基于VMD_MPE和FCM聚类的变转速工况下转子不平衡故障诊断方法

PDF(2177 KB)

振动与冲击 ›› 2022, Vol. 41 ›› Issue (14) : 290-298.

论文

钟志贤，马李奕，蔡忠侯，段一戬，陈金华

作者信息 +

Method of rotor unbalance fault diagnosis under variable-speed conditions based on VMD_MPE and FCM clustering

ZHONG Zhixian， MA Liyi， CAI Zhonghou， DUAN Yijian， CHEN Jinhua

Author information +

文章历史 +

摘要

旋转机械在变转速工况下转子不平衡故障诊断问题一直是故障诊断领域的难点，为解决该问题，提出一种基于变分模态分解（VMD）与多尺度排列熵（MPE）和模糊C均值（FCM）聚类结合的故障诊断方法（VMD_MPE-FCM）。首先，用VMD对转子的振动信号进行处理，得到若干本征模态分量（IMF）；然后根据转子不平衡故障时一倍频（1×）处振幅剧烈增加的现象，从VMD得到的各IMF频谱图中筛选出最能表征转子不平衡故障特征的IMF；进而采用MPE法对筛选出的IMF进行量化；最后，将量化所得值作为特征向量输入FCM，得到各转速工况下的标准聚类中心，采用择近原则，运用模糊贴近算法计算出待识别数据与标准聚类中心的贴近度，从而实现变转速工况下转子不平衡的故障识别。在转子实验台上采用VMD_MPE-FCM法进行了变转速工况下转子不平衡故障诊断实验，实验结果表明：该方法是有效的，可以准确、高效地提取出转子故障特征，能够很好地识别出不同转速工况下转子的不平衡故障。
关键词：变转速工况；转子不平衡故障；变分模态分解；多尺度排列熵；模糊C均值；故障诊断

Abstract

Rotor fault diagnosis of rotating machinery under variable speed conditions is a difficult problem in the field of fault diagnosis. To solve this problem, a method based on variational mode decomposition (VMD) with multiscale permutation entropy (MPE) and fuzzy c means clustering (FCM) was proposed (VMD_MPE-FCM). Firstly, the vibration signals of rotor were decomposed with VMD into a series of intrinsic mode functions (IMF). Then, the IMF which contains the most unbalance fault features was selected according to the phenomenon that the amplitude at the first harmonic (1×) increases sharply when the rotor unbalance fault occurs. Furthermore, MPE method was taken to quantify the selected IMF. Finally, the quantified values were put into FCM as the feature vectors to obtain the standard cluster center of each speed condition. Following this, the nearness between data to be identified and standard cluster center was calculated with a series of fuzzy nearness algorithms, so as to realize the identification and classification. The displacement signals of unbalanced rotor under variable-speed conditions were analyzed with VMD_MPE-FCM, results show that proposed method can extract unbalance fault features of rotor precisely and effectively, so as to diagnose the unbalance rotor fault under variable speed conditions accurately.
Key words: variable-speed conditions；unbalance rotor fault; variational mode decomposition (VMD); multi-scale permutation entropy (MPE); fuzzy c means (FCM); fault diagnosis

导出引用

钟志贤，马李奕，蔡忠侯，段一戬，陈金华. 基于VMD_MPE和FCM聚类的变转速工况下转子不平衡故障诊断方法[J]. 振动与冲击, 2022, 41(14): 290-298

ZHONG Zhixian， MA Liyi， CAI Zhonghou， DUAN Yijian， CHEN Jinhua. Method of rotor unbalance fault diagnosis under variable-speed conditions based on VMD_MPE and FCM clustering[J]. Journal of Vibration and Shock, 2022, 41(14): 290-298

