基于ELMD的样本熵及Boosting-SVM的滚动轴承故障诊断

何志坚1,2,周志雄 1

振动与冲击 ›› 2016, Vol. 35 ›› Issue (18) : 190-195.

PDF(1907 KB)
PDF(1907 KB)
振动与冲击 ›› 2016, Vol. 35 ›› Issue (18) : 190-195.
论文

基于ELMD的样本熵及Boosting-SVM的滚动轴承故障诊断

  • 何志坚1,2 , 周志雄 1
作者信息 +

Fault diagnosis of roller bearing based on ELMD sample entropy and Boosting-SVM

  • HE Zhi-jian1,2  ZHOU Zhi-xiong1 
Author information +
文章历史 +

摘要

针对滚动轴承非平稳性的振动信号,本文提出了基于总体局域均值分解(Ensemble Local Mean Decomposition, ELMD)的样本熵及Boost-SVM的滚动轴承故障诊断方法。首先,对振动信号进行ELMD分解,获得一系列乘积函数(product function, PF);其次,根据分解特性提出基于K-L散度的自适应法选取主PF分量,计算主PF分量的样本熵并将其组合成特征向量;最后,将特征向量输入Boosting-SVM分类器进行训练与测试,从而识别滚动轴承的故障类型。实验结果表明,该方法能够有效的诊断出三种状态,且效果较局域均值分解方法好。

Abstract

Aiming at the no stationary characteristic of a gear fault vibration signal, it proposes a recognition method based on sample entropy of ELMD (Ensemble local mean decomposition) and Boosting-SVM. First, the vibration signal was decomposed by ELMD, then a series of product function were obtained; Secondly, according to the decomposition characteristics of ELMD, an adaptive method based on K-L divergence was proposed to select principal PFs, then, calculate the sample entropy of principal PF component and combined into a feature vector; Finally, the feature vector were input Boosting-SVM classifier to train and test to identify the type of roller bearing faults. Experimental results show that this method can effectively diagnosis three kinds of working condition, and the effect is better than local mean decomposition method.
 

关键词

滚动轴承 / 故障诊断 / 总体局域均值分解 / 样本熵

Key words

roller bearing / fault diagnosis / ensemble local mean decomposition / sample entropy

引用本文

导出引用
何志坚1,2,周志雄 1. 基于ELMD的样本熵及Boosting-SVM的滚动轴承故障诊断[J]. 振动与冲击, 2016, 35(18): 190-195
HE Zhi-jian1,2 ZHOU Zhi-xiong1 . Fault diagnosis of roller bearing based on ELMD sample entropy and Boosting-SVM[J]. Journal of Vibration and Shock, 2016, 35(18): 190-195

参考文献

[1] Lei Y G, Zuo M J. Fault diagnosis of rotating machinery using an improved HHT based on EEMD and sensitive IMFs [J]. Measurement Science and Technology, 2009, 20(12):1-12.
[2] 隋文涛,张丹,Wilson Wang.基于EMD和MKD的滚动轴承故障诊断[J].振动与冲击,2015,34(9):55-59.
SUI Wen-tao, ZHANG Dan, Wilson Wang. Fault diagnosis of rolling element bearings based on EMD and MKD [J]. Journal of Vibration and Shock, 2015, 34(9):55-59.
[3] 冯毅,曹劲然,路宝春,等. 基于连续峭度优化的滚动轴承故障特征提取小波变换方法[J].振动与冲击,2015,34(14):27-32.
FENG Yi, CAO Jin-ran, LU Bao-chun, et al. Fault feature extraction method for rolling bearing based on wavelet transform optimized by continuous kurtosis [J]. Journal of Vibration and Shock, 2015, 34(14):27-32.
[4] Smith JS. The local mean decomposition and its application to EEG perception data [J]. Journal of the Royal Society, 2005, 2(5):443-454.
[5] Sun J D, Xiao Q Y, Wen J T, et al. Natural gas pipeline small leakage feature extraction and recognition based on LMD envelope spectrum entropy and SVM [J]. Measurement, 2014, 55(9):434-443.
[6] Feng Z P, Zuo M J, Qu J, et al. Joint amplitude and frequency demodulation analysis based on local mean decomposition for fault diagnosis of planetary gearboxes [J]. Mechanical Systems and Signal Processing, 2013, 40(1):56-75.
[7] Sun J D, Xiao Q Y, Wen J T, et al. Natural gas leak location with K–L divergence-based adaptive selection of Ensemble Local Mean Decomposition components and high-order ambiguity function [J]. Journal of Sound and Vibration, 2015, 347:232-245.
[8] Lei Y G, He Z J, Zi Y Y. Application of the EEMD method to rotor fault diagnosis of rotating machinery [J]. Mechanical Systems and Signal Processing, 2009, 23(4):1327-1338.
[9] 周智,张优云,朱永生,等.基于EEMD 和共振解调的滚动轴承自适应故障诊断[J].振动与冲击,2013,32(2):76-80.
ZHOU Zhi, ZHANG You-yun, et al. Adaptive fault diagnosis of rolling bearings based on EEMD and demodulated resonance [J]. Journal of Shock and Vibration, 2013, 32(2):76-80.
[10] Wu Z H, Huang N E. A study of the characteristics of white noise using the empirical mode decomposition method [J]. Proceedings of the Royal Society of London.Series A: Mathematical, Physical and Engineering Sciences, 2004, 460(2046):1597-1611.
[11] Zhang F, Liu Y, Chen C, et al. Fault diagnosis of rotating machinery based on kernel density estimation and Kullback–Leibler divergence [J]. Journal of Mechanical Science and Technology, 2014, 11(28):4441-4454.
[12] Shapovalov M V, Dunbrack R L. A Smoothed Backbone-Dependent Rotamer Library for Proteins Derived from Adaptive Kernel Density Estimates and Regressions [J]. Structure, 2011, 19(6): 844-858.
[13] 苏文胜,王奉涛,朱泓,等. 基于小波包样本熵的滚动轴承故障特征提取[J]. 振动、测试与诊断,2011,31(2):162-166.
SU Wen-sheng, WANG Feng-tao, ZHU Hong, et al. Feature extraction of rolling element bearing fault using wavelet packet sample entropy[J]. Journal of Vibration, Measurement&Diagnosis, 2011, 31(2):162-166.
[14] Richman J S, Moorman R J. Physiological time-series analysis using approximate entropy and sample entropy [J]. J Physiol Heart Circ Physiol, 2000, 278(6):2039
[15] Wang C W, You W H. Boosting-SVM: effective learning with reduced data dimension [J]. Applied Intelligence, 2013, 39(3):465-474.

PDF(1907 KB)

Accesses

Citation

Detail

段落导航
相关文章

/