A model to determining the remaining useful life of rotating equipment, based on a new approach to determining state of degradation

Abstract

Condition assessment is one of the most significant techniques of the equipment’s health management. Also, in PHM methodology cycle, which is a developed form of CBM, condition assessment is the most important step of this cycle. In this paper, the remaining useful life of the equipment is calculated using the combination of sensor information, determination of degradation state and forecasting the proposed health index. The combination of sensor information has been carried out using a new approach to determining the probabilities in the Dempster-Shafer combination rules and fuzzy c-means clustering method. Using the simulation and forecasting of extracted vibration-based health index by autoregressive Markov regime switching (ARMRS) method, final health state is determined and the remaining useful life (RUL) is estimated. In order to evaluate the model, sensor data provided by FEMTO-ST Institute have been used.

Keywords

remaining useful life (RUL) / prognostics and health management (PHM) / autoregressive markov regime switching (ARMRS) / health index (HI) / Dempster-Shafer theory / fuzzy c-means (FCM) / Kurtosis-entropy / degradation

References

[1] LeeJ, WuF J, ZhaoW, GhaffariM, LiaoL X, SiegelD. Prognostics and health management design for rotary machinery systems: Reviews, methodology and applications. Mechanical Systems and Signal Processing, 2014, 42(1): 314-3342

[2] TahanM, TsoutsanisE, MuhammadM, Abdul KarimZ A. Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: A review. Applied Energy, 2017, 198: 122-144

[3] KanM S, TanA C C, MathewJ. A review on prognostic techniques for non-stationary and non-linear rotating systems. Mechanical Systems and Signal Processing, 2015, 62–63: 1-20

[4] AnD, KimN H, ChoiJ H. Practical options for selecting data-driven or physics-based prognostics algorithms with reviews. Reliability Engineering & System Safety, 2015, 133: 223-236

[5] RaiA, UpadhyayS H. A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings. Tribology International, 2016, 96: 289-306

[6] MosallamA, MedjaherK, ZerhouniN. Data-driven prognostic method based on Bayesian approaches for direct remaining useful life prediction. Journal of Intelligent Manufacturing, 2016, 27(5): 1037-1048

[7] DengY J, BarrosA, GrallA. Degradation modeling based on a time-dependent Ornstein-Uhlenbeck process and residual useful lifetime estimation. IEEE Transactions on Reliability, 2016, 65(1): 126-140

[8] RenL, CuiJ, SunY-Q, ChengX-J. Multi-bearing remaining useful life collaborative prediction: A deep learning approach. Journal of Manufacturing Systems, 2017, 43: 248-256

[9] SutrisnoE, OhH, VasanA S S, PechtMEstimation of remaining useful life of ball bearings using data driven methodologies, 2012, Denver. New York, USA, IEEE

[10] KimothoJ K, Sondermann-WoelkeC, MeyerT, SextroW. Machinery prognostic method based on multi-class support vector machines and hybrid differential evolution-particle swarm optimization. Chemical Engineering Transactions, 2013, 33: 619-624

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

[12] HongS, ZhouZ, ZioE, HongK. Condition assessment for the performance degradation of bearing based on a combinatorial feature extraction method. Digital Signal Processing, 2014, 27: 159-166

[13] ZuritaD, CarinoJ A, DelgadoM, OrtegaJ ADistributed neuro-fuzzy feature forecasting approach for condition monitoring, 2014, New York, USA, IEEE

[14] SoualhiA, MedjaherK, ZerhouniN. Bearing health monitoring based on Hilbert-Huang transform, support vector machine, and regression. IEEE Transactions on Instrumentation and Measurement, 2015, 64(1): 52-62

[15] NieY-T, WanJ-QEstimation of remaining useful life of bearings using sparse representation method, 2015, New York, USA, IEEE

[16] ZhangB, ZhangL-J, XuJ-W. Degradation feature selection for remaining useful life prediction of rolling element bearings. Quality and Reliability Engineering International, 2016, 32(2): 547-554

[17] GUO Liang, GAO Hong-li, HUANG Hai-feng, HE Xiang, LI Shi-chao. Multifeatures fusion and nonlinear dimension reduction for intelligent bearing condition monitoring [J]. Shock and Vibration, 2016: 1–10. DOI: https://doi.org/10.1155/2016/4632562.

