基于集合经验模式分解和K-奇异值分解字典学习的滚动轴承故障诊断

李继猛; 李铭; 姚希峰; 王慧; 于青文; 王向东

doi:10.3969/j.issn.1000-1158.2020.10.13

PDF(671 KB)

计量学报 ›› 2020, Vol. 41 ›› Issue (10) : 1260-1266. DOI: 10.3969/j.issn.1000-1158.2020.10.13

力学计量

基于集合经验模式分解和K-奇异值分解字典学习的滚动轴承故障诊断

李继猛,李铭,姚希峰,王慧,于青文,王向东

作者信息 +

Rolling Bearing Fault Diagnosis Based on Ensemble Empirical Mode Decomposition and K-Singular Value Decomposition Dictionary Learning

LI Ji-meng,LI Ming,YAO Xi-feng,WANG Hui,YU Qing-wen,WANG Xiang-dong

Author information +

文章历史 +

摘要

针对经典K-奇异值分解算法构造的字典中原子形态受噪声、谐波干扰影响,进而降低冲击故障特征提取精度的问题,提出了基于集合经验模式分解和K-奇异值分解字典学习的冲击特征提取方法。该方法首先利用集合经验模式分解与Hurst指数对振动信号进行预处理,剔除谐波干扰;其次,利用经典K-奇异值分解算法和预处理信号构造超完备字典;然后,利用K-均值聚类算法对字典中的原子进行筛选;最后,利用正交匹配追踪算法实现冲击故障特征的稀疏表示。实验分析和工程应用验证了所提方法的有效性和实用性。

Abstract

The morphology of atom in dictionary constructed by the K-singular value decomposition algorithm is affected by noise and harmonic interference, which reduces the extraction precision of the fault feature. To solve this problem, a method of impulse feature extraction based on ensemble empirical mode decomposition and K-singular value decomposition dictionary learning is proposed to realize the fault diagnosis of rolling bearing. Firstly, ensemble empirical mode decomposition and Hurst exponent are used to preprocess the vibration signal to remove the harmonic interference; Then, the preprocessed signal K-singular value decomposition algorithm is learned by K-singular value decomposition algorithm to construct the over-complete dictionary; Next, the dictionary is analyzed K-means clustering algorithm to remove the atoms with smaller kurtosis values; Finally, the orthogonal matching pursuit algorithm is used to realize the sparse representation of impulse fault features. Experiments analysis and engineer application verify the effectiveness and practicability of the proposed method.

导出引用

李继猛,李铭,姚希峰,王慧,于青文,王向东. 基于集合经验模式分解和K-奇异值分解字典学习的滚动轴承故障诊断[J]. 计量学报. 2020, 41(10): 1260-1266 https://doi.org/10.3969/j.issn.1000-1158.2020.10.13

LI Ji-meng,LI Ming,YAO Xi-feng,WANG Hui,YU Qing-wen,WANG Xiang-dong. Rolling Bearing Fault Diagnosis Based on Ensemble Empirical Mode Decomposition and K-Singular Value Decomposition Dictionary Learning[J]. Acta Metrologica Sinica. 2020, 41(10): 1260-1266 https://doi.org/10.3969/j.issn.1000-1158.2020.10.13

