基于EMD熵特征融合的滚动轴承故障诊断方法

向丹; 岑健

doi:10.13224/j.cnki.jasp.2015.05.016

基于EMD熵特征融合的滚动轴承故障诊断方法

doi: 10.13224/j.cnki.jasp.2015.05.016

向丹,
岑健

广东技术师范学院自动化学院, 广州 510635

基金项目:

广东省教育厅科技创新项目(2013KJCX0121)

广东优秀青年教师培养计划(Yq2013110)

广东省教育厅特色创新项目(自然科学类)(2014KTSCX146)

广东省自然科学基金(2014A030313639)

详细信息

作者简介:
向丹(1980-),女,湖北宜昌人,副教授,博士,主要从事控制工程、测试技术与自动化的研究.

中图分类号: V233;TH165.3
计量
- 文章访问数: 935
- HTML浏览量: 2
- PDF量: 784
- 被引次数: 0
出版历程
- 收稿日期: 2013-11-20
- 刊出日期: 2015-05-28

Method of roller bearing fault diagnosis based on feature fusion of EMD entropy

XIANG Dan,
CEN Jian

School of Automatization, Guangdong Polytechnic Normal University, Guangzhou 510635, China

摘要

摘要: 研究了滚动轴承故障诊断单一故障信号的局限性和故障特征的非线性,从信息融合的理论出发,利用非线性动力学参数熵作为特征,提出了基于经验模态分解(EMD)熵特征融合的方法来解决滚动轴承故障诊断问题.首先将原始信号进行EMD,利用EMD的自适应多分辨率的特点计算EMD得到的固有模态函数(IMF)信号的多种熵值,然后采用核主元分析(KPCA)对提取的状态特征进行信息融合,从而得到互补的特征,最后将提取的融合特征通过支持向量机(SVM)进行故障诊断.滚动轴承故障诊断实验表明:该方法结合了EMD、信息熵理论和KPCA强大的非线性处理能力的特点,可以进行滚动轴承故障诊断.
- 滚动轴承 /
- 故障诊断 /
- 熵 /
- 核主元分析 /
- 支持向量机
Abstract: The limitation of single fault signal for roller bearing fault diagnosis and nonlinear relation of fault features were studied. Starting from theory of information fusion, the method based on feature fusion of empirical mode decomposition (EMD) entropy was proposed using nonlinear dynamics parameters of entropy as features to deal with roller bearing fault diagnosis problem. Firstly, EMD was conducted for original signal, and on the basis of the property of adaptive multi-resolution for the EMD, different entropies of the intrinsic mode function (IMF) signal reconstructed by using the EMD were calculated. Secondly, the information fusion of the state features was further implemented by using the kernel principal component analysis (KPCA) to extract the complementary feature. Finally, the support vector machine (SVM) was employed to diagnose the fault by using the extracted fusion features. The experiment of rolling bearing fault diagnosis shows that the proposed method combines EMD, information entropy theory and strong nonlinear processing of KPAC, so it can be used for roller bearing fault diagnosis.
- roller bearing /
- fault diagnosis /
- entropy /
- kernel principal component analysis /
- support vector machine

HTML

参考文献(15)

[1]	Mclnerny S A, Dai Y.Basic vibration signal processing for bearing fault detection[J].IEEE Transactions on Education, 2003, 4(1):149-156.
[2]	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].Proceedings of The Royal Society A:Mathematical, Physical and Engineering Sciences, 1998, 454(1971):903-995.
[3]	YAN Ruqiang, GAO R X.Approximate entropy as a diagnostic tool for machine health monitoring[J].Mechancial Systems and Signal Processing, 2007, 21(2):824-839.
[4]	Pincus S M.Approximate entropy as a complexity measure[J].Chaos, 1995, 5(1):110-117.
[5]	于德介, 陈淼峰, 程军圣, 等.基于EMD的奇异值熵在转子系统故障诊断中的应用[J].振动与冲击, 2006, 25(2):24-26. YU Deje, CHEN Miaofeng, CHENG Junsheng, et al.Fault diagnosis approach for rotor system based on EMD method and singular value entropy[J].Journal of Vibration and Shock, 2006, 25(2):24-26.(in Chinese)
[6]	张超, 陈建军, 郭迅.基于EMD能量熵和支持向量机的齿轮故障诊断方法[J].振动与冲击, 2010, 29(10):216-219. ZHANG Chao, CHEN Jianjun, GUO Xun.Gear fault diagnosis method based on EMD energy entropy and SVM[J].Journal of Vibration and Shock, 2010, 29(10):216-219.(in Chinese)
[7]	张超, 陈建军, 郭迅.基于EEMD能量熵和支持向量机的齿轮故障诊断方法[J].中南大学学报, 2012, 43(3):932-939. ZHANG Chao, CHEN Jianjun, GUO Xun.Gear fault diagnosis method based on ensemble empirical mode decomposition energy entropy and support vector mechine[J].Journal of Central South University, 2012, 43(3):932-939.(in Chinese)
[8]	何柯峰, 高隽.一种基于主分量分析的融合识别方法[J].仪器仪表学报, 2004, 25(4):440-444. HE Kefeng, GAO Jun.A method of fusion recognition based on PCA[J].Chinese Journal of Scientific Instrument, 2004, 25(4):440-444.(in Chinese)
[9]	向丹, 葛爽.一种基于小波包样本熵和流形学习的故障特征提取模型[J].振动与冲击, 2014, 33(11):1-5. XIANG Dan, GE Shuang.A model of fault feature extraction based on wavelet packet sample entropy and manifold learning[J].Journal of Vibration and Shock, 2014, 33(11):1-5.(in Chinese)
[10]	Fegeant O.Closed form solutions for the point mobilities of axi-symmetrically excited cylindrical shells[J].Journal of Sound and Vibration, 2001, 243(1):89-115.
[11]	鞠萍华, 秦树人, 秦毅, 等.多分辨EMD方法与频域平均在齿轮早期故障诊断的研究[J].振动与冲击, 2009, 28(5):97-101. JU Pinghua, QIN Shuren, QIN Yi, et al.Study of the average in the early fault diagnosis of gear multiresolution and frequency domain EMD method[J].Journal of Vibration and Shock, 2009, 28(5):97-101.(in Chinese)
[12]	Scholkopf B, Smola A, Muller K R.Nonlinear component analysis as a kernel eigenvalue problem[J].Neural Computation, 1998, 10(5):1299-1319.
[13]	许洁, 胡寿涛.基于KPCA和MKL-SVM的非线性过程监控与故障诊断[J].仪器仪表学报, 2010, 31(11):2428-2433. XU Jie, HU Shoutao.Nonlinear process monitoring and fault diagnosis based on KPCA and MKL-SVM[J].Chinese Journal of Scientific Instrument, 2010, 31(11):2428-2433.(in Chinese)
[14]	向丹, 葛爽.基于样本熵和流形学习的故障特征提取方法[J].航空动力学报, 2014, 29(7):1535-1542. XIANG Dan, GE Shuang.Method of fault feature extraction based on EMD sample entropy and manifold learning[J].Journal of Aerospace Power, 2014, 29(7):1535-1542.(in Chinese)
[15]	张熠卓, 徐光华, 梁霖, 等.利用增量式非线性流形学习的状态监测方法[J].西安交通大学学报, 2011, 45(1):64-68.(in Chinese) ZHANG Yizhuo, XU Guanghua, LIANG Lin, et al.Condition monitoring method for mechanical equipments based on incremental nonlinear manifold learning[J].Journal of Xi'an Jiaotong University, 2011, 45(1):64-68.(in Chinese)