采用符号时间序列分析的轴承早期微弱故障预警

韦祥; 李本威; 张赟

doi:10.7652/xjtuxb201806013

您当前的位置：

首页 >

文章列表页 >

采用符号时间序列分析的轴承早期微弱故障预警

更新时间：2025-07-09

- 采用符号时间序列分析的轴承早期微弱故障预警
- A Warning Method for Early Weak Failures of Bearings by Symbolic Time Series Analysis
- 西安交通大学学报 2018年52卷第6期页码：84-90
- 作者机构：
  
  中国人民解放军海军航空大学航空基础学院,山东,烟台,264001
- 作者简介：
- 基金信息：
  
  : 2017-12-24。作者简介: 韦祥(1990—),男,博士生;李本威(通信作者),男,教授,博士生导师。基金项目: 国家自然科学基金资助项目(51505492);山东省泰山学者专项经费资助项目
- DOI：10.7652/xjtuxb201806013
  中图分类号： O322;TH133.33
- 网络首发：2018-06-10，
  
  纸质出版：2018
- 稿件说明：
移动端阅览
韦祥, 李本威, 张赟. 采用符号时间序列分析的轴承早期微弱故障预警[J]. 西安交通大学学报, 2018,52(6):84-90.

A Warning Method for Early Weak Failures of Bearings by Symbolic Time Series Analysis[J]. 2018, 52(6): 84-90.
韦祥, 李本威, 张赟. 采用符号时间序列分析的轴承早期微弱故障预警[J]. 西安交通大学学报, 2018,52(6):84-90. DOI： 10.7652/xjtuxb201806013.

A Warning Method for Early Weak Failures of Bearings by Symbolic Time Series Analysis[J]. 2018, 52(6): 84-90. DOI： 10.7652/xjtuxb201806013.

摘要

针对轴承早期磨损故障预警难的问题

提出了一种采用符号时间序列分析的轴承早期微弱故障预警方法。首先对轴承振动信号进行相空间重构

其次利用聚类的思想对相空间进行分割

对分割的子区间赋予唯一的符号

从而将振动信号转化为符号时间序列

最后通过Lempel-Ziv复杂度对符号时间序列进行定量分析。以Duffing方程为研究对象

验证了该方法对于动力学结构表征的精确性

表征精度可达95.85%; 与常规的符号时间序列分析方法相比

所提方法对动力学结构表征精度更高。利用该算法对于动力学结构变化的敏感性特点

将其应用于轴承状态监控中

试验结果显示算法可以发现轴承早期微弱磨损故障并实现全寿命性能衰退的监控。

Abstract

A warning method for early weak failures of bearings is proposed based on symbolic time series analysis to address the problem in early warning of weak faults in bearings. The phase space of bearing vibration signals is reconstructed using C-C method and then segmented by k-means clustering. Then each segmented subinterval is given an unique symbol and the bearing vibration signals are transformed into a symbolic time series. Finally

a quantitative analysis of the symbolic time series is carried out through the Lempel-Ziv complexity. The algorithm's accuracy of the representation of the dynamic structure is verified using the Duffing equation as the study object

and its precision is up to 95.85%. A comparison with the conventional symbolic time series analysis methods shows that the proposed method has a better accuracy. Since the proposed algorithm is sensitive to the dynamical changes

it is applied in the bearing state monitoring. Experimental results show that the algorithm can discover the early feeble wear-out failures of bearings and realizes the monitoring of whole life performance degradation.

关键词

Keywords

references

ALAMDARI M M, SAMALI B, LI J C. Damage localization based on symbolic time series analysis [J]. Structural Control and Health Monitoring, 2015, 22(2): 374-393.

张华, 曾文韬, 鄢威. 基于符号动力学信息熵与SVM的液压泵故障诊断 [J]. 振动测试与诊断, 2017, 37(2): 288-293.

