基于ITD与稀疏编码收缩的滚动轴承故障特征提取方法

PDF(944 KB)

振动与冲击 ›› 2018, Vol. 37 ›› Issue (19) : 23-29.

论文

余建波1，刘海强1，郑小云1，周炳海1，程辉2，孙习武2

作者信息 +

Fault feature extraction method of rolling bearings based on ITD-SCS

Yu Jianbo1 Liu Haiqiang1 Zheng Xiaoyun1 Zhou Binhai1 Cheng Hui2 Sun Xiwu2

Author information +

文章历史 +

摘要

针对滚动轴承早期故障信号具有周期性冲击的特点和被强噪声淹没而难以提取的问题，本文提出了一种基于固有时间尺度分解（Intrinsic time scale decomposition, ITD）与稀疏编码收缩（Sparse coding shrinkage，SCS）集成的轴承故障特征提取方法（命名为ITD-SCS）。ITD能自适应地将振动信号分解成若干固有旋转分量(Proper rotation，PR)，选择有效的PR分量突显信号的冲击特征。进一步采用奇异值分解（Singular value decomposition, SVD）对每一有效PR实施滤噪作为SCS的前置滤噪单元以提高信号的稀疏性。最后，通过SCS利用极大似然估计方法提取合成信号中的冲击特征。将ITD-SCS应用于轴承内圈故障仿真信号和外圈实际故障振动信号的实验结果表明，ITD-SCS能有效提取强背景噪声下的轴承故障信号的冲击特征。

Abstract

Aiming at problems of early faults of rolling bearings having the feature of periodic impacts and very difficult to extract due to being submerged by strong noise, a new method for fault feature extraction of rolling bearings based on the time scale decomposition (ITD) and the sparse coding shrinkage (SCS) or ITD-SCS was proposed here.ITD could be used to adaptively decompose non-stationary and nonlinear vibration signals into several intrinsic rotation components or proper rotations (PRs), some of them were effectively selected to highlight impact features of original signals.Furthermore, the singular value decomposition (SVD) was used to perform noise-filtering for each effective PR, and SVD was taken as the pre-filtering noise unit of SCS to improve signals’ sparsity.Finally, SCS used the maximum likelihood estimation to extract impact features in synthetic signals.Numerical simulation results and testing ones for rolling bearings’ fault vibration signals showed that ITD-SCS method can be used to effectively extract impact features of bearing fault signals under strong background noise.

导出引用

余建波1，刘海强1，郑小云1，周炳海1，程辉2，孙习武2. 基于ITD与稀疏编码收缩的滚动轴承故障特征提取方法[J]. 振动与冲击, 2018, 37(19): 23-29

Yu Jianbo1 Liu Haiqiang1 Zheng Xiaoyun1 Zhou Binhai1 Cheng Hui2 Sun Xiwu2. Fault feature extraction method of rolling bearings based on ITD-SCS[J]. Journal of Vibration and Shock, 2018, 37(19): 23-29

