The frequent failure components in rotary machinery are the rolling element bearings as it is important for prognostics of rolling element bearings. In this study, the data-driven technique was used to develop the prognostic models based on particle swarm optimization techniques. These models apply to estimate the rolling element bearing degradation and predict remaining useful life. Initially, the fault features were extracted by processing the vibration signals through wavelet packet decomposition based on the intensifying impulsive characteristics and superiority of features. Health indicators evaluate from fault features. The prognostic models are developed with the following approaches: Gated recurrent neural network, classification and regression tree, and Autoregressive-Moving Average models. Performances of models are verified on the basis of error in prediction. To verify the suggested methodology, an experiment on normal and faulty bearings was conducted using a bearing test rig. Experimental results clarify that the prognostic algorithms predict bearing remaining useful life with significant robustness. Outperformance of the proposed method and conformation of degree of accuracy from results indicate that remaining useful life is conjectured as inference compared with the published literature.
NandiSToliyatHALiX.Condition monitoring and fault diagnosis of electrical motors: a review. IEEE T Energ Conv2005; 20(4): 719–729.
2.
GebraeelNElwanyAPanJ.Residual life predictions in the absence of prior degradation knowledge. IEEE T Reliab2009; 58(1): 106–117.
3.
GebraeelNLawleyM.A neural network degradation model for computing and updating residual life distributions. IEEE T Autom Sci Eng2008; 5(1): 154–163.
4.
SassiSBadriBThomasM.A numerical model to predict damaged bearing vibrations. J Vib Contr2007; 13(11): 1603–1628.
5.
NistaneVHarshaS.Performance evaluation of bearing degradation based on stationary wavelet decomposition and extra trees regression. World J Eng2018; 15(5): 646–658.
6.
NistaneVMHarshaSP.Prognosis of degradation progress of ball bearings using supervised machine learning. Proc IMechE, Part K: J Multi-Body Dynamics2017; 232: 183–198.
7.
NistaneVM.Wavelet-based features for prognosis of degradation in rolling element bearing with non-linear autoregressive neural network. Austral J Mech Eng2019; 23: 1–5.
8.
KankarPKSharmaSCHarshaSP.Fault diagnosis of ball bearings using continuous wavelet transform. Appl Soft Comput2011; 11(2): 2300–2312.
9.
RandallRBAntoniJ.Rolling element bearing diagnostics: a tutorial. Mech Syst Sig Process2011; 25(2): 485–520.
10.
HengAZhangSTanAC, et al. Rotating machinery prognostics: state of the art, challenges and opportunities. Mech Syst Sig Process2009; 23(3): 724–739.
11.
CobleJHinesJW.Identifying optimal prognostic parameters from data: a genetic algorithms approach. In: Proceedings of the annual conference of the prognostics and health management society, San Diego, CA, 23September2009.
12.
BrothertonTJahnsGJacobsJ, et al. Prognosis of faults in gas turbine engines. In: Proceedings of the 2000 IEEE aerospace conference, Big Sky, MT, 25March2000, pp. 163–171. New York: IEEE.
13.
FinkOZioEWeidmannU.Predicting component reliability and level of degradation with complex-valued neural networks. Reliab Eng Syst Safe2014; 121: 198–206.
14.
MahamadAKSaonSHiyamaT.Predicting remaining useful life of rotating machinery based artificial neural network. Comp Math Appl2010; 60(4): 1078–1087.
15.
TianZ.An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring. J Intel Manuf2012; 23(2): 227–237.
16.
BenkedjouhTMedjaherKZerhouniN, et al. Remaining useful life estimation based on nonlinear feature reduction and support vector regression. Eng Appl Artif Intel2013; 26(7): 1751–1760.
17.
TianZZuoMJ. Health condition prognostics of gears using a recurrent neural network approach. In: Proceedings of the 2009 reliability and maintainability symposium, Fort Worth, TX, 26–29January2009, pp. 460–465. New York: IEEE.
18.
RojasR. The back propagation algorithm. In: FeldmanJ (ed.) Neural networks. Berlin; Heidelberg: Springer, 1996, pp. 149–182.
19.
HuangRXiLLiX, et al. Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods. Mech Syst Sig Process2007; 21(1): 193–207.
20.
TsePWAthertonDP.Prediction of machine deterioration using vibration based fault trends and recurrent neural networks. J Vib Acoust1999; 121(3): 355–362.
