Intelligent identification method using kernel extreme learning machine for rolling bearing multi-working condition multi-feature automatic selection

PDF(2046 KB)

Journal of Vibration and Shock ›› 2020, Vol. 39 ›› Issue (23) : 182-189.

HU Aijun, ZHANG Junhua, LIU Suixian, XU Sha

Author information +

History +

Abstract

There are many deficiencies in intelligent fault diagnosis of rolling bearing, especially, for fault diagnosis under complex working conditions, there are problems of insufficient feature extraction and low diagnosis accuracy.Here, aiming at fault diagnosis of rolling bearing under multi-working condition with different fault types, different levels of fault and different loads, an intelligent identification method using kernel extreme learning machine based on multi-feature automatic selection was proposed.Firstly, effective fault features were extracted in time domain, frequency one and time-frequency one, respectively.Secondly, Laplace score (LS) was adopted to automatically select sensitive features according to the importance of each feature, the goal was to eliminate some redundant information and improve computational efficiency.Finally, the kernel extreme learning machine with simulated annealing particle swarm optimization was adopted to realize multi-fault state recognition of rolling bearing.The method was applied in fault identification of rolling bearing under variable loads.It was shown that compared with other identification methods, the proposed method has higher recognition accuracy and faster classification speed.

Key words

rolling bearing / fault diagnosis / Laplace score / simulated annealing particle swarm optimization / kernel extreme learning machine

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

HU Aijun, ZHANG Junhua, LIU Suixian, XU Sha. Intelligent identification method using kernel extreme learning machine for rolling bearing multi-working condition multi-feature automatic selection[J]. Journal of Vibration and Shock, 2020, 39(23): 182-189

References

[1] Wu S D, Wu P H, Wu C W, et al. Bearing Fault Diagnosis Based on Multiscale Permutation Entropy and Support Vector Machine[C] // Molecular Diversity Preservation International, 2012:1343-1356.
[2] Liu H, Han M. A fault diagnosis method based on local mean decomposition and multi-scale entropy for roller bearings[J]. Mechanism and Machine Theory, 2014, 75:67-78.
[3] 石志标，陈长河，曹丽华．基于云PSO-SVM的汽轮机转子故障诊断研究[J].热能动力工程,2018,33(6):41-47.
SHI Z B, CHEN C H, CAO L H.Study of the Diagnosis of Any Fault Occurred to the Rotor of a Steam Turbine Based on the Cloud Particle Swarm Optimization-Supporting Vector Machine .Journal of Engineering for Thermal Energy and Power,2018,33(6):41-47.
[4] 王浩任，黄亦翔，赵帅,等.基于小波包和拉普拉斯特征值映射的柱塞泵健康评估方法[J].振动与冲击,2017,36(22):45-50.
WANG H R, HUANG Y X,ZHAO S, et al. Health assessment for a piston pump based on WPD and LE[J].Journal of Vibration and Shock.2017,36(22):45-50.
[5] 黄宏臣,韩振南,张倩倩,等.基于拉普拉斯特征映射的滚动轴承故障识别[J].振动与冲击,2015,34(5):128-134+144.
HUANG H C,HAN Z N,ZHANG Q Q,et al. Method of fault diagnosis for rolling bearings based on Laplace eigenmap[J].
Journal of Vibration and Shock.2015,34(5):128-134+144.
[6] Zhang K, Li Y, Scarf P, et al. Feature selection for high-dimensional machinery fault diagnosis data using multiple models and Radial Basis Function networks[J]. Neurocomputing, 2011, 74(17): 2941-2952.
[7] Jiang Q, Jia M, Hu J, et al. Machinery fault diagnosis using supervised manifold learning[J]. Mechanical Systems and Signal Processing, 2009, 23(7): 2301-2311.
[8] He X, Cai D, Niyogi P, et al. Laplacian Score for Feature Selection[C]. neural information processing systems, 2005: 507-514.
[9] Li Y, Xu M, Wang R, et al. A fault diagnosis scheme for rolling bearing based on local mean decomposition and improved multiscale fuzzy entropy[J]. Journal of Sound and Vibration, 2016, 360:277-299.
[10] 李兵，张培林，任国全，等．运用EMD和GA—SVM的齿轮故障特征提取与选择[J]．振动测试与诊断，2009，29(4)：445-448.
LI B,ZHANG P L,REN G Q,et al. Gear Fault Diagnosis Using Empirical Mode Decomposition, Genetic Algorithm and Support Vector[J].Journal of Vibration, Measurement & Diagnosis.2009，9(4)：445-448.
[11] 蒋永华,程光明,阚君武,等.基于NGA优化SVM的滚动轴承故障诊断[J].仪器仪表学报,2013,34(12):2684-2689.
JIANG Y H,CHENG G M,KAN J W,etal. Rolling bearing fault diagnosis based on NGA optimized SVM[J].Chinese Journal of Scientific Instrument.2013,34(12):2684-2689.
[12] 陈法法,汤宝平,董绍江.基于粒子群优化LS-WSVM的旋转机械故障诊断[J].仪器仪表学报,2011,32(12):2747-2753.
CHEN F F,TANG B P,DONG S J. Rotating machinery fault diagnosis based on LS-WSVM with particle swarm optimization[J].Chinese Journal of Scientific Instrument. 2011,32(12):747-2753.
[13] 陈绍炜,柳光峰,冶帅．基于核极限学习机的模拟电路故障诊断研究[J].西北工业大学学报,2015,33(2):290-294.
CHEN S W,LIU G F,YE S. A Method of Fault Diagnosis for Analog Circuit Based on KELM[J].Journal of Northwestern Polytechnical University,2015,33(2):290-294.
[14] 刘义亚,李可,宿磊. 基于近似熵和LCD-KELM的滚动轴承故障诊断[J].噪声与振动控制,2018,38(2):162-167.
LIU Y Y, LI K, SU L. Intelligent Diagnosis Method for Rolling Bearings using Approximate Entropy and LCD-KELM[J].2018,38(2):162-167.
[15] 赵孝礼,赵荣珍,孙业北,等.基于正则化核最大边界投影维数约简的滚动轴承故障诊断[J].振动与冲击,2017,36(14):104-110.
ZHAO X L,ZHAO R Z,SUN Y B,et al. Fault diagnosis of rolling bearings based on the dimension reduction using the regularized kernel maximum margin projection[J].Journal of Vibration and Shock.2017,36(14):104-110.
[16] Liu Z , Cao H , Chen X , et al. Multi-fault classification based on wavelet SVM with PSO algorithm to analyze vibration signals from rolling element bearings [J]. Neurocomputing,2013, 99:399-410.
[17] 邓艾东，赵力，包永强．基于模糊熵的转子碰摩声发射信号的识别[J].机械工程学报, 2010, 46(3): 71-75.
DENG A D,ZHAO L,BAO Y Q.Recognition of Rub-impact Acoustic Emission Signal Based on Fuzzy Entropy[J]. Journal of Mechanical Engineering, 2010, 46(3): 71-75.
[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 C L，WU Y J，ZHEN C J．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] Huang G B , Zhou H , Ding X , et al. Extreme Learning Machine for Regression and Multiclass Classification[J]. IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics), 2012, 42(2):513-529.2010, 46(3): 71-75.
[20] Luo M , Li C , Zhang X , et al. Compound feature selection and parameter optimization of ELM for fault diagnosis of rolling element bearings[J]. ISA Transactions, 2016: S0019057816301847.