This article proposes a component-level predictive maintenance scheduling framework in which system residual life prediction information is utilized. In the proposed framework, predictive maintenance scheduling is only triggered when a system is close to failure. A lifetime margin is used to infer that a system is close to failure but still safely operational when predictive maintenance scheduling is triggered. Some technical elements are detailed to facilitate the implementation of the proposed framework. A simulation study based on an example predictive maintenance scheduling framework (framework B) is provided to illustrate the implementation of the proposed framework, and compare framework B with the corresponding counterpart only consisting of predictive maintenance scheduling models (framework A). Given a relatively low noise level of system degradation processes, compared with the classical prognostics framework only consisting of predictive maintenance scheduling models, the proposed framework is similarly effective in failure prevention and more economic in that several premature preventive maintenance acts are saved.
JardineAKSLinDBanjevicD. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech Syst Sig Process2006; 20(7): 1483–1519.
2.
HengAZhangSTanACC. Rotating machinery prognostics: State of the art, challenges and opportunities. Mech Syst Sig Process2009; 23(3): 724–739.
3.
Camci F. Process monitoring, diagnostics and prognostics using support vector machines and hidden Markov models. PhD Dissertation, Wayne State University, MI, 2005.
4.
DjurdjanovicDLeeJNiJ. Watchdog agent – An infotronics-based prognostics approach for product performance degradation assessment and prediction. Adv Eng Inf2003; 17(3–4): 109–125.
5.
YamRCMTsePWLiL. Intelligent predictive decision support system for condition-based maintenance. Int J Adv Manuf Technol2001; 17(5): 383–391.
6.
RoyATangiralaS. Stochastic modeling of fatigue crack dynamics for on-line failure prognostics. IEEE Trans Control Syst Technol1996; 4(4): 443–451.
7.
KacprzynskiGJSarlashkarARoemerMJ. Predicting remaining life by fusing the physics of failure modeling with diagnostics. JOM2004; 56(3): 29–35.
8.
LiCJLeeH. Gear fatigue crack prognosis using embedded model, gear dynamic model and fracture mechanics. Mech Syst Sig Process2005; 19(4): 836–846.
9.
GuJBarkerDPechtM. Prognostics implementation of electronics under vibration loading. Microelectron Reliab2007; 47(12): 1849–1856.
10.
GebraeelNLawleyMLiuR. Residual life predictions from vibration-based degradation signals: A neural network approach. IEEE Trans Ind Electron2004; 51(3): 694–700.
11.
BaruahPChinnamRB. HMMs for diagnostics and prognostics in machining processes. Int J Prod Res2005; 43(6): 1275–1293.
12.
HuangRXiLLiX. 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.
13.
ZioEMaioFD. A data-driven fuzzy approach for predicting the remaining useful life in dynamic failure scenarios of a nuclear system. Reliab Eng Syst Saf2010; 95(1): 49–57.
14.
EngelSJGilmartinBJBongortK. Prognostics, the real issues involved with prediction life remaining. Proceedings of IEEE aerospace conference, 18–25 March 2000, Big Sky, MT457–470.
GallADieulleLBerenguerC. Continuous-time predictive maintenance scheduling for a deteriorating system. IEEE Trans Reliab2002; 51(2): 141–150.
17.
ChristerAHWangWSharpJM. A state space condition monitoring model for furnace erosion prediction and replacement. Eur J Oper Res1997; 101(1): 1–14.
18.
LiLYouM-YNiJ. Reliability-based dynamic maintenance threshold for failure prevention of continuously monitored degrading systems. J Manuf Sci Eng, Trans ASME2009; 31(3): 031010(1–9).
19.
KaiserKAGebraeelN. Predictive maintenance management using sensor-based degradation models. IEEE Trans Syst Man Cybern Part A: Syst Humans2009; 39(4): 840–849.
20.
YouM-YLiLMengG. Cost-effective updated sequential predictive maintenance policy for continuously monitored degrading systems. IEEE Trans Autom Sci Eng2010; 7(2): 257–265.
21.
SikorskaJZHodkoewiczMMaL. Prognostics modeling options for remaining useful life estimation by industry. Mech Syst Sig Process2011; 25(5): 1803–1836.
22.
ZhangJLeeJ. A review on prognostics and health monitoring of Li-ion battery. J Power Sources2011; 196(15): 6007–6014.
23.
FanHHuCChenM. Cooperative predictive maintenance of repairable systems with dependent failure modes and resource constraint. IEEE Trans Reliab2011; 60(1): 144–157.
24.
CamciF. System maintenance scheduling with prognostics information using genetic algorithm. IEEE Trans Reliab2009; 58(3): 539–552.
25.
GebraeelNLawleyMALiR. Residual-life distributions from component degradation signals: A Bayesian approach. IIE Trans2005; 37(6): 543–557.
26.
WangW. A model to predict the residual life of rolling element bearing given monitored condition information to date. IMA J Manage Math2002; 13(1): 3–16.
27.
LuHKolarikWJLuSS. Real-time performance reliability prediction. IEEE Trans Reliab2001; 50(4): 353–357.
28.
XuZJiYZhouD. Real-time reliability prediction for a dynamic system based on hidden degradation process identification. IEEE Trans Reliab2008; 57(2): 230–242.
29.
ChinnamRB. On-line reliability estimation of individual components using statistical degradation signal models. Qual Reliab Eng Int2002; 18(1): 53–73.
WangH. A survey of maintenance policies of deteriorating systems. Eur J Oper Res2002; 139(3): 469–489.
32.
ZhouXXiLLeeJ. Reliability-centered predictive maintenance scheduling for a continuously monitored system subject to deterioration. Reliab Eng Syst Saf2007; 92(4): 530–534.
33.
LinDZuoMJYamRCM. Sequential imperfect preventive maintenance models with two categories of failure modes. Nav Res Logist2001; 48(2): 172–183.
34.
MeekerWQEscobarLA. Statistical methods for reliability data, New York: Wiley, 1998.
35.
LuSLuHKolarikWJ. Multivariate performance reliability prediction in real-time. Reliab Eng Syst Saf2001; 72(1): 39–45.
36.
ChinnamRBBaruahP. A neuro-fuzzy approach for estimating mean residual life in condition-based maintenance systems. Int J Mater Prod Technol2004; 20(1–3): 166–179.
37.
LiaoHZhaoWGuoH. Predicting remaining useful life of an individual unit using proportional hazards model and logistic regression model. Proceedings of annual reliability and maintainability symposium, 23–26 January 2006, Newport Beach, CA127–132.
38.
YanHKogMLeeJ. A prognostics algorithm for machine performance assessment and its application. Prod Plann Control2004; 15(8): 796–801.
39.
CamciFChinnamRB. Hierarchical HMMs for autonomous diagnostics and prognostics. Proceedings of IEEE international conference on neural networks, 16–21 July 2006, Vancouver, BC2445–2452.
40.
YouM-YLiuFWangW. Statistically planned and individually improved predictive maintenance management for continuously monitored degrading systems. IEEE Trans Reliab2010; 59(4): 744–753.
