机械基础工程

G-KSVD字典及其在滚动轴承故障信号稀疏表示中的应用

展开
  • 燕山大学电气工程学院,秦皇岛,066004
孟宗,男,1977年生,教授、博士研究生导师。研究方向为机械故障诊断、信号分析与处理。E-mail:mzysu@ysu.edu.cn。

收稿日期: 2020-08-17

  网络出版日期: 2021-08-14

基金资助

国家自然科学基金(52075470,61873227);河北省自然科学基金(E2019203448);中央引导地方科技发展基金(206Z4301G)

G-KSVD Dictionary and Its Applications in Sparse Representation of Rolling Bearing Fault Signals#br#

Expand
  • School of Electrical Engineering,Yanshan University,Qinhuangdao,Hebei,066004

Received date: 2020-08-17

  Online published: 2021-08-14

摘要

针对传统学习字典中缺少原子相干性分析的问题和最优原子选择问题,提出了一种基于有效奇异分量的G-K奇异值分解(G-KSVD)字典学习方法。基于信号相干性提出自相关函数脉冲能量比(ACFPER),并以此为指标对奇异分量进行筛选,实现信号的降噪,利用包含故障信息较多的分量对字典原子进行更新和系数求解,从而达到增强信号中冲击成分的目的,并通过减少反馈层来降低时间成本。利用仿真信号和实际轴承信号对所提方法进行有效性及重复性的验证,结果表明,G-KSVD算法在有效区间内具有良好的去噪效果和较低的时间成本。

本文引用格式

孟宗, 郜文清, 潘作舟, 张光雅, 樊凤杰 . G-KSVD字典及其在滚动轴承故障信号稀疏表示中的应用[J]. 中国机械工程, 2021 , 32(15) : 1776 -1785 . DOI: 10.3969/j.issn.1004-132X.2021.15.002

Abstract

For the lack of atomic coherence analysis and the lack of optimal atomic selection in the learning dictionary, a G-KSVD dictionary learning methods was proposed based on effective singular components herein. The method comprised the following steps. First, the ACFPER was proposed based on the coherence of the signals. The singular component was screened to achieve the signal denoising and the updating of the dictionary atom, and the solution of the coefficient were realized by using a component containing more fault information. Thus, the purpose of enhancing the impact components in the signals was achieved. Then the algorithm reduced the feedback layers in order to cut down the time cost. Last, the validity and repeatability of the proposed method were verified by using the simulation signals and the actual bearing signals. The results show that the G-KSVD algorithm has good denoising effectiveness in the idoneity interval, furthermore the time cost is low. 