[18] MosallamA, MedjaherK, ZerhouniN. Time series trending for condition assessment and prognostics. Journal of Manufacturing Technology Management, 2014, 25(4): 550-567

[19] LiN-P, LeiY-G, LinJ, DingS X. An improved exponential model for predicting remaining useful life of rolling element bearings. IEEE Transactions on Industrial Electronics, 2015, 62(12): 7762-7773

[20] WangL, ZhangL, WangX-Z. Reliability estimation and remaining useful lifetime prediction for bearing based on proportional hazard model. Journal of Central South University, 2015, 22(12): 4625-4633

[21] CarinoJ A, ZuritaD, DelgadoM, OrtegaJ A, Romero-TroncosoR JRemaining useful life estimation of ball bearings by means of monotonic score calibration, 2015, New York, USA, IEEE

[22] LeiY-G, LiN-P, LinJ. A new method based on stochastic process models for machine remaining useful life prediction. IEEE Transactions on Instrumentation and Measurement, 2016, 65(12): 2671-2684

[23] NiuG, QianF, ChoiB K. Bearing life prognosis based on monotonic feature selection and similarity modeling. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2016, 230(18): 3183-3193

[24] HuangZ-Y, XuZ-G, KeX-J, WangW-H, SunY-X. Remaining useful life prediction for an adaptive skew-Wiener process model. Mechanical Systems and Signal Processing, 2017, 87: 294-306

[25] ChengZ-WResidual useful life prediction for rolling element bearings based on multi-feature fusion regression, 2017, New York, USA, IEEE

[26] TrinhH C, KwonY K. An empirical investigation on a multiple filters-based approach for remaining useful life prediction. Machines, 2018, 6(3): 35

[27] RenL, SunY-Q, CuiJ, ZhangL. Bearing remaining useful life prediction based on deep autoencoder and deep neural networks. Journal of Manufacturing Systems, 2018, 48: 71-77

[28] RenL, SunY-Q, WangH, ZhangL. Prediction of bearing remaining useful life with deep convolution neural network. IEEE Access, 2018, 613041-13049

[29] DengS-C, ChenZ-Q, ChenZAuxiliary particle filter-based remaining useful life prediction of rolling bearing, 2017, New York, USA, IEEE

[30] WuY-T, YuanM, DongS-P, LinL, LiuY-Q. Remaining useful life estimation of engineered systems using vanilla LSTM neural networks. Neurocomputing, 2018, 275: 167-179

[31] LiX, ZhangW, DingQ. Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction. Reliability Engineering & System Safety, 2019, 182: 208-218

[32] Ben AliJ, Chebel-MorelloB, SaidiL, MalinowskiS, FnaiechF. Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network. Mechanical Systems and Signal Processing, 2015, 56–57: 150-172

[33] ZhaoM-H, TangB-P, TanQ. Bearing remaining useful life estimation based on time-frequency representation and supervised dimensionality reduction. Measurement, 2016, 86: 41-55

[34] LiaoL-X, JinW-J, PavelR. Enhanced restricted boltzmann machine with prognosability regularization for prognostics and health assessment. IEEE Transactions on Industrial Electronics, 2016, 63(11): 7076-7083

[35] WangZ-Q, HuC-H, FanH-D. Real-time remaining useful life prediction for a nonlinear degrading system in service: application to bearing data. ASME Transactions on Mechatronics, 2018, 23(1): 211-222

[36] SingletonR K, StrangasE G, AviyenteS. Extended kalman filtering for remaining-useful-life estimation of bearings. IEEE Transactions on Industrial Electronics, 2015, 62(3): 1781-1790

[37] FengY, HuangX-D, HongR-J, ChenJ. Online residual useful life prediction of large-size slewing bearings: A data fusion method. Journal of Central South University, 2017, 24(1): 114-126

[38] LiuY-M, ZhaoC-C, XiongM-Y, ZhaoY-H, QiaoN-G, TianG-D. Assessment of bearing performance degradation via extension and EEMD combined approach. Journal of Central South University, 2017, 24(5): 1155-1163

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

[40] LeiY-G, LiN-P, GontarzS, LinJ, RadkowskiS, DybalaJ. A model-based method for remaining useful life prediction of machinery. Transactions on Reliability, 2016, 65(3): 1314-1326

[41] LiH-K, WangY-HRolling bearing reliability estimation based on logistic regression model, 2013, New York, USA, IEEE

[42] LI Yao-long, LI Hong-ru, WANG Bing, GU Hong-qiang. Rolling element bearing performance degradation assessment using variational mode decomposition and Gathgeva clustering time series segmentation [J]. International Journal of Rotating Machinery, 2017: 1–12. DOI: https://doi.org/10.1155/2017/2598169.

