Total variation on horizontal visibility graph and its application to rolling bearing fault diagnosis
Total variation on horizontal visibility graph and its application to rolling bearing fault diagnosis
复制标题
水平能见度图全变分及其在滚动轴承故障诊断中的应用
DOI：
10.1016/j.mechmachtheory.2019.103768
复制
发表时间：
2020-05-01
影响因子：
5.2
通讯作者：
Yu, Dejie
中科院分区：
文献类型：
--
作者：
Gao, Yiyuan;Yu, Dejie
图上的全变差（TVG）是一种度量图信号光滑性的强有力的顶点域指标，但其性能与底层图密切相关。由于水平可见度图比路径图更能反映轴承振动信号的动力学特性，因此将TVG的底层图指定为水平可见度图。本文定义了水平可见图上的顶点域指数TVG，简称为TVHVG。为了更好地区分滚动轴承的不同状态，将轴承振动信号转换为以其水平可见度图为索引的图形信号，并提取顶点域索引TVHVG作为单一故障特征。提出了一种基于TVHVG特征提取和马氏距离分类的滚动轴承故障诊断新方法。所提出的方法被应用于分析两组实验数据，包含正常和故障滚动轴承。结果表明，该方法能有效地诊断不同类型和程度的轴承故障，且在区分滚动轴承不同状态方面，顶点域指标TVHVG优于经典的时域指标上级。(C)2020爱思唯尔有限公司版权所有。
The total variation on graph (TVG) is a powerful vertex domain index for measuring the smoothness of graph signals, but its performance is closely related to the underlying graph. Since the horizontal visibility graph can better reflect the dynamics characteristics of bearing vibration signals than the path graph, the underlying graph of TVG is designated as horizontal visibility graph. The vertex domain index TVG defined on horizontal visibility graph is called simply as TVHVG in this paper. For better distinguishing the different states of rolling bearings, the bearing vibration signal is converted into the graph signal indexed by its horizontal visibility graph, and the vertex domain index TVHVG is extracted as the single fault feature. Based on TVHVG feature extraction and Mahalanobis distance classification, a novel fault diagnosis method for rolling bearings is proposed. The proposed method is applied to analyze two sets of experimental data containing normal and faulty rolling bearings. The results indicate that the proposed method can diagnose the bearing faults with different types and degrees effectively, and the vertex domain index TVHVG is superior to some classical time domain indexes in distinguishing the different states of rolling bearings. (C) 2020 Elsevier Ltd. All rights reserved.