基于多尺度最优模糊熵的液压泵特征提取方法研究

PDF(1625 KB)

振动与冲击 ›› 2016, Vol. 35 ›› Issue (9) : 184-189.

论文

舒思材，韩东

作者信息 +

Approach of Hydraulic Pump’s Feature Extraction Based on Multiscale Optimal Fuzzy Entropy

SHU Si-cai，HAN Dong

Author information +

文章历史 +

摘要

为了更有效地提取液压泵振动信号的特征，在多尺度模糊熵(Multiscale Fuzzy Entropy MFE)的基础上，结合层次熵（Hierarchical Entropy HE）提出了基于多尺度最优模糊熵(Multiscale Optimal Fuzzy Entropy MOFE)的特征提取方法。基于多尺度模糊熵的特征提取方法是不够全面的，它仅仅分析了时间序列在各尺度上的均值成分，而非均值成分也应当被考虑在内。多尺度最优模糊熵通过引入层次熵的理论，首先，分析时间序列在不同尺度下的所有节点；其次，比较同尺度各节点的模式区分能力；然后，选取最能区分液压泵振动信号不同状态的节点为该尺度最优节点；最后，不同尺度下的最优节点模糊熵构成了对原时间序列的多尺度最优模糊熵分析。实验数据分析和比较结果验证了该方法的有效性。

Abstract

In order to extract features of hydraulic pump more effectively,a new approach based on MOFE combined with HE is proposed on the basement of MFE.Since there are inherent disadvantages for MFE,only averaging component in each scale is analyzed and other neglected ingredients should also be considered.By introducing of HE,MOFE make analysis of all nodes of time series in various scales.Furthermore,recognition ability for nodes in the same scale is compared and the one with optimun recognition is selected.Finally,fuzzy entropies of optimal nodes on all scale make up MOFE analysis for original time series.The proposed algorithm is verified by experimental data analysis and comparison.

导出引用

舒思材，韩东. 基于多尺度最优模糊熵的液压泵特征提取方法研究[J]. 振动与冲击, 2016, 35(9): 184-189

SHU Si-cai，HAN Dong. Approach of Hydraulic Pump’s Feature Extraction Based on Multiscale Optimal Fuzzy Entropy[J]. Journal of Vibration and Shock, 2016, 35(9): 184-189

参考文献

[1] 唐宏宾,吴运新,滑广军等. 基于EMD包络谱分析的液压泵故障诊断方法[J]. 振动与冲击,2012,31(9):44-48.
TANG Hong-bin,WU Yun-xin,HUA Guang-jun,et al. Fault
diagnosis of pump using EMD and envelope spectrum
analysis[J]. Journal of Vibration and
Shock,2012,31(9):44-48.
[2] Yang Y,Yu D J,Cheng J S. A roller bearing fault diagnosis method based on EMD energy entropy and ANN[J]. Journal of Sound and Vibration,2006,294(1-2):269-277.
[3] Pincus S M. Approximate entropy as a measure of system complexity[J]. Proceedings of the National Academy of Sciences,1991,88(6):2297-2301.
[4] Richman J S,Moorman J R. Physiological time series analysis using approximate entropy and sample entropy[J]. American Journal of Physiology-Heart and Circulatory Physiology,2000,278:2039-2049.
[5] 陈伟婷. 基于熵的表面肌电信号特征提取研究[D]. 上海:上海交通大学,2008.
CHEN Wei-ting. A study of feature extraction from SEMG signal based on entropy[D]. Shanghai:Shanghai Jiao Tong
University,2008.
[6] 郑近德,陈敏均,程军圣等. 多尺度模糊熵极其在滚动轴承故障诊断中的应用[J]. 振动工程学报,2014,27(1):145-151.
ZHENG Jin-de,CHEN Min-jun,CHENG Jun-sheng,et al. Multiscale fuzzy entropy and its application in rolling bearing fault diagnosis[J]. Journal of Vibration Engineering,2014,27(1):145-151.
[7] Jiang Y,Peng C K,Xu Y S. Hierarchical entropy analysis for biological signals[J]. Journal of Computational and Applied Mathematics,2011,236:728-742.