[43] SloukiaF, AroussiM E, MedromiH, WahbiMBearings prognostic using mixture of gaussians hidden Markov model and support vector machine, 2013, New York, USA, IEEE

[44] WangY, PengY-Z, ZiY-Y, JinX-H, TsuiK L. A two-stage data-driven-based prognostic approach for bearing degradation problem. IEEE Transactions on Industrial Informatics, 2016, 12(3): 924-932

[45] MedjaherK, ZerhouniN, BakloutiJData-driven prognostics based on health indicator construction: Application to PRONOSTIA’s data, 2013, New York, USA, IEEE

[46] LoutasT H, RouliasD, GeorgoulasG. Remaining useful life estimation in rolling bearings utilizing data-driven probabilistic E-support vectors regression. IEEE Transactions on Reliability, 2013, 62(4): 821-832

[47] BoskoskiP, GasperinM, PetelinDBearing fault prognostics based on signal complexity and Gaussian process models, 2012, New York, USA, IEEE

[48] WangT-YBearing life prediction based on vibration signals: A case study and lessons learned, 2012, New York, USA, IEEE

[49] PorotskySRemaining useful life estimation for systems with non-trendability behaviour, 2012, New York, USA, IEEE

[50] PanY-P, ErM J, LiX, YuH-Y, GouriveauR. Machine health condition prediction via online dynamic fuzzy neural networks. Engineering Applications of Artificial Intelligence, 2014, 35: 105-113

[51] XiaoL, ChenX-H, ZhangX-H, LiuM. A novel approach for bearing remaining useful life estimation under neither failure nor suspension histories condition. Journal of Intelligent Manufacturing, 2017, 28(8): 1893-1914

[52] FumeoE, OnetoL, AnguitaD. Condition based maintenance in railway transportation systems based on big data streaming analysis. Procedia Computer Science, 2015, 53: 437-446

[53] JavedK, GouriveauR, ZerhouniN, NectouxP. Enabling health monitoring approach based on vibration data for accurate prognostics. IEEE Transactions on Industrial Electronics, 2015, 62(1): 647-656

[54] AnD, KimN H, ChoiJBearing prognostics method based on entropy decrease at specific frequency, 2016, Reston, Virginia, AIAA

[55] HinchiA Z, TkiouatM. Rolling element bearing remaining useful life estimation based on a convolutional long-short-term memory network. Procedia Computer Science, 2018, 127: 123-132

[56] JavedK, GouriveauR, ZerhouniNNovel failure prognostics approach with dynamic thresholds for machine degradation, 2013, New York, USA, IEEE

[57] KhadersabA, ShivakumarS. Vibration analysis techniques for rotating machinery and its effect on bearing faults. Procedia Manufacturing, 2018, 20: 247-252

[58] ShaoH-D, JiangH-K, LiX-Q, LiangT-C. Rolling bearing fault detection using continuous deep belief network with locally linear embedding. Computers in Industry, 2018, 96: 27-39

[59] SheD-M, JiaM-P. Wear indicator construction of rolling bearings based on multi-channel deep convolutional neural network with exponentially decaying learning rate. Measurement, 2019, 135: 368-375

[60] PearsonR K. Outliers in process modeling and identification. IEEE Transactions on Control Systems Technology, 2002, 10(1): 55-63

[61] BabuC N, ReddyB E. A moving-average filter based hybrid ARIMA-ANN model for forecasting time series data. Applied Soft Computing, 2014, 23: 27-38

[62] PanY-N, ChenJ, LiX-L. Bearing performance degradation assessment based on lifting wavelet packet decomposition and fuzzy c-means. Mechanical Systems and Signal Processing, 2010, 24(2): 559-566

