An Adaptive Remaining Life Prediction for Rolling Element Bearings

In order to select the effective health index and build reasonably the prediction model for prognostics, a new approach is proposed. The generative topographic mapping-based negative likelihood probability is used as the health index, and K-means clustering algorithm is employed for state division. The adaptive prediction model based on Markov model and least mean square algorithm is built by the historical data and the online monitoring data. According to the given threshold, the remaining life can be captured. Based on experimental verification, the results indicate that the selected health index is able to effectively reflect the condition of rolling bearings and the proposed model shows high prediction accuracy in comparison to the common one.

[1]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[2]  Zhengjia He,et al.  Remaining life prognostics of rolling bearing based on relative features and multivariable support vector machine , 2013 .

[3]  Jun Wu,et al.  Failure time prediction for mechanical device based on the degradation sequence , 2015, J. Intell. Manuf..

[4]  Nagi Gebraeel,et al.  A Neural Network Degradation Model for Computing and Updating Residual Life Distributions , 2008, IEEE Transactions on Automation Science and Engineering.

[5]  Kwok L. Tsui,et al.  A naive Bayes model for robust remaining useful life prediction of lithium-ion battery , 2014 .

[6]  Chaochao Chen,et al.  Machine remaining useful life prediction: An integrated adaptive neuro-fuzzy and high-order particle filtering approach , 2012 .

[7]  Christopher M. Bishop,et al.  GTM: The Generative Topographic Mapping , 1998, Neural Computation.

[8]  Xiaodong He,et al.  Theoretical prediction and experimental verification of pulling carbon nanotubes from carbon fiber prepared by chemical grafting method , 2013 .

[9]  Noureddine Zerhouni,et al.  CNC machine tool's wear diagnostic and prognostic by using dynamic Bayesian networks , 2012 .

[10]  Ying Peng,et al.  A novel method for online health prognosis of equipment based on hidden semi-Markov model using sequential Monte Carlo methods , 2012 .

[11]  Joseph Mathew,et al.  Bearing fault prognosis based on health state probability estimation , 2012, Expert Syst. Appl..

[12]  Dustin G. Mixon,et al.  On a Markov‐modulated shock and wear process , 2009 .

[13]  Jianbo Yu,et al.  A nonlinear probabilistic method and contribution analysis for machine condition monitoring , 2013 .

[14]  James Kuria Kimotho,et al.  Machinery Prognostic Method Based on Multi-Class Support Vector Machines and Hybrid Differential Evolution – Particle Swarm Optimization , 2013 .

[15]  Christopher M. Bishop,et al.  Developments of the generative topographic mapping , 1998, Neurocomputing.

[16]  Rong Li,et al.  Residual-life distributions from component degradation signals: A Bayesian approach , 2005 .

[17]  Iqbal Gondal,et al.  Multi-step support vector regression and optimally parameterized wavelet packet transform for machine residual life prediction , 2013 .

[18]  Daming Lin,et al.  A review on machinery diagnostics and prognostics implementing condition-based maintenance , 2006 .