基于MMFE和可拓k-medoids聚类的轴承性能退化评估

赵聪聪1,刘玉梅2,赵颖慧3,白杨4,施继红1

振动与冲击 ›› 2022, Vol. 41 ›› Issue (17) : 123-130.

PDF(2757 KB)
PDF(2757 KB)
振动与冲击 ›› 2022, Vol. 41 ›› Issue (17) : 123-130.
论文

基于MMFE和可拓k-medoids聚类的轴承性能退化评估

  • 赵聪聪1,刘玉梅2,赵颖慧3,白杨4,施继红1
作者信息 +

Evaluation of bearing performance degradation based on MMFE and extensible k-medoids clustering algorithm

  • ZHAO Congcong1, LIU Yumei2, ZHAO Yinghui3, BAI Yang4, SHI Jihong1
Author information +
文章历史 +

摘要

传统轴承性能退化评估常为定性分析,且多以垂向振动信号为对象,忽略了不同方向振动信息之间的相关性。本文将评价多通道时间序列复杂度的多元多尺度熵引入到轴承运行状态的特征提取,构建多元多尺度模糊熵特征来考虑轴承不同方向振动信息之间的关联性。结合k-medoids算法和可拓学理论建立了轴承性能退化的定量评估模型。通过对轴承正常状态样本进行k-medoids聚类得到聚类中心,根据样本点与聚类中心之间的欧式距离确定可拓集合的边界,进一步利用可拓关联函数构建轴承性能退化评估模型,并采用轴承全寿命疲劳试验进行了验证。试验结果表明,本文所提方法能有效识别轴承的早期性能退化,并能实现对轴承性能退化程度的定量评估。
关键词:轴承;性能退化;多元多尺度模糊熵;k-medoids算法;可拓学

Abstract

Traditional bearing performance degradation assessment methods usually makes qualitative analysis, and takes vertical signal of bearing as the research object, ignoring the correlationship between vibration signals in different directions. To resolve this problem, the multivariable multi-scale fuzzy entropy (MMFE) for evaluating the complexity of multi-channel time series was introduced into the feature extration of bearing operating state. Extenics and k-medoids clustering algorithm were combined to establish the bearing performance degradation evaluation model. By clustering the samples in bearing normal state with k-medoids algorithm, the clustering center of bearing normal state was obtained. According to the Euclidean distance between the tested samples and the normal state clustering center, the extension sets were determined. Furthermore, based on the extension correlation function, the quantitative assessment model of bearing performance degradation was established. The bearing whole life fatigue test was used to verify the effectiveness of the proposed method. The results show that the proposed method can detect the early performance degradation of bearing effectively, evaluate the bearing performance degradation quantitatively as well.
Key words: bearing; performance degradation; multivariable multi-scale fuzzy entropy; k-medoids algorithm; extenics

关键词

轴承 / 性能退化 / 多元多尺度模糊熵 / k-medoids算法 / 可拓学

Key words

bearing / performance degradation / multivariable multi-scale fuzzy entropy / k-medoids algorithm / extenics

引用本文

导出引用
赵聪聪1,刘玉梅2,赵颖慧3,白杨4,施继红1. 基于MMFE和可拓k-medoids聚类的轴承性能退化评估[J]. 振动与冲击, 2022, 41(17): 123-130
ZHAO Congcong1, LIU Yumei2, ZHAO Yinghui3, BAI Yang4, SHI Jihong1. Evaluation of bearing performance degradation based on MMFE and extensible k-medoids clustering algorithm[J]. Journal of Vibration and Shock, 2022, 41(17): 123-130

参考文献

[1] LIU Yu-mei,ZHAO Cong-cong,XIONG Ming-ye,et al.Assessment of bearing performance degradation via extension and EEMD combined approach[J].Journal of Central South University,2017,24(5):1155-1163.
[2] 王国彪,何正嘉,陈雪峰,等.机械故障诊断基础研究“何去何从”[J].机械工程学报,2013,49(1):63-72.
WANG Guo-biao,HE Zheng-jia,CHEN Xue-feng,et al.Basic research on machinery fault diagnosis-what is the prescription [J].Journal of Mechanical Engineering,2013,49(1):63-72.
[3] 池永为.滚动轴承故障的振动特性分析与智能诊断方法研究[D].杭州,浙江大学,2018.
[4] AHMED M U,MANDIC D P.Multivariate multiscale entropy analysis[J].Signal Processing Letters IEEE,2012,19(2):91-94.
[5] 李洪儒,于贺,田再克,等.基于二元多尺度熵的滚动轴承退化趋势预测[J].中国机械工程,2017,28(20):2420–2425 +2433.
LI Hong-ru,YU He,TIAN Zai-ke,et al. Degradation trend prediction of rolling beatings based on two-element multiscale entropy[J].China Mechanical Engineering,2017,28(20):2420-2425+2433.
[6] 易彩.高速列车轮对轴承状态表征与故障诊断方法研究[D].成都,西南交通大学,2015.
[7] Rai A,Upadhyay S H. Bearing performance degradation assessment based on a combination of empirical mode decomposition and K-medoids clustering[J].Mechanical Systems and Signal Processing,2017,93:16-29.
[8] 郑近德,潘海洋,张俊,等.基于多变量多尺度模糊熵的行星齿轮箱故障诊断[J].振动与冲击,2019,38(06):187-193.
ZHENG Jin-de,PAN Hai-yang,ZHANG Jun,et al. Multivariate multiscale fuzzy entropy based planetary gearbox fault diagnosis[J].Journal of Vibration and Shock,2019,38(06):187-193.
[9] PREET I,AROR A,DEEPAL I,et al. Analysis of K-Means and K-medoids algorithm for big data[J].Procedia Computer Science,2016,(78):507-512.
[10] 张龙,宋成洋,邹友军,等.基于Renyi熵和K-medoids聚类的轴承性能退化评估[J].振动与冲击,2020,39(20):24-31+46.
ZHANG Long,SONG Cheng-yang,ZHOU Youjun,et al.Bearing performance degradation assessment based on Renyi entropy and K-medoids clustering[J].Journal of Vibration and Shock,2020,39(20):24-31+46.
[11] 赵聪聪,赵颖慧,白杨,等.基于可拓学和SVDD的轴箱轴承故障监测[J].振动与冲击,2020,39(04):63-68.
ZHAO Cong-cong,ZHAO Ying-hui,BAI Yang,et al.Fault monitoring for axlebox bearing based on extenics and support vector data description[J].Journal of Vibration and Shock,2020,39(04):63-68.
[12] LEE J,QIU H,YU G,et al.Rexnord Technical Services(2007).IMS,University of Cincinnati.“Bearing Data Set”[OL].NASA Ames Prognostic Data Repository (http://ti.arc.nasa.gov/project/prognostic-data-repository),NASA Ames Research Center,Moffett Field,CA,2007.
[13] ZHENG Jin-de,CHENG Jun-sheng,YANG Yu,et al. A rolling bearing fault diagnosis method based on multi-scale fuzzy entropy and variable predictive model-based class discrimination[J].Mechanism and Machine Theory,2014,78(16):187-200.
[14] Detroja K P,Gudi R D,Patwardhan S C.Data reduction algorithm based on principle of distributional equivalence for fault diagnosis[J].Control Engineering Practice,2012,20(10):1033-1041.

PDF(2757 KB)

Accesses

Citation

Detail

段落导航
相关文章

/