Reliability estimation and remaining useful lifetime prediction for bearing based on proportional hazard model

Abstract

As the central component of rotating machine, the performance reliability assessment and remaining useful lifetime prediction of bearing are of crucial importance in condition-based maintenance to reduce the maintenance cost and improve the reliability. A prognostic algorithm to assess the reliability and forecast the remaining useful lifetime (RUL) of bearings was proposed, consisting of three phases. Online vibration and temperature signals of bearings in normal state were measured during the manufacturing process and the most useful time-dependent features of vibration signals were extracted based on correlation analysis (feature selection step). Time series analysis based on neural network, as an identification model, was used to predict the features of bearing vibration signals at any horizons (feature prediction step). Furthermore, according to the features, degradation factor was defined. The proportional hazard model was generated to estimate the survival function and forecast the RUL of the bearing (RUL prediction step). The positive results show that the plausibility and effectiveness of the proposed approach can facilitate bearing reliability estimation and RUL prediction.

Keywords

prognostics / reliability estimation / remaining useful life / proportional hazard model

References

[1] SikorskaJ Z, HodkiewiczM, MaL. Prognostic modelling options for remaining useful life estimation by industry [J]. Mechanical Systems and Signal Processing, 2011, 25(5): 1803-1836

[2] SiX-s, WangW-b, HuC-h, ZhouD-hua. Remaining useful life estimation-A review on the statistical data driven approaches [J]. European Journal of Operational Research, 2011, 213(1): 1-14

[3] MahamadA K, SaonS, HiyamaT. Predicting remaining useful life of rotating machinery based artificial neural network [J]. Computers & Mathematics with Applications, 2010, 60(4): 1078-1087

[4] DevarajanK, EbrahimiN. A semi-parametric generalization of the Cox proportional hazards regression model: Inference and applications [J]. Computational Statistics & Data Analysis, 2011, 55(1): 667-676

[5] ChenB-j, ChenX-f, LiB, HeZ-j, CaoH-r, CaiG-gai. Reliability estimation for cutting tools based on logistic regression model using vibration signals [J]. Mechanical Systems and Signal Processing, 2011, 25(7): 2526-2537

[6] TranV T, ThomP, HamH, YangB S, NguyenT T. Machine performance degradation assessment and remaining useful life prediction using proportional hazard model and support vector machine [J]. Mechanical Systems and Signal Processing, 2012, 32: 320-330

[7] SiX-s, WangW-b, ChenM-y, HuC-h, ZhouD-hua. A degradation path-dependent approach for remaining useful life estimation with an exact and closed-form solution [J]. European Journal of Operational Research, 2013, 226(1): 53-66

[8] LiuD-t, PengY, LiJ-b, PengX-yuan. Multiple optimized online support vector regression for adaptive time series prediction [J]. Measurement, 2013, 46(8): 2391-2404

[9] TangS-j, GuoX-s, YuC-q, ZhouZ-j, ZhouZ-f, ZhangB-cheng. Real time remaining useful life prediction based on nonlinear Wiener based degradation processes with measurement errors [J]. Journal of Central South University, 2014, 21(12): 4509-4517

[10] BenkedjouhT, MedjaherK, ZerhouniN, RechakS. Remaining useful life estimation based on nonlinear feature reduction and support vector regression [J]. Engineering Applications of Artificial Intelligence, 2013, 26(7): 1751-1760

[11] HongS, ZhouZ, ZioE, WangW-bin. An adaptive method for health trend prediction of rotating bearings [J]. Digital Signal Processing, 2014, 35: 117-123

[12] LiS, ElbestawiM A. Fuzzy clustering for automated tool condition monitoring in machining [J]. Mechanical Systems and Signal Processing, 1996, 10(5): 533-550

[13] SilvaR G, ReubenR L, BakerK J, WilcoxS J. Tool wear monitoring of turning operations by neural network and expert system classification of a feature set generated from multiple sensors [J]. Mechanical Systems and Signal Processing, 1998, 12(2): 319-332

[14] LI Xu, ZHENG A-nan, ZHANG Xu-nan, LI Chen-chen, ZHANG Li. Rolling element bearing fault detection using support vector machine with improved ant colony optimization[J]. Measurement, 2013, 46(8): 2726-2734.

[15] LeiY-g, HeZ-j, ZiY-y, HuQiao. Fault diagnosis of rotating machinery based on multiple ANFIS combination with GAs [J]. Mechanical Systems and Signal Processing, 2007, 21(5): 2280-2294

[16] LinH, ChuanL, DongZ, SimiaoF. The mutual information based correlation analysis between fault types and monitor data [J]. Procedia Engineering, 2011, 15: 5268-5273

[17] CristescuC P, StanC, ScarlatE I, MineaT, CristescuC M. Parameter motivated mutual correlation analysis: Application to the study of currency exchange rates based on intermittency parameter and Hurst exponent [J]. Physica A: Statistical Mechanics and its Applications, 2012, 391(8): 2623-2635

[18] KhasheiM, BijariM. Hybridization of the probabilistic neural networks with feed-forward neural networks for forecasting [J]. Engineering Applications of Artificial Intelligence, 2012, 25(6): 1277-1288

[19] RajabzadehG, SalehiS, NematiA, SolatiH. Enhancing glass ionomer cement features by using the HA/YSZ nanocomposite: A feed forward neural network modeling [J]. Journal of the Mechanical Behavior of Biomedical Materials, 2014, 29: 317-327

[20] KalbfleischJ D, PrenticeR LThe statistical analysis of failure time data [M], 2011Toronto, CanadaJohn Wiley & Sons218-224

[21] NectouxP, GouriveauR, MedjaherK, RamassoE C-, MorelloB, ZerhouniN, VarnierC. PRONOSTIA: An experimental platform for bearings accelerated degradation tests [C]. Conference on Prognostics and Health Management Denver, 2012United StatesIEEE Reliability Society1-8