参考文献

[1] 孙伟，熊邦书，黄建萍，等. 小波包降噪与LMD相结合的滚动轴承故障诊断方法[J]. 振动与冲击，2012, 31(18):153-156.
SUN Wei, XIONG Bangshu, HUANG Jianping, et al. Fault diagnosis of a rolling bearing using Wavelet packet de-noising and LMD [J]. Journal of Vibration and Shock, 2012, 31(18):153-156.
[2] YU J. Local and nonlocal preserving projection for bearing defect classification and performanc assessment [J]. IEEE Transactions on Industrial Electronics, 2012, 59(5): 2363-2376.
[3] The Mathworks Inc, Wavelet Toolbox User’s Guide-for Use with Matlab, 1999.
[4] 陶然，许有才，邓方华，等. 基于SVD优化LMD的电梯导靴振动信号故障特征提取[J]. 振动与冲击, 2017, 36(22): 25-.
TAO Ran, XU Youcai, DENG Fanghua1, et al. Feature extraction of the elevator guide shoe vibration signal based on SVD optimizing LMD [J]. Journal of Vibration and Shock, 2017, 36(22): 25-.
[5] 陈俊洵，程龙生，胡绍林，等. 基于EMD的改进马田系统的滚动轴承故障诊断[J]. 振动与冲击, 2017, 36(5): 151-156.
CHEN Junxun,CHENG Longsheng, HU Shaolin,et al. Fault diagnosis for rolling bearings using modified Mahalanobis–Taguchi system [J]. Journal of Vibration and Shock, 36(5): 151-156.
[6] 李舜酩, 郭海东, 李殿荣. 振动信号处理方法综述[J]. 仪器仪表学报, 2013, 34(8):1907-1915.
LI shunming, Guo Haidong, Li Dianrong. Review of vibration signal processing methods [J]. Chinese Journal of Scientific Instrument, 2013,34(8) :1907-1915.
[7] Frei M G, Osorio I. Intrinsic time-scale decomposition:time–frequency–energy analysis and real-time filtering of non-stationary signals[C] Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences. The Royal Society, 2007, 463(2078): 321-342.
[8] 罗颂荣，程军圣，杨宇. 基于本征时间尺度分解和变量预测模型模式识别的机械故障诊断[J]. 振动与冲击，2013, 32(13):43-48.
LUO Songrong, CHENG Junsheng, YANG Yu.Machine fault diagnosis method using ITD and variable predictive model-based class discrimination [J]. Journal of Vibration and Shock, 2013, 32(13):43-48.
[9] 杨宇，王欢欢，喻镇涛，等. 基于ITD改进算法和关联维数的转子故障诊断方法[J]. 振动与冲击， 2012, 31(23):67-70.
YANG Yu, WANG Huanhuan, YU Zhentao, et al. A rotor fault diagnosis method based on ITD improved algorithm and correlation dimension [J]. Journal of Vibration and Shock, 2012, 31(23):67-70.
[10] 张小龙, 张氢, 秦仙蓉,等. 基于ITD复杂度和PSO-SVM的滚动轴承故障诊断[J]. 振动与冲击, 2016, 35(24):102-107.
ZHANG Xiaolong, ZHANG Qing, QIN Xianrong, et al. Rolling bearing fault diagnosis based on ITD Lempel-Ziv complexity and PSO-SVM [J]. Journal of Vibration and Shock, 2016, 35(24):102-107.
[11] Hyvärinen A. Sparse Code Shrinkage: Denoising of Nongaussian Data by Maximum Likelihood Estimation[C]// Neural Computation. 1999:1739-1768.
[12] Yan Y, Kang G, Hong L. Image Denoising by Sparse Code Shrinkage[C]// International Conference on Wireless Communications, NETWORKING and Mobile Computing. IEEE, 2009:1-4.
[13] Fyfe K R, Zuo M J, Lin J. Mechanical Fault Detection Based on the Wavelet De-Noising Technique [J]. Journal of Vibration & Acoustics, 2004, 126(1):9-16.
[14] Wang X, Luo Z, Hu H, et al. Extraction of weak crack signals based on sparse code shrinkage combined with wavelet packet filtering [J]. Applied Acoustics, 2016, 112:53-58.
[15] 吴小涛, 杨锰, 袁晓辉,等. 基于峭度准则 EEMD 及改进形态滤波方法的轴承故障诊断[J]. 振动与冲击, 2015, 34(2):38-44.
WU Xiao-tao, YANG Meng, YUAN Xiao-hui, et al. Bearing fault diagnosis using EEMD and improved morphologicalfiltering method based on kurtosis criterion [J]. Journal of Vibration and Shock, 2015, 34(2):38-44.
SUN Jiedi, XIAO Qiyang, WEN Jiangtao, et al. Gas Pipeline Small Leak Aperture Classification Based on Local Mean Decomposition Envelope Spectrum Entropy and SVM [J]. Journal of Mechanical Engineering, 2014, 50 (20):18-25.
[16] Vidakovic B. Statistical Modeling by Wavelets / B. Vidakovic.[J]. John Wiley & Sons Inc New York, 1999.
[17] 赵学智，叶邦彦，陈统坚. 基于小波-奇异值分解差分谱的弱故障特征提取方法[J].机械工程学报, 2012,48(7):37-48.
ZHAO Xuezhi, YE Bangyan, CHEN Tongjian. Extraction Method of Faint Fault Feature Based on Wavelet-SVD Difference Spectrum [J]. Journal of Mechanical Engineering, 2012, 48 (7):37-48.
[18] SHAO R, HU W, LI J. Multi-fault feature extraction and diagnosis of gear transmission system using time-frequency analysis and wavelet threshold de-noising based on EMD [J]. Shock and Vibration, 2013, 20(4): 763-780.
[19] Han T, Jiang D, Wang N. The Fault Feature Extraction of Rolling Bearing Based on EMD and Difference Spectrum of Singular Value [J]. Shock & Vibration, 2016, 2016(13):1-14.