摘要
为充分挖掘未标记样本所蕴含的有效信息,进而提升诊断精度,研究提出一种基于变分模态分解(VMD)散布熵与改进灰狼优化支持向量数据描述(SVDD)的轴承半监督故障诊断方法。首先采用中心频率观察法确定VMD分解模态参数K,进而将原始信号分解为一系列本征模态函数并计算各分量的散布熵值,构成测试样本和部分标记的训练样本;再由半监督模糊C均值(SSFCM)聚类对训练样本进行聚类分析,从而对所得聚类簇进行SVDD建模,同时采用k近邻准则进行决策优化,并由所提自适应变异灰狼算法优化SVDD模型参数;最后将基于最优参数训练的改进决策SVDD模型用于测试样本的故障模式识别。试验分析和对比结果表明,所提方法具有较好的诊断性能。
Abstract
To fully explore the effective information contained in unlabeled samples which can contribute to improve the diagnostic accuracy, a semi-supervised fault diagnosis method for bearings was proposed based on the variational mode decomposition (VMD) dispersion entropy and improved support vector data description (SVDD) with modified grey wolf optimizer. The central frequency observation method was applied to determine the mode number K of VMD, thus the original signal was decomposed into a set of intrinsic mode functions. The dispersion entropy values of all components were calculated to construct testing samples and partly labeled training samples. Then, the training samples were clustered by semi-supervised fuzzy C means clustering (SSFCM), after which the obtained clusters were modeled by SVDD. Meanwhile, the k nearest neighbor criterion was employed to improve the decision strategy, and the proposed adaptive mutation grey wolf optimizer was applied to optimize the parameters of SVDD. Finally, SVDD models based on optimal parameters were trained and utilized to recognize the fault pattern of testing samples. The experimental analysis and comparison illustrate that the proposed method achieves superior diagnostic performance.
关键词
变分模态分解 /
散布熵 /
支持向量数据描述 /
自适应变异灰狼算法 /
半监督模糊C均值 /
故障诊断
{{custom_keyword}} /
Key words
variational mode decomposition /
dispersion entropy /
support vector data description /
adaptive mutation grey wolf optimizer /
semi-supervised fuzzy C means clustering /
fault diagnosis
{{custom_keyword}} /
付文龙1,2,谭佳文1,2,王凯1,2.
基于VMD散布熵与改进灰狼优化SVDD的轴承半监督故障诊断研究[J]. 振动与冲击, 2019, 38(22): 190-197
FU Wenlong1,2,TAN Jiawen1,2,WANG Kai1,2.
Semi-supervised fault diagnosis of bearings based on the VMD dispersion entropy and improved SVDD with modified grey wolf optimizer#br#[J]. Journal of Vibration and Shock, 2019, 38(22): 190-197
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 武英杰,辛红伟,王建国,等.基于VMD滤波和极值点包络阶次的滚动轴承故障诊断 [J].振动与冲击,2018,37(14): 102-107.
WU Yingjie,XIN Hongwei,WANG Jianguo,et al.Rolling bearing fault diagnosis based on the variational mode decomposition filtering and extreme point envelope order [J].Journal of Vibration and Shock,2018,37(14): 102-107.
[2] 程军圣,王健,桂林.改进的EEMD方法及其在滚动轴承故障诊断中的应用 [J].振动与冲击,2018,37(16): 51-56.
CHENG Junsheng,WANG Jian,GUI Lin.An improved EEMD method and its application in rolling bearing fault diagnosis [J].Journal of Vibration and Shock,2018,37(16): 51-56.
[3] Kankar P K,Sharma S C,Harsha S P.Rolling element bearing fault diagnosis using wavelet transform [J].Neurocomputing,2011,74(10): 1638-1645.
[4] 时培明,丁雪娟,李庚,等.一种EMD改进方法及其在旋转机械故障诊断中的应用 [J].振动与冲击,2013,32(4) : 185-190.
SHI Peiming,DING Xuejuan,LI Geng,et al.An improved method of EMD and its applications in rotating machinery fault diagnosis [J].Journal of Vibration and Shock,2013,32(4) : 185-190.
[5] Dragomiretskiy K,Zosso D.Variational mode decomposition [J].IEEE Transactions on Signal Processing,2014,62(3): 531-544.
[6] 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].Proceedings Mathematical Physical & Engineering Sciences,1998,454(1971),903-995.
[7] Rostaghi M,Azami H.Dispersion Entropy: A measure for time-series analysis [J].IEEE Signal Processing Letters,2016,23(5): 610-614.
[8] 李从志,郑近德,潘海洋,等.基于自适应多尺度散布熵的滚动轴承故障诊断方法 [J].噪声与振动控制,2018,38(5): 173-180.
LI Congzhi,ZHENG Jinde,PAN Haiyang,et al.Fault diagnosis method of rolling bearings based on adaptive multi-scale dispersion entropy [J].Noise and Vibration Control,2018,38(5): 173-180.
[9] Pedrycz W .Algorithms of fuzzy clustering with partial supervision [J].Pattern Recognition Letters,1985,3(1): 13-20.
[10] Tax D M J,Duin R P W.Support vector data description [J].Pattern Recognition Letters,1999,20(11): 1191-1199.
[11] Zhu M,Wang Y,Chen S,et al.Sphere-structured support vector machines for multi-class pattern recognition [J].Rough Sets,Fuzzy Sets,Data Mining,and Granular Computing,2003,2639: 589-593.
[12] 袁胜发,褚福磊.球结构支持向量机在转轴碰摩位置识别中的应用 [J].振动与冲击,2009,28(8): 70-73.
Yuan Shengfa,Chu Fulei.Diagnostic approach to detect rub-impact fault of shaft based on sphere support vector machines [J].Journal of Vibration and Shock.2009,28(8): 70-73.
[13] Wu X,Kumar V,Quinlan J R.The top ten algorithms in data mining [J].Knowledge and Information Systems,2008,14(1): 1-31.
[14] Mirjalili S,Mirjalili S M,Lewis A.Grey wolf optimizer [J].Advances in Engineering Software,2014,69(3): 46-61.
[15] Mittal N,Singh U,Sohi B S.Modified grey wolf optimizer for global engineering optimization [J].Applied Computational Intelligence and Soft Computing,2016,2016.
[16] Pehlivanoglu,Volkan Y.A new particle swarm optimization method enhanced with a periodic mutation strategy and neural networks [J].IEEE Transactions on Evolutionary Computation,2013,17(3): 436-452.
[17] Bearing Data Center of the Case Western Reserve University available online http://csegroups.case.edu/bearingdatacenter.
[18] 刘长良,武英杰,甄成刚.基于变分模态分解和模糊C均值聚类的滚动轴承故障诊断 [J].中国电机工程学报,2015,35(13): 3358-3365.
LIU Changliang,WU Yingjie,ZHEN Chenggang.Rolling bearing fault diagnosis based on variational mode decomposition and fuzzy C means clustering [J].Proceedings of the CSEE,2015,35(13): 3358-3365.
[19] 康守强,胡明武,王玉静,等.基于特征迁移学习的变工况下滚动轴承故障诊断方法 [J].中国电机工程学报,2019,39(3): 764-772.
KANG Shouqiang,HU Mingwu,WANG Yujing,et al.Fault diagnosis method of a rolling bearing under variable working conditions based on feature transfer learning [J].Proceedings of the CSEE,2019,39(3): 764-772.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}