Fault diagnosis for rotating machineries under variable operation conditions based on SVDI
SONG Tao1,2,WANG Yulin3, ZHAO Mingfu1,2,ZHONG Nianbing1,2
1.Chongqing Key Lab of Modern Photoelectric Detection Technology and Instrument, Chongqing 400054, China;
2.School of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, China;
3.Chongqing Vocational College of Public Transportation, Chongqing 402247, China
摘要旋转机械设备变工况特点导致振动特征不稳定，给故障诊断带来很大困难这一问题。提出一种基于奇异值分解插值(Singular Value Decomposition Interpolation, SVDI)的变工况故障诊断方法，构建离散工况下的振动信号样本，通过奇异值分解将样本特征矩阵分解为奇异向量、旋转矩阵和特征均值，分别对奇异向量、旋转矩阵和特征均值进行插值，再重构实测工况下的特征矩阵，最后通过特征约简、模式识别方法进行故障诊断。该方法可在没有完备样本库的条件下估计出一定范围内任意工况的振动特征，能解决旋转机械设备变工况条件下的故障诊断难题。多种转速下的齿轮箱故障诊断实例证明了该方法的有效性。
Abstract：Variable operation conditions of rotating machineries lead to unstable vibration characteristics to bring large difficulties to their fault diagnosis.Here, a method for variable conditions fault diagnosis based on the singular value decomposition interpolation (SVDI) was proposed.Firstly, vibration signal samples of rotating machinery were collected under a discrete operation condition.Then sample characteristic matrices were decomposed into singular vectors, rotation matrices and characteristic means with SVD.These singular vectors, rotation matrices and characteristic means were interpolated to reconstruct characteristic matrices under the actual measured operation condition.Finally, the fault diagnosis for rotating machinery was conducted with the feature reduction and pattern recognition method.It was shown that the proposed method can be used to estimate vibration characteristics of rotating machinery under any working condition to a certain extent when there is no complete sample base, and solve difficult fault diagnosis problems of rotating machineries under variable operation conditions.
宋涛1,2，王瑜琳3，赵明富1,2，钟年丙1,2. 基于SVDI的变工况旋转机械故障诊断方法[J]. 振动与冲击, 2018, 37(19): 211-216.
SONG Tao1,2,WANG Yulin3, ZHAO Mingfu1,2,ZHONG Nianbing1,2. Fault diagnosis for rotating machineries under variable operation conditions based on SVDI. JOURNAL OF VIBRATION AND SHOCK, 2018, 37(19): 211-216.
[1] CAO H, ZHOU K, CHEN X. Chatter identification in end milling process based on EEMD and nonlinear dimensionless indicators[J]. International Journal of Machine Tools & Manufacture, 2015, 92:52–59.
[2] HONG L, DHUPIA J S, SHENG S. An explanation of frequency features enabling detection of faults in equally spaced planetary gearbox[J]. Mechanism & Machine Theory, 2014, 73(2):169–183.
[3] BAOPING TANG,TAO SONG,FENG LI et al，Fault diagnosis for a wind turbine transmission system based on manifold learning and Shannon wavelet support vector machine, Renewable Energy, 2014,62:1-9.
[4] SU Z, TANG B, LIU Z, et al. Multi-fault diagnosis for rotating machinery based on orthogonal supervised linear local tangent space alignment and least square support vector machine[J]. Neurocomputing, 2015, 157:208–222.
[5] 苏祖强, 汤宝平, 邓蕾,等. 有监督LLTSA特征约简旋转机械故障诊断[J]. 仪器仪表学报, 2014(8):1766-1771.
Su Zuqiang，Tang Baoping，Deng Lei，Yin Aijun, Rotating machinery fault diagnosis with supervised-linear local tangent space alignment for dimension reduction[J], Chinese Journal of Scientific Instrument, , 2014(8):1766-1771.
[6] YANG Y, WANG H, CHENG J, et al. A fault diagnosis approach for roller bearing based on VPMCD under variable speed condition[J]. Measurement, 2013, 46(8):2306–2312.
[7] A. SOLEIMANI, S.E. KHADEM. Early fault detection of rotating machinery through chaotic vibration feature extraction of experimental data sets[J]. Chaos, Solitons & Fractals, 2015, 78:61–75.
[8]刘若晨, 左洪福. 变工况下滚动轴承故障注入静电监测方法研究[J]. 仪器仪表学报, 2014, 35(10):2348-2355.
LIU RUOCHEN，ZUO HONGFU, Research on electrostatic monitoring method of rolling bearings with injected fault under variable operating conditions[J], Chinese Journal of Scientific Instrument, 2014, 35(10):2348-2355.
[9] 潘海宁, 张军, 秦明,等. 基于能量谱特征的变速风机振动调制信号的检测方法[J]. 中国电机工程学报, 2014, S1 (S):166-171.
PAN Haining, ZHANG Jun,QIN Ming et al. Modulation Signal Detection of Wind Turbine’s Vibration Based on Feature Extraction of the Energy Spectrum[J], Proceedings of the CSEE, 2014(S1):166-171.
[10] LIU H, WANG X, LU C. Rolling Bearing Fault Diagnosis under Variable Conditions Using Hilbert-Huang Transform and Singular Value Decomposition[J]. Mathematical Problems in Engineering, 2014, 2014(1):1-10.
[11] 邹新光, 崔彦平, 乔智利,等. Hilbert解调与倒阶次谱的变工况齿轮特征提取[J]. 机械设计与制造, 2016(11):38-41.
Zou Xinguang, Cui Yanping, Qiao Zhili et al. Variable Gear Feature Extraction of the Hilbert Demodulation and Order Time Spectrum[J], Machinery Design & Manufacture, 2016(11):38-41.
[12]BORGHESANI P, PENNACCHI P, RANDALL R B, et al. Order tracking for discrete-random separation in variable speed conditions[J]. Mechanical Systems & Signal Processing, 2012, 30(7):1–22.
[13] 秦嗣峰, 冯志鹏, LIANG Ming. Vold-Kalman滤波和高阶能量分离在时变工况行星齿轮箱故障诊断中的应用研究[J]. 振动工程学报, 2015, 28(5):839-845.
Qin Sifeng, Feng Zhipeng, Liang Ming, Application of Vold-Kalman filter and higher order energy separation to fault diagnosis of planetary gearbox under time-varying conditions[J], Journal of Vibration Engineering, 2015, 28(5):839-845.
[14] COYLE E, COLLINS E G, ROBERTS R G. Speed independent terrain classification using Singular Value Decomposition Interpolation.[C]// Proceedings - IEEE International Conference on Robotics and Automation. 2011:4014-4019.
[15] 宋涛. 基于流形学习的风电机组传动系统早期故障特征提取方法研究[D]. 重庆大学, 2013.
SONG TAO, Early Fault Feature Extraction for Wind Turbine Transmission System Based on Manifold Learning[D], Chongqing University, 2013.
