摘要
为提高在非平稳工况下对滚动轴承故障的直观辨识能力,笔者提出基于LMD-CM-PCA的故障诊断方法。首先,对滚动轴承振动信号进行局部均值分解(local mean decomposition,简称LMD),提取乘积函数(product function,简称PF)矩阵;然后,计算PF矩阵与原振动信号的皮氏相关系数(pearson product-moment correlation coefficient,简称PPCC),将PFs对应的PPCC代入相关熵模型得到PF的相关熵矩阵(correntropy matrix,简称CM),CM经主成分分析(principal component analysis,简称PCA)进行特征变换得到融合相关熵矩阵(integrated correntropy matrix,简称ICM)。分别在轻微和严重故障时,对滚动轴承不同工况下的振动样本进行交叉混合,并计算其ICM。结果证明,ICM在可视维度比传统特征(如:能量矩和谱峭度)的融合特征更能隔离工况对故障可分性的干扰。LMD-CM-PCA方法为滚动轴承故障的直观辨识提供了技术支持,在故障诊断方面具有良好的应用前景。
It is necessary to improve the visual robust fault identification ability of roller bearing in non-stationary operating condition.To achieve it,LMD-CM-PCA approach was proposed.First,based on roller bearing vibration acceleration signals,local mean decomposition(LMD)was applied to extract product function(PF)sample matrix.Second,the discrete correntropy and Pearson product-moment correlation coefficient(PPCC)of PF and primary signal were calculated.Correntropy was modified by PPCC as the amplitude modulation(AM)of correntropy.Then,the correntropy matrix(CM)of the samples was constructed with AM-correntropy being itselements.Finally,principal component analysis(PCA)was employed to implement the integration of CM with the largest variance accumulated contribution rate as the evaluation index.Integrated CM(ICM)of vibration datum under mixed operating conditions was calculated in slight fault and serious fault situations both.The visual results indicated that ICM could isolate operat-ing condition better and separate faults under different fault severity levels more robustly than traditional characteristics,such as energy moment and spectral kurtosis,do.Above all,application of ICM,like roller bearing fault features provides more effective technical support for roller bearing fault intuitively diagnosis so that it can support applications in fault diagnosis and safety early warning fields.
引文
[1]Chen Fafa,Tang Baoping,Song Tao,et al.Multifault diagnosis study on roller bearing based on multikernel support vector machine with chaotic particle swarm optimization[J].Measurement,2014,47(1):576-590.
[2]Bin Guangfu,Gao Jinji,Li Xuejun,et al.Early fault diagnosis of rotating machinery based on wavelet packets—empirical mode decomposition feature extraction and neural network[J].Mechanical Systems and Signal Processing,2012,27:696-711.
[3]郑近德,潘海洋,张俊,等.APEEMD及其在碰摩故障诊断中的应用[J].振动、测试与诊断,2016,36(2):257-263.Zheng Jinde,Pan Haiyang,Zhang Jun,et al.Adaptive partly ensemble empirical mode decomposition and its application for rotor rubbing fault diagnosis[J].Journal of Vibration,Measurement&Diagnosis,2016,36(2):257-263.(in Chinese)
[4]Han Minghong,Pan Jiali.A fault diagnosis method combined with LMD,sample entropy and energy ratio for roller bearings[J].Measurement,2015,76:7-19.
[5]Henr′iquez P,Alonso J B,Ferrer M A,et al.Review of automatic fault diagnosis systems using audio and vibration signals[J].IEEE Transactions on Systems Man and Cybernetics:Systems,2014,44(5):642-652.
[6]张云强,张培林,吴定海,等.基于CSLBP的轴承信号时频特征提取方法[J].振动、测试与诊断,2016,36(1):22-27.Zhang Yunqiang,Zhang Peilin,Wu Dinghai,et al.Time-frequency feature extraction method based on cslbp for bearing signals[J].Journal of Vibration,Measurement&Diagnosis,2016,36(1):22-27.(in Chinese)
[7]付云骁,贾利民,季常煦,等.基于多维振动特征的滚动轴承故障诊断方法[J].噪声与振动控制,2014,34(3):165-169.Fu Yunxiao,Jia Limin,Ji Changxu,et al.Fault diagnosis method of rolling bearings based on multi-dimensional vibration features[J].Noise and Vibration Control,2014,34(3):165-169.(in Chinese)
[8]王奉涛,陈守海,闫达文,等.基于流形-奇异值熵的滚动轴承故障特征提取[J].振动、测试与诊断,2016,36(2):288-294.Wang Fengtao,Chen Shouhai,Yan Dawen.et al.Fault feature extraction method for rolling bearing based on manifold and singular values entropy[J].Journal of Vibration,Measurement&Diagnosis,2016,36(2):288-294.(in Chinese)
[9]Santamaria I,Pokharel P P,Principe J C.Generalized correlation function:definition,properties,and application to blind equalization[J].IEEE Transactions on Signal Processing,2006,54(6):2187-2197.
[10]Hassan M,Terrien J,Marque C,et al.Comparison between approximate entropy,correntropy and time reversibility:application to uterine electromyogram signals[J].Medical Engineering&Physics,2011,33(8):980-986.
[11]付云骁,贾利民,秦勇,等.基于乘积函数相关熵的滚动轴承故障辨识方法[J].应用基础与工程科学学报,2016,24(2):333-343.Fu Yunxiao,Jia Limin,Qin Yong,et al.Roller element bearing fault identification method based on product function correntropy[J].Journal of Basic Science and Engineering,2016,24(2):333-343.(in Chinese)
[12]李巍华,林龙,单外平.基于广义S变换与双向2DPCA的轴承故障诊断[J].振动、测试与诊断,2015,35(3):499-506.Li Weihua,Lin Long,Shan Waiping.Bearing fault diagnosis based on generalized S-Transform and directional 2DPCA[J].Journal of Vibration,Measurement&Diagnosis,2015,35(3):499-506.(in Chinese)
[13]Wang Yanxue,Xiang Jiawei,Markert R,et al.Spectral kurtosis for fault detection,diagnosis and prognostics of rotating machines:A review with applications[J].Mechanical System and Signal Processing,2015,66-67:679-698.