基于MEMD互近似熵及FCM聚类的轴承故障诊断方法

摘要/Abstract

摘要：

提出了一种基于掩蔽经验模式分解(MEMD)互近似熵及模糊C均值聚类(FCM)的滚动轴承故障诊断新方法。MEMD可以有效抑制经验模式分解存在的模态混叠问题；互近似熵是近似熵的改进，能更好体现信号的不规则度和复杂度。信号经掩蔽经验模式分解后得到一组平稳的本征模函数(IMF)，通过能量分析筛选出与原始信号最为相关的几个IMF分量，计算其互近似熵值以作为故障特征向量，能够直观体现设备的运行状况。故障模式识别采用的FCM算法，计算相对简单，聚类效果好。实验分析证明了该方法的优越性。

关键词: 故障诊断, 掩蔽经验模式分解, 互近似熵, 模糊C均值聚类

Abstract:

A new fault diagnosis method for rolling bearings was presented based on MEMD cApEn and FCM clustering herein. The MEMD method could restrain mode mixing of EMD effectively and the cApEn was the improvement of approximate entropy, which could express the more irregularity and complexity. Signals were decomposed by MEMD to obtain a set of stationary intrinsic mode function (IMF), and some IMF components that were most relevant to the original signals were sifted out by the energy analysis criterion. The cApEn values of every IMF components were calculated as fault feature vectors that could represent the operating conditions of equipment more intuitively. FCM algorithm was introduced to fault recognition, which could achieve well effect of clustering with easier calculation. The experiments and engineering analyses demonstrate the superiority of this method.

Key words: fault diagnosis, masking empirical mode decomposition(MEMD), cross approximate entropy(cApEn), fuzzy C-means(FCM) clustering

中图分类号:

TH17

张淑清, 胡永涛, 李盼, 包红燕, 姜万录, 钱磊. 基于MEMD互近似熵及FCM聚类的轴承故障诊断方法[J]. 中国机械工程, 2015, 26(19): 2613-2618.

Zhang Shuqing, Hu Yongtao, Li Pan, Bao Hongyan, Jiang Wanlu, Qian Lei. Fault Diagnosis Method for Bearings Based on MEMD Cross Approximate Entropy and FCM Clustering[J]. China Mechanical Engineering, 2015, 26(19): 2613-2618.

参考文献

[1]周帅. 基于时频分析的旋转机械故障诊断方法研究与应用[D]. 大连：大连理工大学，2012.
[2]艾树峰. 基于多尺度Hermitian小波包络谱的轴承故障诊断[J]. 中国机械工程，2012，23(1)：34-38.
Ai Shufeng. Bearing Fault Diagnosis Based on Multi-scale Hermitian Wavelet Envelop Spectrum[J]. China Mechanical Engineering，2012，23(1)：34-38.
[3]王金福，李富才. 机械故障诊断技术中的信号处理方法：时域分析[J]. 噪声与振动控制，2013，33(3)：128-132.
Wang Jinfu，Li Fucai. Review of Signal Processing Methods in Fault Diagnosis for Machinery[J]. Noise and Vibration Control，2013，33(3)：128-132.
[4]程军圣，郑近德，杨宇. 基于局部特征尺度分解的经验包络解调方法及其在机械故障诊断中的应用[J]. 机械工程学报，2012，48(19)：87-94.
Cheng Junshen，Zheng Jinde，Yang Yu. Empirical Envelope Demodulation Approach Based on Local Characteristic-scale Decomposition and Its applications to Mechanical Fault Diagnosis[J]. Journal of Mechanical Engineering，2012，48(19)：87-94.
[5]时培明，李庚，韩东颖. 基于改进EMD的旋转机械耦合故障诊断方法研究[J]. 中国机械工程，2013，24(17)：2367-2372.
Shi Peiming，Li Geng，Han Dongying. Study on Coupling Faults of Rotary Machinery Diagnosis Method Based on Improved EMD[J]. China Mechanical Engineering，2013，24(17)：2367-2372.
[6]Deering R，Kaiser J F. The Use of a Masking Signal to Improve Empirical Mode Decomposition[C]//IEEE International Conference on Acoustics，Speech，and Signal Processing. Philadelphia，2005：485-488.
[7]Andreadis I I，Giannakakis G A，Papageorgiou C，et al. Detecting Complexity Abnormalities in Dyslexia Measuring Approximate Entropy of Electronic Signals[C]//Engineering in Medicine and Biology Society, Annual International Conference of the IEEE. Minneapolis，2009：6292-6295.
[8]沈维蕾，赵韩，周蓉. 基于模糊聚类分析的控制图变点估计研究[J]. 中国机械工程，2012，23(23)：2835-2838.
Shen Weilei，Zhao Han，Zhou Rong. Research on Change-point Estimation of Control Charts Based on Fuzzy Clustering Approach[J]. China Mechanical Engineering，2012，23(23)：2835-2838.
[9]葛娟，李一兵，林云. 一种新的混合信号调制识别方法[J]. 弹箭与制导学报，2011，31(6)：183-186.
Ge Juan，Li Yibin，Lin Yun. A New Method for Modulation Recognition of Communication Signal[J]. Journal of Projectiles，Rockets，Missiles and Guidance，2011，31(6)：183-186.
[10]胡维平，莫家玲，杜明辉. 经验模态分解中的频域分辨率及其改进方法[J]. 华南理工大学学报(自然科学版)，2007，35(5)：15-19.
Hu Weiping，Mo Jialing，Du Minghui. Frequency-domain Resolution and Its Improvement During Empirical Mode Decomposition[J]. Journal of South China University of Technology (Natural Science Edition)，2007，35(5)：15-19.
[11]孙伟峰，彭玉华，杨阳，等. 经验模态分解频率分辨率的一种改进方法[J]. 计算机工程与应用，2010，46(1)：129-133.
Sun Weifeng，Peng Yuhua，Yang Yang，et al. Method for Improving Frequency Resolution of Empirical Mode Decomposition[J]. Computer Engineering and Applications，2010，46(1)：129-133.
[12]James E G，Molenaar P，Newell K M. Time Dependence of Coupling in Frequency-scaled Bimanual Coordination[J]. Neuroscience Letters，2011，490(2)：156-160.
[13]Zhao Nan，Li Xiaofeng，Yu Wenli，et al. ERP Instantaneous Synchronization Analysis Based on Cross Approximate Entropy[J]. Progress in Natural Science，2007，17：161-164.
[14]张淑清，孙国秀，李亮，等. 基于LMD近似熵和FCM聚类的机械故障诊断研究[J]. 仪器仪表学报，2013，34(3)：714-720.
Zhang Shuqing，Sun Guoxiu，Li Liang，et al. Study on Mechanical Fault Diagnosis Method Based on LMD Approximate Entropy and Fuzzy C-means Clustering[J]. Chinese Journal of Scientific Instrument，2013，34(3)：714-720.
[15]王雪，李宣平，戴逸翔. 多相水平集协同空间模糊聚类图像多目标分割[J]. 机械工程学报，2013，49(6)：89-94.
Wang Xue，Li Xuanping，Dai Yixiang. Multiphase Level Set-based Multi-objective Image Segmentation Cooperating with Spatial Fuzzy C-means[J]. Journal of Mechanical Engineering，2013，49(6)： 89-94.
[16]陈舵，李雪，崔杜武，等. 一种基于模糊度的聚类有效性函数[J]. 模式识别与人工智能，2008，21(1)：34-41.
Chen Duo，Li Xue，Cui Duwu，et al. Cluster Validity Function Based on Fuzzy Degree[J]. PR&AI，2008，21(1)：34-41.