摘要
针对电动机轴承早期故障信号非线性非平稳性特征,造成故障信号特征提取和故障诊断困难,提出一种改进的基于添加自适应白噪声的完备集合经验模态分解与支持向量机结合的电动机轴承故障诊断方法。将美国凯斯西储大学测得的电动机轴承正常运行、滚动针体故障、外圈故障、内圈故障共4种信号分别用CEEMDAN和EEMD进行分解,得到多个模式分量,再将IMF能量法计算得到的特征向量引入支持向量机,进行电动机轴承故障识别。试验对比研究表明,该方法能更有效进行电动机轴承早期故障识别。
Because the fault signal of the motor bearing has nonlinear and non-stationary characteristics,it is difficult to extract the fault signal feature and make the fault diagnosis. This paper puts forward a complete set of empirical mode decomposition based on adaptive add white noise improvement and support vector machine with its fault diagnosis method. The four types of signals of the motor bearing normal operation,rolling needle fault,outer and inner race faults measured by Case Western Reserve University are decomposed by CEEMDAN and EEMD to get multiple mode component,and then the feature vector is calculated by IMF energy method,which is introduced to the support vector machine for the fault diagnosis. Experimental result shows that this method can be used to effectively make the incipient fault diagnosis for the motor bearing.
引文
[1]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]. Proceeding of the Royal Society of London-Series A:Mathematical,Physical and Engineering Sciences,1998,454:903-995.
[2]Wu Z H,Huang N E. Ensemble empirical mode decomposition:A noise assisted data analysis method[J]. Advances in Adaptive Data Analysis,2009,1(1):1-41.
[3]张超,陈建军. EEMD算法和EMD方法抗模态混叠对比研究[J].振动与冲击,2010,29(增刊):87-90.
[4]卢珍.关于经验模态分解与整体经验模态分解的分离效果差别的探讨[J].科学技术与工程,2011(33):8353-8356.
[5]Torresm,Colominasm,Scholot Thauer G,et al. A complete ensemble empirical mode decomposition with adaptive noise[C]//Proceedings of the 2011 IEEE International Conference on Acoustics,Speech and Signal Processing. Piscataway,NJ:IEEEPress,2011:4144-4147
[6]M A Colominas,G Schlotthauer,M E Torres.Improved complete ensemble EMD:A suitable tool For biomedical signal processing[J]. Biomedical Signal Processing&Control,2014,14:19-29.
[7]张周锁,李凌均,何正嘉.基于支持向量机的多故障分类器及应用[J].机械科学与技术,2004,23(5):536-538.
[8]魏永合,王明华,林梦菊,等.基于改进EEMD的滚动轴承故障特征提取技术[J].组合机床与自动化加工技术,2015,(1):87-90.
[9] The case western reserve university bearing data center website.Bearing data center seeded fault test data[EB/OL].[2011-01-10]. http://www.eecs/cwru/edu/laboratory/bearing.