参考文献

[1] 王正. 转动机械的转子动力学设计[M]. 北京：清华大学出版社，2015：38.
WANG Zheng. Rotor dynamics design of rotating machinery[M]. Beijing: Tsinghua University Press, 2015: 39.
[2] 周生通，李鸿光，张龙，等. 基于嵌入式谱随机有限元法的转子系统随机不平衡响应特性分析[J]. 振动与冲击，2016，35（19）：45-49+57.
ZHOU Tongsheng, LI Hongguang, ZHANG Long, et al. Stochastic unbalance response characteristics of rotor systems based on instrusive spectral stochastic finite eletment method [J]. Journal of Vibration and Shock, 2016, 35（19）:45-49+57.
[3] 王广斌，杜晓阳，罗军. 面向转子故障特征提取的多尺度拉普拉斯特征映射方法[J]. 中国机械工程，2016，27（20）：2791-2797.
WANG Guangbin, DU Xiaoyang, LUO Jun. Multi-scale laplace feature mapping for rotor fault feature extraction[J]. China Mechanical Engineering，2016，27（20）：2791-2797.
[4] G.N.D.S. Sudhakar, A.S. Sekhar. Identification of unbalance in a rotor bearing system[J]. Journal of Sound and Vibration,2011, 330(10):2299-2313.
[5] YAN Jihong, Hu Yuanyuan, GUO Chaozhong. Rotor unbalance fault diagnosis using DBN based on multi-source heterogeneous information fusion[J]. Procedia Manufacturing, 2019, 35:1184-1189.
[6] 孙斌，刘立远，牛翀. 基于局部切空间排列和K-最近邻分类器的转子故障诊断方法[J]. 中国机械工程，2015，26（01）：74-78.
SUN Bin, LIU Liyuan, NIU Chong. Rotor fault diagnosis methods based on local tangent space alignment and K-nearest neighbor[J]. China Engineering, 2015, 26(01):74-78.
[7] Mohammad Gohari. Modelling of shaft unbalance Modelling: a multi discs rotor using K-Nearest Neighbor and Decision Tree Algorithms[J]. Measurement, 2020,151: 127-134.
[8] 王菲. 基于VMD的转子故障特征提取及识别[D]. 华北电力大学，2018.
WANG Fei. Fault feature extraction and recognition of rotor based on VMD[D]. North China Electric Power University, 2018.
[9] Y. Hu，X. Tu，F. Li，et al. An adaptive and tacholess order analysis method based on enhanced empirical wavelet transform for fault detection of bearings with varying speeds[J]. Journal of Sound and Vibration, 2017, 409:241-255.
[10] 唐贵基，庞彬，何玉灵. 基于SSD-HT时频阶比跟踪的变转速转子故障诊断[J]. 推进技术，2018，39（05）：1134-1141.
TANG Guiji，PANG Bin，HE Yuling. Time-frequency order tracking for rotor fault diagnosis under variable speed conditions based on SSD-HT[J]. Journal of Propulsion Technology. 2018，39（05）：1134-1141.
[11] 郭俊. 变转速工况下直驱式永磁同步风力发电机轴承故障诊断方法研究[D]. 中国科学技术大学，2020.
GUO Jun. Bearing fault diagnosis of permanent magnet synchronous generator in direct-drive wind turbine under variable-Speed condition[D]. University of Science and Technology of China, 2020.
[12] 任勇. 变转速旋转机械关键零部件故障诊断研究[D].中国矿业大学，2019.
REN Yong. Fault diagnosis for key components of rotating machinery under varying speeds[D]. China University of Mining and Technology, 2019.
[13] 闻邦椿，顾家柳，夏松波. 高等转子动力学—理论技术与应用[M]. 北京：机械工业出版社，2000：228+333-334.
WEN Bangchun, GU Jialiu, XIA Songbo. Advanced rotor dynamics theory technology and application[M]. Beijing: China Machine Press, 2000: 228+333-334.
[14] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3):531-544.
[15] 刘尚坤，唐贵基. 改进的VMD方法及其在转子故障诊断中的应用[J]. 动力工程学报，2016，36（06）：448-453.
LIU Shangkun, TANG Guiji. Application of improved VMD method in fault diagnosis of rotor systems[J]. Journal of Chinese Society of Power Engineering,2016, 36(06):448-453.
[16] Aziz W, Arif M. Multiscale permutation entropy of physiological times series[C]//Proceeding of IEEE International Multi-topic Conference，INMIC，2005：1-6.
[17] 温广瑞，陈征，张志芬. 基于模糊C均值聚类和转子轴心轨迹特征的转子状态诊断[J]. 振动与冲击，2019，38（15）：27-35.
WEN Guangrui, CHEN Zheng, ZHANG Zhifen. Rotor state diagnosis based on fuzzy C-mean value clustering and its axial center orbit features[J]. Journal of Vibration and Shock, 2019, 38(15):27-35.
[18] 张运东. 基于FVMD多尺度排列熵和GK模糊聚类的故障诊断方法[D]. 燕山大学，2017.
ZHANG Yundong. A method of fault diagnosis based on FVMD multi-scale permutation entropy and GK fuzzy clustering[D]. Yanshan University, 2017.
[19] 郑近德，程军圣，杨宇. 多尺度排列熵及其在滚动轴承故障诊断中的应用[J]. 中国机械工程，2013，24（19）：2641-2646.
ZHENG Jinde, CHENG Junsheng, YANG Yu. Multi-scale permutation entropy and its applications to rolling bearing fault diagnosis[J]. China Mechanical Engineering, 2013, 24(19):2641-264.
[20] 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.