[63] ChengC-Q, Sa-NgasoongsongA, BeycaO, LeT, YangH, KongZ, BukkapatnamS T S. Time series forecasting for nonlinear and non-stationary processes: a review and comparative study. IIE Transactions, 2015, 47(10): 1053-1071

[64] WangS-N, ZhangX-Y, GaoD-Z, ChenB, ChengY-J, YangY-Z, YuW-T, HuangZ-W, PengJA remaining useful life prediction model based on hybrid long-short sequences for engines, 2018, New York, USA, IEEE

[65] WangD, ZhaoY, YangF-F, TsuiK L. Nonlinear-drifted Brownian motion with multiple hidden states for remaining useful life prediction of rechargeable batteries. Mechanical Systems and Signal Processing, 2017, 93: 531-544

[66] YanJ-H, LeeJA hybrid method for on-line performance assessment and life prediction in drilling operations, 2007, New York, USA, IEEE

[67] PhamH T, TranV T, YangB S. A hybrid of nonlinear autoregressive model with exogenous input and autoregressive moving average model for long-term machine state forecasting. Expert Systems with Applications, 2010, 37(4): 3310-3317

[68] WuW, HuJ-T, ZhangJ-LPrognostics of machine health condition using an improved ARIMA-based prediction method, 2007, New York, USA, IEEE

[69] ZhouY, HuangM. Lithium-ion batteries remaining useful life prediction based on a mixture of empirical mode decomposition and ARIMA model. Microelectronics Reliability, 2016, 65: 265-273

[70] RaiA, UpadhyayS H. The use of MD-CUMSUM and NARX neural network for anticipating the remaining useful life of bearings. Measurement, 2017, 111: 397-410

[71] Ben AliJ, FnaiechN, SaidiL, Chebel-MorelloB, FnaiechF. Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals. Applied Acoustics, 2015, 89: 16-27

[72] SamantaB, Al-BalushiK R. Artificial neural network based fault diagnostics of rolling element bearings using time-domain features. Mechanical Systems and Signal Processing, 2003, 17(2): 317-328

[73] ZhengX-J, FangH-J. An integrated unscented kalman filter and relevance vector regression approach for lithium-ion battery remaining useful life and short-term capacity prediction. Reliability Engineering & System Safety, 2015, 144: 74-82

[74] AndreD, NuhicA, Soczka-GuthT, SauerD U. Comparative study of a structured neural network and an extended Kalman filter for state of health determination of lithium-ion batteries in hybrid electricvehicles. Engineering Applications of Artificial Intelligence, 2013, 26(3): 951-961

[75] HochsteinA, AhnH I, LeungY T, DenesukMSwitching vector autoregressive models with higher-order regime dynamics Application to prognostics and health management, 2014, New York, USA, IEEE

[76] PengY-Z, WangY, ZiY-Y. Switching state-space degradation model with recursive filter/smoother for prognostics of remaining useful life. IEEE Transactions on Industrial Informatics, 2019, 15(2): 822-832

[77] HamiltonJ DRegime switching models, 2010, London, UK, Palgrave Macmillan UK, 202209

[78] SchwarzG. Estimating the dimension of a model. The annals of statistics, 1978, 6(2): 461-464

[79] PERLIN M. MS_Regress-the MATLAB package for Markov regime switching models [R]. 2015. DOI: 10.2139/ssrn.1714016.

[80] ShaferGA mathematical theory of evidence, 1976, Princeton, Princeton University Press

[81] SENTZ K, FERSON S. Combination of evidence in Dempster-Shafer theory [R]. Office of Scientific and Technical Information (OSTI), 2002. DOI: https://doi.org/10.2172/800792.

[82] SMARANDACHE F, DEZERT J. Advances and applications of DSmT for information fusion [R]. Collected Works, 2015. https://hal.archives-ouvertes.fr/hal-01080187/.

[83] NECTOUX P, GOURIVEAU R, MEDJAHER K, RAMASSO E, CHEBEL-MORELLO B, ZERHOUNI N, VARNIER C. PRONOSTIA: An experimental platform for bearings accelerated degradation tests [C]// IEEE International Conference on Prognostics and Health Management. PHM’12. 2012: CPF12PHM-CDR. https://hal.archives-ouvertes.fr/hal-00719503.