基于Renyi熵和K-medoids聚类的轴承性能退化评估

摘要
图/表
参考文献(28)
相关文章 (15)

全文: PDF (2119 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要滚动轴承性能退化评估是实现轴承剩余寿命预测和制定维修方案的基础，聚类分析作为数据挖掘的基本工具在故障评估中得到广泛应用。K-medoids聚类算法不易受极端数据影响，与隶属度函数相结合计算隶属度值作为故障指标可将故障程度大小表示在特定区间上，Renyi熵作为特征能很好地识别信号的微小变化。对滚动轴承振动信号进行小波包分解并降噪，将最优子带进行重构后计算Renyi熵，构成特征向量输入到K-medoids聚类模型中得到隶属度作为评价指标评估当前轴承性能状态，实现对故障的定量评估，同时设定自适应阈值确定早期故障出现时间。人工植入故障试验和全寿命疲劳试验分析表明该方法能有效评估故障程度大小且能及时发现早期故障的出现。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章

关键词 ：滚动轴承, Renyi熵, K-medoids, 性能退化

Abstract：Bearing performance degradation assessment (PDA) underlies residual useful life prediction and maintenance decision-making. In bearing fault diagnosis and PDA, a commonly used method is clustering analysis, among which the K-medoids clustering is not susceptible to extreme data. The amalgamation of the K-medoids clustering and a membership function are expected to give a health indicator with a determined value range for PDA. Vibration signals are first decomposed into multiple sub-bands on which a denoising algorithm is then applied, resulting in a series of denoised sub-band signals. The Renyi entropy is a nonlinear parameter able to identify subtle change in signals. As such, Renyi entropies of denoised sub-band signals constitute the feature vectors presented to the combined model of K-medoids based clustering and a membership function. Resultant health indicator was used to depict bearing health condition with the help of an adaptive threshold. Results on artificially induced faults and bearing run-to-failure data demonstrate that the proposed method is able to track the progress of bearing faults and detect them at incipient stage.

Key words： rolling bearing Renyi entropy K-medoids performance degradation

收稿日期: 2019-06-05 出版日期: 2020-10-15

引用本文:

张龙1，宋成洋1，邹友军1，洪闯1，王朝兵1,2. 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.
ZHANG Long1，SONG Chengyang1，ZOU Youjun1，HONG Chuang1，WANG Chaobing2. Bearing performance degradation assessment based on Renyi entropy and K-medoids clustering. JOURNAL OF VIBRATION AND SHOCK, 2020, 39(20): 24-31.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2020/V39/I20/24

