on multi-label learning

传统故障诊断方法大多是针对单一故障类型,然而在实际工业中多种故障会同时出现,即复合故障.针对复合故障诊断问题,一些学者引入多标签学习思想,多标签K近邻算法(ML-KNN)就是其中之一.然而ML-KNN算法作为一阶算法,只考虑标签与对应样本数据间的关系,却忽略了标签间的联系.针对该问题提出一种分级多标签学习算法,名为分层多标签K近邻算法(HML-KNN).HML-KNN算法将机械设备的退化阶段和故障类型分为两级,将第1级得到的标签信息进行转化,转化后的信息作为新特征放入第2级进行判断.HML-KNN算法是一种高阶算法,考虑了全局的标签信息,并在算法中包含了标签的特征转化,使得到的结果准确率更高.最后通过XJTU-SY数据集验证HML-KNN算法在处理复合故障诊断问题上的优越性.

Traditional fault diagnosis methods are mostly for a single fault type at one time,but in the actual industry,many kinds of faults will occur at the same time,that is compound fault.For the problem of compound fault diagnosis,some scholars have introduced the method of multi-label learning,and the multi-label K-nearest neighbor(ML-KNN)algorithm is one of them.However,as a first-order algorithm,the ML-KNN algorithm only considers the relationship between the label and the corresponding sample data,but ignores the relationship between the labels.In this study,a hierarchical multi-label learning algorithm is proposed,named hierachical multi-label K-nearest neighbor(HML-KNN).The HML-KNN algorithm categorizes the degradation state as the first level and fault type of machinery as the second level.The first level label information is transformed,and the transformed information is put into the second level as new features for judgment.The HML-KNN algorithm is a high-level algorithm that takes into account the global label information,and includes the feature conversion of the label,which makes the result more accurate.Through the verification on the XJTU-SY bearing data set,the superiority of the HML-KNN algorithm in dealing with compound fault diagnosis is demonstrated.