基于黎曼流形的轴承故障诊断方法  

Bearing Fault Diagnosis Method Based on Riemannian Manifold

作　　者：刘远红[1] 刘帆 李鑫[2] LIU Yuanhong;LIU Fan;LI Xin(School of Electrical Engineering and Information,Northeast University of Petroleum,Daqing 163318,China;No.3 Dilling Company,Daqing Dilling Engineering Company Limited,Daqing 163000,China)

机构地区：[1]东北石油大学电气信息工程学院,黑龙江大庆163318 [2]大庆钻探工程公司钻井三公司,黑龙江大庆163000

出　　处：《吉林大学学报（信息科学版）》2021年第5期546-552,共7页Journal of Jilin University（Information Science Edition）

摘　　要：为解决传统流形学习方法在轴承数据的非欧氏空间中特征提取时的不佳表现,提出引入黎曼流形学习方法。在黎曼流形的框架下,利用原始数据集构造出黎曼流形,并基于此流形提出了黎曼图嵌入特征提取方法,通过对局部结构编码实现初步降维。然后,在低维黎曼流形的基础上融合主成分分析算法(PCA:Principal Components Analysis)和线性判别分析算法(LDA:Linear Discriminant Analysis)设计分类器并对轴承数据进行了聚类。最后,通过在两个轴承数据集上的实验,分析了该方法提取特征的能力。实验结果表明,与现有的故障诊断方法相比,该方法具有较强的故障诊断能力。In order to solve the poor performance of traditional manifold learning method in feature extraction from non-Euclidean space of bearing data,a Riemann manifold learning method is proposed.Under the framework of Riemannian manifold,the Riemannian manifold is constructed by using the original data set,and based on this manifold,a Riemannian graph embedding feature extraction method is proposed.The preliminary dimensionality reduction is realized by coding the local structure.Then,based on the low-dimensional Riemannian manifold,a classifier is designed to cluster the bearing data by combining the principal component analysis algorithm(PCA:Principal Components Analysis)and the linear discriminant analysis algorithm(LDA:Linear Discriminant Analysis).Finally,the ability of this method to extract features is analyzed through experiments on two bearing data sets.Compared with the existing fault diagnosis methods,this algorithm has stronger fault diagnosis ability.

关 键 词：滚动轴承 故障诊断 流形学习 黎曼流形 特征提取 

分 类 号：TP23[自动化与计算机技术—检测技术与自动化装置]