[1] 胥永刚，孟志鹏，赵国亮. 基于双树复小波变换的轴承复合故障诊断研究[J]. 仪器仪表学报，2014， 35(02): 447-452.
XU Yong-gang, MENG Zhipeng, ZHAO Guoliang. Study on compomld falllt diagnosis of rolling bearing based on dual-tree complex wavelet transform[J]. Chinese Joumal of Scientmc Instmment. 2014, 35(02): 447-452.
[2] 曾庆虎，邱静，刘冠军，等. 基于小波相关滤波-包络分析的早期故障特征提取方法[J]. 仪器仪表学报，2008， 29(04): 729-733.
ZENG Qing-hu, QIU Jing, LIU Guanjun,et al. Approach to extraction of incipient fault features based on wavelet correlation filter and envelope analysis[J]. Chinese Journal of Scientific Instrument. 2008, 29 (04): 729-733.
[3] 李巍华，戴炳雄，张绍辉. 基于小波包熵和高斯混合模型的轴承性能退化评估[J]. 振动与冲击， 2013， 32(21): 35-40.
LI Wei-hua, DAI Bing-xiong, ZHANG Shao-hui. Bearing performance degradation assessment based on wavelet packet entropy and Gaussian mixture model[J]. Journal of Vibration and Shock, 2013, 32(21): 35-40.
[4] Hong S, Wang B, Li G, et al. Performance Degradation Assessment for Bearing Based on Ensemble Empirical Mode Decomposition and Gaussian Mixture Model[J]. Journal of Vibration & Acoustics, 2014, 136(6): 061006.
[5] 周建民，郭慧娟，张龙. 基于隐马尔科夫模型的滚动轴承性能退化评估[J]. 华东交通大学学报， 2017(04): 110-116.
ZHOU Jian-min, GUO Hui-juan, ZHANG Long, Evaluation of performance degradation of rolling bearings based on Hidden Markov model[J]. Journal of East China Jiaotong University, 2017(04): 110-116.
[6] 郭磊，李兴林，吴参，等. 基于支持向量机的滚动轴承性能退化评估方法[J]. 轴承， 2012(8): 46-50.
GUO Lei, LI Xing, WU Can,et al. Assessment Method for Performance Degradation of Rolling Bearings Based on SVM[J]. Bearing, 2012(8): 46-50.
[7] 姜万录，雷亚飞，韩可，等. 基于VMD和SVDD结合的滚动轴承性能退化程度定量评估[J]. 振动与冲击， 2018， 37(22): 43-50.
JIANG Wan-lu, LEI Ya-fei, HAN Ke,et al. Performance degradation quantitative assessment method for rolling bearings based on VMD and SVDD[J]. Journal of Vibration and Shock, 2018, 37(22): 43-50.
[8] 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.
[9] 周建民，郭慧娟，张龙. 一种融合型异常检测算法及其在轴承性能退化评估中的应用[J]. 制造技术与机床， 2017(10): 65-70.
ZHOU Jian-min, GUO Hui-juan, ZHANG Long. An anomaly detection algorithm of fusion type and its application in bearing performance degradation assessment[J]. Design and Research, 2017(10): 65-70.
[10] 夏均忠，吕麒鹏，陈成法，等. 基于JRD和CUSUM的滚动轴承性能退化状态识别与评估[J]. 振动与冲击， 2019， 38(2): 1-5.
XIA Jun-zhong, LU Qi-peng, CHEN Cheng-fa,et al. Performance degradation status identification and assessment of rolling element bearing based on the JRD and CUSUM[J]. Journal of Vibration and Shock, 2019, 38(2): 1-5.
[11] 潘楚，罗可. 基于改进粒计算的K-medoids聚类算法[J]. 计算机应用， 2014， 34(7): 1997-2000.
PAN Chu, LUO Ke. Improved K-medoids algorithm based on improved granular computing[J]. Joumal of Computer Applications, 2014, 34(7): 1997-2000.
[12] 高小梅，冯云，冯兴杰. 增量式K-Medoids聚类算法[J]. 计算机工程， 2005， 31(z1): 181-183.
GAO Xiao-mei, FENG Yun, FENG Xing-jie. Incremental Clustering Algorithm Based on K-Medoids[J]. Computer Engineering, 2005, 31(z1): 181-183.
[13] 何正嘉，袁静，柴艳阳. 机械故障诊断的内积变换原理与应用[M]. 北京: 科学出版社， 2012.
[14] G N N, A A I. Rolling element bearing fault diagnosis using wavelet packets[J]. Coal Mine Machinery, 2009, 3(35): 197-205.
[15] 钟孟春，张春林，李华，等. 改进的小波包能量分段阈值降噪方法[J]. 计算机工程与应用， 2015， 51(05): 204-207.
ZHONG Meng-chun, ZHANG Chun-lin, LI Hua,et al. Improved de-noising method based on wavelet packet energy subsection threshold. Computer Engineering and Applications, 2015, 51(05): 204-207.
[16] 马济通，邱天爽，李蓉，等. 脉冲噪声下基于Renyi熵的分数低阶双模盲均衡算法[J]. 电子与信息学报， 2018， 40(02): 378-385.
MA Ji-tong, QIU Tian-shuang, LI Rong,et al. Dual-mode blind equalization algorithm based on Renyi Entropy and Fractional Lower Order Statistics under impulsive noise. Journal of Electronics & Information Technology, 2018, 40(02): 378-385.
[17] Zyczkowski K. Renyi extrapolation of Shannon entropy[J]. Physics, 2003, 10(3): 297-310.
[18] Markel D, Zaidi H, El Naqa I. Novel multimodality segmentation using level sets and Jensen-Renyi divergence[J]. Medical Physics, 2013, 40(12): 121908.
[19] Kaufman L, Rousseeuw P J. Partitioning Around Medoids (Program PAM)[M]. Finding Groups in Data. Wiley-Blackwell, 2008.
[20] Bezdek J C. A Physical Interpretation of Fuzzy ISODATA[J]. IEEE Transactions on Systems Man & Cybernetics, 2007, 6(5): 387-389.
[21] Pal N R, Bezdek J C. On cluster validity for the fuzzy c-means model[J]. IEEE Transactions on Fuzzy Systems, 1995, 3(3): 370-379.
[22] 张龙，成俊良，李兴林，等. 基于自适应频带冲击强度的滚动轴承故障量化评估[J]. 振动与冲击， 2018， 37(19): 30-38.
ZHANG Long, CHENG Jun-liang, LI Xing-lin,et al. Fault quantitative evaluation of rolling bearings based on shock value of selected frequency band[J], Journal of Vibration and Shock, 2018, 37(19): 30-38.
[23] J. Lee, H. Qiu, G. Yu, J. Lin, and Rexnord Technical Services (2007). IMS, University of Cincinnati."Bearing Data Set", NASA Ames Prognostic Data Repository (http://ti.arc.nasa.gov/project/prognostic-data-repository), NASA Ames Research Center, Moffett Field, CA
[24] 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.
[25] 张龙，黄文艺，熊国良，等. 基于多域特征与高斯混合模型的滚动轴承性能退化评估[J]. 中国机械工程， 2014， 25(22): 3066-3072.
ZHANG Long, HUANG Wen-yi, XIONG Guo-liang,et al. Assessment of rolling bearing performance degradation using Gauss Mixture Model and Multui-domain Feature[J]. China Mechanical Engineering, 2014, 25(22): 3066-3072.
[26] 龙铭，文章，黄文艺，等. 滚动轴承故障程度评估的AR-GMM方法[J]. 机械科学与技术， 2016， 35(08): 1183-1188.
LONG Ming, WEN Zhang, HUANG Wen-yi,et al. Assessment of rolling bearing fault degree using AR-GMM[J]. Mechanical Science and Technology for Aerospace Engineering, 2016, 35(08): 1183-1188.
[27] Liao N H , Zhao N W , Guo N H . Predicting remaining useful life of an individual unit using proportional hazards model and logistic regression model[C]// Rams 06 Reliability & Maintainability Symposium. IEEE Computer Society, 2006.
[28] 张龙，熊国良，黄文艺. 复小波共振解调频带优化方法和新指标[J]. 机械工程学报， 2015(03): 129-138.
ZHANG Long, XIONG Guo-liang, HUANG Wen-yi. New Procedure and Index for the Parameter Optimization of Complex Wavelet Based Resonance Demodulation[J]. Journal of Mechanical Engineering, 2015(03): 129-138.