参考文献

[1]GOLAFSHAN R, SANLITURK K Y. SVD and Hankel Matrix Based De-noising Approach for Ball Bearing Fault Detection and Its Assessment Using Artifificial Faults[J]. Mechanical Systems Signal Process, 2016, 70/71:36-50.
[2]WANG Jianhong, QIAO Liyan, YE Yongqiang, et al. Fractional Envelope Analysis for Rolling Element Bearing Weak Fault Feature Extraction[J]. IEEE/CAA Journal of Automatica Sinica, 2017, 4(2):353-360.
[3]HU Aijun, XIANG Ling, XU Sha, et al. Frequency Loss and Recovery in Rolling Bearing Fault Detection[J]. Chinese Journal of Mechanical Engineering, 2019, 32(2):145-156.
[4]李从志, 郑近德, 潘海洋, 等. 基于精细复合多尺度散布熵与支持向量机的滚动轴承故障诊断方法[J]. 中国机械工程, 2019, 30(14):1713-1719.
LI Congzhi, ZHENG Jinde, PAN Haiyang, et al. Fault Diagnosis Method for Rolling Bearing Based on Fine Composite Multi-scale Spreading Entropy and Support Vector Machine[J]. China Mechanical Engineering, 2019, 30(14):1713-1719.
[5]李继猛, 李铭, 王慧, 等. 基于相关正交匹配追踪算法的风电机组滚动轴承稀疏故障诊断方法[J]. 中国机械工程, 2018, 29(12):1428-1433.
LI Jimeng, LI Ming, WANG Hui, et al. Sparse Fault Diagnosis Method for Rolling Bearing of Wind Turbine Based on Correlation Orthogonal Matching Tracking Algorithm[J]. China Mechanical Engineering, 2018, 29(12):1428-1433.
[6]GUO Jinku, WU Jinying, YANG Xiaojun, et al. Ultrasonic Nondestructive Signals Processing Based on Matching Pursuit with Gabor Dictionary[J]. Chinese Journal of Mechanical Engineering, 2011, 24(4):591-595.
[7]郭俊锋, 李育亮. 基于学习字典的机器人图像稀疏表示方法[J]. 自动化学报, 2020, 46(4):820-830.
GUO Junfeng, LI Yuliang. Sparse Representation of Robot Images Based on Learning Dictionaries[J]. Automatic Chemical Reporting, 2020, 46(4):820-830.
[8]孙占龙, 佟庆彬. 基于ADMM字典学习的滚动轴承振动信号稀疏分解[J]. 中国机械工程, 2017, 28(3):310-315.
SUN Zhanlong, TONG Qingbin. Sparse Decomposition of Vibration Signals of Rolling Bearings Based on ADMM Dictionary Learning[J]. China Mechanical Engineering, 2017, 28(3):310-315.
[9]张文颢, 李永健, 张卫华. 基于K-奇异值分解和层次化分块正交匹配算法的滚动轴承故障诊断[J]. 中国机械工程, 2019, 30(4):406-412.
ZHANG Wenhao, LI Yongjian, ZHANG Weihua. Fault Diagnosis of Rolling Bearing Based on K-singular Value Decomposition and Hierarchical Block Orthogonal Matching Algorithm[J]. China Mechanical Engineering, 2019, 30(4):406-412.
[10]AHARON M, ElAD M, BRUCKSTEIN A. K-SVD:an Algorithm for Designing Overcomplete Dictionaries for Sparse Representation[J]. IEEE Transactions on Signal Processing, 2006, 54(11):4311-4322.
[11]YANG Boyuan, LIU Ruonan, CHEN Xuefeng. Fault Diagnosis for a Wind Turbine Generator Bearing via Sparse Representation and Shift-invariant K-SVD[J]. IEEE Transactions on Industrial Informatics, 2017, 13(3):1321-1331.
[12]LIN Huibin, DING Kang, YANG Honggang. Sliding Window Denoising K-Singular Value Decomposition and Its Application on Rolling Bearing Impact Fault Diagnosis[J]. Journal of Sound and Vibration, 2018, 421:205-219.
[13]乐友喜, 杨涛, 曾贤德. CEEMD与K-SVD字典训练相结合的去噪方法[J]. 石油地球物理勘探, 2019, 54(4):729-736.
LE Youxi, YANG Tao, ZENG Xiande. CEEMD and K-SVD Dictionary Training Combined Denoising Method[J]. Petroleum Geophysical Exploration, 2019, 54(4):729-736.
[14]QIN Yi, ZOU Jingqiang, TANG Baoping, et al. Transient Feature Extraction by the Improved Orthogonal Matching Pursuit and K-SVD Algorithm with Adaptive Transient Dictionary[J]. IEEE Transactions on Industrial Informatics, 2020, 16(1):215-227.
[15]SHAO Shuai, XU Rui, LIU Weifeng, et al. Label Embedded Dictionary Learning for Image Classification[J]. Neurocomputing, 2020, 385:122-131.
[16]HE Mengfu, ZHOU Youguang, LI Yang, et al. Long Short-term Memory Network with Multi-resolution Singular Value Decomposition for Prediction of Bearing Performance Degradation[J]. Measurement, 2020, 156:107582.
[17]ZHAO Xuezhi, YE Bangyan. Selection of Effective Singular Values Using Difference Spectrum and Its Application to Fault Diagnosis of Headstock[J]. Mechanical Systems & Signal Processing, 2011, 25(5):1617-1631.
[18]REZA G, KENAN Y S. SVD and Hankel Matrix Based De-noising Approach for Ball Bearing Fault Detection and Its Assessment Using Artificial Faults[J]. Mechanical Systems and Signal Processing, 2016, 70/71:36-50.
[19]LI Hua, LIU Tao, WU Xing, et al. Research on Bearing Fault Feature Extraction Based on Singular Value Decomposition and Optimized Frequency Band Entropy[J]. Mechanical Systems and Signal Processing, 2019, 118:477-502.
[20]ZHU Liya, SONG Huansheng, ZHANG Xi, et al. A Robust Meaningful Image Encryption Scheme Based on Block Compressive Sensing and SVD Embedding[J]. Signal Processing, 2020, 175:107926.
[21]陈伟. 一种有效的分段光滑信号逼近方法[J]. 电子学报, 2016, 44(8):2004-2008.
CHEN Wei. An Effective Segmental Smooth Signal Approximation Method[J]. Journal of Electronics, 2016, 44(8):2004-2008.
[22]ZHENG Kai, LI Tianliang, ZHANG Bin, et al. Incipient Fault Feature Extraction of Rolling Bearings Using Autocorrelation Function Impulse Harmonic to Noise Ratio Index Based SVD and Teager Energy Operator[J]. Applied Sciences, 2017, 7(11):1117.
[23]王霄, 谢平, 郭源耕, 等. 基于多字典共振稀疏分解的脉冲故障特征提取[J]. 中国机械工程, 2019, 30(20):2456-2462.
WANG Xiao, XIE Ping, GUO Yuangeng, et al. Pulse Fault Feature Extraction Based on Multi-dictionary Resonance Sparse Decomposition[J]. China Mechanical Engineering, 2019, 30(20):2456-2462.
[24]姜少飞, 邬天骥, 彭翔, 等. 基于XGBoost特征提取的数据驱动故障诊断方法[J]. 中国机械工程, 2020, 31(10):1232-1239.
JIANG Shaofei, WU Tianji, PENG Xiang, et al. Data Driven Fault Diagnosis Based on XGBoost Feature Extraction[J]. China Mechanical Engineering, 2020, 31(10):1232-1239.
[25]CHEN Dongyue, LIN Jianhui, LI Yanping. Modified Complementary Ensemble Empirical Mode Decomposition and Intrinsic Mode Functions Evaluation Index for High-speed Train Gearbox Fault Diagnosis[J]. Journal of Sound and Vibration, 2018, 424(23):192-207.
[26]PATRICIA H R, JESUS B A, MIGUEL A F, et al. Application of the Teager-Kaiser Energy Operator in Bearing Fault Diagnosis[J]. ISA Transactions, 2013, 52(2):278-284.
[27]李心一, 谢志江, 罗久飞. 加窗插值快速傅里叶变换在滚动轴承故障诊断中的应用[J]. 中国机械工程, 2018, 29(10):1166-1172.
LI Xinyi, XIE Zhijiang, LUO Jiufei. Application of Window Interpolation Fast Fourier Transform in Fault Diagnosis of Rolling Bearing[J]. China Mechanical Engineering, 2018, 29(10):1166-1172.
文章导航

/

〈 〉