ZHANG Hua, ZENG Wentao, YAN Wei. Fault diagnosis of hydraulic pump based on symbolic dynamic entropy and SVM [J]. Journal of Vibration, Measurement and Diagnosis, 2017, 37(2): 288-293.

SARKAR S, MUKHERJEE K, JIN Xin, et al. Optimization of symbolic feature extraction for pattern classification [J]. Signal Processing, 2012, 92(3): 625-635.

GUPTA S, RAY A, KELLER E. Symbolic time series analysis of ultrasonic data for early detection of fatigue damage [J]. Mechanical Systems and Signal Processing, 2007, 21(2): 866-884.

PARK J Y, KWON D. Detection of failure precursors in multilayer ceramic capacitors based on symbolic time series analysis [J]. Nanoscience and Nanotechnology Letters, 2016, 8(1): 75-80.

ANITA S A, NICHOLAS W. Symbolization of time-series: an evaluation of SAX, persist, and ACA [C]∥ 2011 4th International Congress on Image and Signal Processing. Piscataway, NJ, USA: IEEE, 2011: 2223-2228.

HOU Fengzhen, HUANG Xialin, CHEN Ying. Combination of equiprobable symbolization and time reversal asymmetry for heartbeat interval series analysis [J]. Physical Review: E Statistical, Nonlinear and Soft Matter Physics, 2013, 87(1): 012908.

GUERRA-FILHO G, ALOIMONOS Y. A language for human action [J]. Computer, 2007, 40(5): 42-51.

ZINNEN A, LAERHOVEN K V, SCHIELE B. Toward recognition of short and non-repetitive activities from wearable sensors [C]∥ European Conference on Ambient Intelligence. Berlin Germany: Springer-Verlag, 2007: 142-158.

SANT A A, WICKSTRO N. A symbol-based approach to gait analysis from acceleration signals: Identification and detection of gait events and a new measure of gait symmetry [J]. IEEE Transactions on Information Technology in Biomedicine, 2010, 14(5): 1180 -1187.

孟庆芳. 非线性动力系统时间序列分析方法及其应用研究 [D]. 济南: 山东大学, 2008: 21-22.

PACKARD N H, CRUTCHFIELD J P, FARMERS J D, et al. Geometry from a time series [J]. Phys Rev Lett, 1980, 45(9): 712-716.

TAKENS F. Reconstruction theory and nonlinear time series analysis [J]. Handbook of Dynamical Systems, 2010, 3(3): 347-377.

KIM H S, EYKHOLT R, SALAS J D. Nonlinear dynamics, delay times, and embedding windows [J]. Physical: D Nonlinear Phenomena, 1999, 127(1): 48-60.

陆振波, 蔡志明, 姜可宇. 基于改进的C-C方法的相空间重构参数选择 [J]. 系统仿真学报, 2007, 19(11): 2527-2538.

LU Zhenbo, CAI Zhiming, JIANG Keyu. Determination of embedding parameters for phase space reconstruction based on improved C-C method [J]. Journal of System Simulation, 2007, 19(11): 2527-2538.

李武, 赵娇燕, 严太山. 基于平均差异度优选初始聚类中心的改进k-均值聚类算法 [J]. 控制与决策. 2017, 32(4): 759-762.

LI Wu, ZHAO Jiaoyan, YAN Taishan. Improved k-均值聚类算法 [J]. 控制与决策. 2017, 32(4): 759-762.

LI Wu, ZHAO Jiaoyan, YAN Taishan. Improved ans clustering algorithm optimizing initial clustering centers based on average different degree [J]. Control and Dicesion, 2017, 32(4): 759-762.

QIU H, LEE J, LIN J, et al. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics [J]. Journal of Sound and Vibration, 2006, 289(4/5): 1066-1090.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

轴承结合部动态参数识别与等效分析模型的研究

往复式冰箱压缩机曲轴动态特性与轴承润滑计算分析

一种改进的局部倒频谱分析方法

一种采用相空间重构的多源数据融合方法

采用机器学习的大规模并行程序I/O性能建模与预测方法