21.
LeeJNiJDjurdjanovicD, et al. Intelligent prognostics tools and e-maintenance. Comp Ind2006; 57(6): 476–489.
22.
GebraeelNLawleyMLiuR, et al. Residual life predictions from vibration-based degradation signals: a neural network approach. IEEE T Ind Electron2004; 51(3): 694–700.
23.
WuSJGebraeelNLawleyMA, et al. A neural network integrated decision support system for condition-based optimal predictive maintenance policy. IEEE T Syst Man Cybern Part A: Syst Human2007; 37(2): 226–236.
24.
KuoWZuoMJ.Optimal reliability modeling: principles and applications. New York: John Wiley & Sons, 2003.
25.
TianZWongLSafaeiN.A neural network approach for remaining useful life prediction utilizing both failure and suspension histories. Mech Syst Sig Process2010; 24(5): 1542–1555.
26.
AkansuANSerdijnWASelesnickIW.Emerging applications of wavelets: a review. Phys Commun2010; 3(1): 1–18.
27.
LiuJ.Shannon wavelet spectrum analysis on truncated vibration signals for machine incipient fault detection. J Meas Sci Technol2012; 23(5): 055604.
28.
WeiZGaoJZhongX, et al. Incipient fault diagnosis of rolling element bearing based on wavelet packet transform and energy operator. WSEAS T Syst2011; 10(3): 81–90.
29.
ChebilJNoelNMesbahM, et al. Wavelet decomposition for the detection and diagnosis of faults in rolling element bearings. Jordan J Mech Ind Eng2009; 3(4): 260–267.
30.
RafieeJTsePHarifiA, et al. A novel technique for selecting mother wavelet function using an intelligent fault diagnosis system. Expert Syst Appl2009; 36: 4862–4875.
31.
LiFZhaoCDingG, et al. A reliable and accurate indoor localization method using phone inertial sensors. In: Proceedings of the 2012 ACM conference on ubiquitous computing, Pittsburgh, PA, 5–8 September 2012, pp. 421–430. New York: ACM.
BengioYSimardPFrasconiP.Learning long-term dependencies with gradient descent is difficult. IEEE T Neur Netw1994; 5(2): 157–166.
34.
HochreiterS.The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int J Uncert Fuzz Knowl-Based Syst1998; 6(2): 107–116.
ChoKVan MerrienboerBGulcehreC, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv, 2014, https://arxiv.org/abs/1406.1078
37.
BreimanLFriedmanJHOlshenRA, et al. Classification and regression trees. Boca Raton, FL: CRC Press, 1984.
38.
EfronBTibshiraniR.Statistical data analysis in the computer age. Science1991; 253(5018): 390–395.
39.
VenablesWNRipleyBD.Modern applied statistics with S-Plus. New York: Springer, 1997.
40.
LydiaMKumarSSSelvakumarAI, et al. Linear and non-linear autoregressive models for short-term wind speed forecasting. Energ Conv Manage2016; 112: 115–124.
41.
GeMKerriganEC.Short-term ocean wave forecasting using an autoregressive moving average model. In: Proceedings of the 2016 UKACC 11th international conference on control (CONTROL), Belfast, 2016, pp. 1–6. New York: IEEE.
42.
PanJMaHJiangX, et al. Adaptive gradient-based iterative algorithm for multivariable controlled autoregressive moving average systems using the data filtering technique. Complexity2018; 2018: 9598307.
43.
LiMLiuXDingF.The maximum likelihood least squares based iterative estimation algorithm for bilinear systems with autoregressive moving average noise. J Franklin Inst2017; 354(12): 4861–4881.
44.
TreleaIC.The particle swarm optimization algorithm: convergence analysis and parameter selection. Inf Process Letter2003; 85(6): 317–325.
45.
ElberhartRKennedyJ.A new optimizer using particle swan theory. In MHS 1995, Proceeding of Sixth international symposium on micro machine and human science IEEE 1995 oct 4; pp 39–43.
46.
GongMCaiQChenX, et al. Complex network clustering by multiobjective discrete particle swarm optimization based on decomposition. IEEE T Evol Comput2014; 18: 82–97.
47.
LiZHeLLiY.A novel multiobjective particle swarm optimization algorithm for signed network community detection. Appl Intell2016; 44: 621–633.