中图分类号： TB936 TB973

参考文献

［1］李继猛, 黄梦君, 谢平, 等. 同步压缩-交叉小波变换及滚动轴承故障特征增强［J］. 计量学报, 2018, 39(2): 237-241.
Li J M, Huang M J, Xie P, et al. Synchrosqueezing-cross wavelet transform and enhanced fault diagnosis of rolling bearing ［J］. [WTBX][STBX]Acta Metrologica Sinica[STBZ][WTBZ], 2018, 39(2): 237-241.
［2］Wang S B, Chen X F, Selesnick I W, et al. Matching synchrosqueezing transform: A useful tool for characterizing signals with fast varying instantaneous frequency and application to machine fault diagnosis ［J］. [WTBX][STBX]Mechanical Systems and Signal Processing[STBZ][WTBZ], 2018, 100: 242-288.
［3］时培明, 苏晓, 袁丹真, 等. 基于VMD和变尺度多稳随机共振的微弱故障信号特征提取方法［J］. 计量学报, 2018, 39(4): 515-520.
Shi P M, Su X, Yuan D Z, et al. A new feature extraction method of weak fault signal based on VMD and re-scaling multi-stable stochastic resonance ［J］. [WTBX][STBX]Acta Metrologica Sinica[STBZ][WTBZ], 2018, 39(4): 515-520.
［4］何志坚, 周志雄, 黄向明. 基于变分模态分解的关联维数及相关向量机的刀具磨损状态监测［J］. 计量学报, 2018, 39(2): 182-186.
He Z J, Zhou Z X, Huang X M. Tool Wear State Monitoring Based on Variational Mode Decomposition and Correlation Dimension and Relevance Vector Machine ［J］. [WTBX][STBX]Acta Metrologica Sinica[STBZ][WTBZ], 2018, 39(2): 182-186.
［5］李志农, 朱明, 褚福磊, 等. 基于经验小波变换的机械故障诊断方法研究［J］. 仪器仪表学报, 2014, 35(11): 2423-2432.
Li Z N, Zhu M, Chu F L, et al. Mechanical fault diagnosis method based on empirical wavelet transform ［J］. [WTBX][STBX]Chinese Journal of Scientific Instrument[STBZ][WTBZ], 2014, 35(11): 2423-2432.
［5］郑近德, 潘海洋, 潘紫微, 等. 自适应无参经验小波变换及其在转子故障诊断中的应用［J］. 中国机械工程, 2016, 27(16): 2218-2224.
Zheng J D, Pan H Y, Pan Z W, et al. Adaptive parameterless empirical wavelet transform and its applications to fault diagnosis of rotor system ［J］. [WTBX][STBX]China Mechanical Engineering[STBZ][WTBZ], 2016, 27(16): 2218-2224.
［6］汪朝海,蔡晋辉,曾九孙. 基于经验模态分解和主成分分析的滚动轴承故障诊断研究［J］. 计量学报, 2019, 40(6): 1077-1082.
Wang C H, Cai J H, Zeng J S. Research on Fault Diagnosis of Rolling Bearing Based on Empirical Mode Decomposition and Principal Component Analysis［J］. [WTBX][STBX]Acta Metrologica Sinica[STBZ][WTBZ], 2019, 40(6): 1077-1082.
［7］张晗, 杜朝辉, 方作为, 等. 基于稀疏分解理论的航空发动机轴承故障诊断［J］. 机械工程学报, 2015, 51(1): 97-105.
Zhang H, Du Z H, Fang Z W, et al. Sparse decomposition based aero-engines bearing fault diagnosis ［J］. [WTBX][STBX]Journal of Mechanical Engineering[STBZ][WTBZ], 2015, 51(1): 97-105.
［8］崔玲丽, 莫代一, 邬娜. 并联基追踪稀疏分解在齿轮箱弱故障诊断中的应用［J］. 仪器仪表学报, 2014, 35(11): 2633-2640.
Cui L L, Mo D Y, Wu N. Application of sparse signal decomposition using dual-BP in gear-box weak fault diagnosis ［J］. [WTBX][STBX]Chinese Journal of Scientific Instrument[STBZ][WTBZ], 2014, 35(11): 2633-2640.
［9］余发军, 周凤星, 严保康. 基于字典学习的轴承早期故障稀疏特征提取［J］. 振动与冲击, 2016, 35(6): 181-186.
Yu F J, Zhou F X, Yan B K. Bearing initial fault feature extraction via sparse representation based on dictionary learning ［J］. [WTBX][STBX]Journal of Vibration and Shock[STBZ][WTBZ], 2016, 35(6): 181-186.
［10］Aharon M, Elad M, Bruckstein A. K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation ［J］. [WTBX][STBX]IEEE Transactions on Signal Processing[STBZ][WTBZ], 2006, 54(11): 4311-4322.
［11］Yang B Y, Liu R N, Chen X F. Fault diagnosis for a wind turbine generator bearing via sparse representation and shift-invariant K-SVD ［J］. [WTBX][STBX]IEEE Transactions on Industrial Informatics[STBZ][WTBZ], 2017, 13(3): 1321-1331.
［12］张峻宁, 张培林, 华春蓉, 等. 改进K-SVD算法在曲轴轴承AE信号的去噪研究［J］. 振动与冲击, 2017(21): 157-163.
Zhang J N, Zhang P L, Hua C R, et al. Improved method for bearing AE signal denoising based on K-SVD algorithms ［J］. [WTBX][STBX]Journal of Vibration and Shock[STBZ][WTBZ], 2017(21): 157-163.
［13］Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis ［J］. [WTBX][STBX]Proceedings of the Royal Society A-mathematical Physical and Engineering Sciences[STBZ][WTBZ], 1998, 454(1971): 903-995.
［14］Wu Z, Huang N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method ［J］. [WTBX][STBX]Advances in Adaptive Data Analysis[STBZ][WTBZ], 2009, 1(1): 1-41.
［15］陈昭, 梁静溪. 赫斯特指数的分析与应用［J］. 中国软科学, 2005, (3):134-138.
Chen Z, Liang J X. The analysis and application of Hurst exponent ［J］. [WTBX][STBX]China Soft Science[STBZ][WTBZ], 2005, (3):134-138.
［16］周志华. 机器学习［M］. 北京: 清华大学出版社, 2016.
［17］付晓, 沈远彤, 付丽华, 等. 基于特征聚类的稀疏自编码快速算法［J］. 电子学报, 2018, 46 (5): 20-25.
Fu X, Shen Y T, Fu L H, et al. An optimized sparse autoencoder network based on feature clustering［J］. [WTBX][STBX]Acta Electronica Sinica[STBZ][WTBZ], 2018, 46 (5): 20-25.