Remaining Useful Life Estimation in Rolling Bearings Utilizing Data-Driven Probabilistic E-Support Vectors Regression

We report on a data-driven approach for the remaining useful life (RUL) estimation of rolling element bearings based on ε-Support Vector Regression ( ε-SVR). Lifetime data are analyzed and evaluated. The occurrence of critical faults in every test is located, and a critical operational threshold is established. Multiple statistical features from the time-domain, frequency domain, and time-scale domain through a wavelet transform are extracted from the recordings of two accelerometers, and assessed for their diagnostic performance. Among those features, Wiener entropy is utilized for the first time in the condition monitoring of rolling bearings. A SVR model is trained and tested for the prediction of RUL on unseen data. Special attention is given in the tuning and the optimization of the user-defined hyper-parameters of the e-SVR model. Error bounds are estimated at each prediction point through a Bayesian treatment of the classical SVR model. The results are in good agreement to the actual RUL curve for all the tested cases. Prognostic performance metrics are also provided, and the discussion on the test results concludes with the generic character of the proposed methodology and its applicability in any prognostic task.

[1]  Noureddine Zerhouni,et al.  Remaining Useful Life Estimation of Critical Components With Application to Bearings , 2012, IEEE Transactions on Reliability.

[2]  Ying Peng,et al.  A prognosis method using age-dependent hidden semi-Markov model for equipment health prediction , 2011 .

[3]  Pascal Vasseur,et al.  Introduction to multi-sensor data fusion , 2004 .

[4]  N. Zerhouni,et al.  Fault prognostic of bearings by using support vector data description , 2012, 2012 IEEE Conference on Prognostics and Health Management.

[5]  Theodoros Loutas,et al.  Condition monitoring of a single-stage gearbox with artificially induced gear cracks utilizing on-line vibration and acoustic emission measurements , 2009 .

[6]  Bhaskar Saha,et al.  A Bayesian Framework for Remaining Useful Life Estimation , 2007, AAAI Fall Symposium: Artificial Intelligence for Prognostics.

[7]  Ronald R. Coifman,et al.  Entropy-based algorithms for best basis selection , 1992, IEEE Trans. Inf. Theory.

[8]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

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

[10]  Donghua Zhou,et al.  Remaining useful life estimation - A review on the statistical data driven approaches , 2011, Eur. J. Oper. Res..

[11]  Steven Y. Liang,et al.  Adaptive Prognostics for Rolling Element Bearing Condition , 1999 .

[12]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[13]  Curtis Lanham President Understanding the Tests that are Recommended for Electric Motor Predictive Maintenance , 2004 .

[14]  T. A. Harris,et al.  A New Stress-Based Fatigue Life Model for Ball Bearings , 2001 .

[15]  David He,et al.  A segmental hidden semi-Markov model (HSMM)-based diagnostics and prognostics framework and methodology , 2007 .

[16]  Vladimir Cherkassky,et al.  The Nature Of Statistical Learning Theory , 1997, IEEE Trans. Neural Networks.

[17]  Nagi Gebraeel,et al.  Residual life predictions from vibration-based degradation signals: a neural network approach , 2004, IEEE Transactions on Industrial Electronics.

[18]  Theodoros Loutas,et al.  Utilising the Wavelet Transform in Condition-Based Maintenance: A Review with Applications , 2012 .

[19]  Bin Zhang,et al.  An integrated architecture for fault diagnosis and failure prognosis of complex engineering systems , 2012, Expert Syst. Appl..

[20]  Nagi Gebraeel,et al.  Predictive Maintenance Management Using Sensor-Based Degradation Models , 2009, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[21]  Theodoros Loutas,et al.  The combined use of vibration, acoustic emission and oil debris on-line monitoring towards a more effective condition monitoring of rotating machinery , 2011 .

[22]  Enrico Zio,et al.  Combining Relevance Vector Machines and exponential regression for bearing residual life estimation , 2012 .

[23]  Bo-Suk Yang,et al.  Machine health prognostics using survival probability and support vector machine , 2011, Expert Syst. Appl..

[24]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[25]  Enrico Zio,et al.  FAILURE PROGNOSTICS BY A DATA-DRIVEN SIMILARITY-BASED APPROACH , 2013 .

[26]  Joseph Mathew,et al.  Rotating machinery prognostics. State of the art, challenges and opportunities , 2009 .

[27]  Alaa Elwany,et al.  Residual Life Predictions in the Absence of Prior Degradation Knowledge , 2009, IEEE Transactions on Reliability.

[28]  Michael J. Roemer,et al.  Predicting remaining life by fusing the physics of failure modeling with diagnostics , 2004 .

[29]  C. James Li,et al.  Gear fatigue crack prognosis using embedded model, gear dynamic model and fracture mechanics , 2005 .

[30]  Lin Ma,et al.  Prognostic modelling options for remaining useful life estimation by industry , 2011 .

[31]  Joyce Snell,et al.  6. Alternative Methods of Regression , 1996 .

[32]  M. Gasperin,et al.  Prediction of the remaining useful life: An integrated framework for model estimation and failure prognostics , 2012, 2012 IEEE Conference on Prognostics and Health Management.

[33]  Noureddine Zerhouni,et al.  Health assessment and life prediction of cutting tools based on support vector regression , 2015, J. Intell. Manuf..

[34]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[35]  Noureddine Zerhouni,et al.  A Data-Driven Failure Prognostics Method Based on Mixture of Gaussians Hidden Markov Models , 2012, IEEE Transactions on Reliability.

[36]  K. Loparo,et al.  HMM-Based Fault Detection and Diagnosis Scheme for Rolling Element Bearings , 2005 .

[37]  Zhigang Tian,et al.  An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring , 2012, J. Intell. Manuf..

[38]  Enrico Zio,et al.  Nuclear Power Plant Components Condition Monitoring by Probabilistic Support Vector Machine , 2013 .

[39]  Sankalita Saha,et al.  Metrics for Offline Evaluation of Prognostic Performance , 2021, International Journal of Prognostics and Health Management.

[40]  Theodoros Loutas,et al.  A hybrid prognostic model for multistep ahead prediction of machine condition , 2012 .

[41]  Junbin Gao,et al.  A Probabilistic Framework for SVM Regression and Error Bar Estimation , 2002, Machine Learning.

[42]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[43]  David Birkes,et al.  Alternative Methods of Regression: Birkes/Alternative , 1993 .

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

[45]  M. Pecht,et al.  Estimation of remaining useful life of ball bearings using data driven methodologies , 2012, 2012 IEEE Conference on Prognostics and Health Management.

[46]  Enrico Zio,et al.  Model-based and data-driven prognostics under different available information , 2013 .

[47]  Hai Qiu,et al.  Physics-based Remaining Useful Life Prediction for Aircraft Engine Bearing Prognosis , 2009 .