In most data-driven prognostics approaches, features extracted from measurements are used in the model to indicate the degradation process and determine the reliability in real time. However, many features with physical meaning commonly exhibit no variation until a failure occurs, which leaves little time to conduct maintenance strategies or replacement policies. Hence, this research presents a novel feature-selection criterion, which enables to select a feature with an obvious trend throughout the entire life, thereby avoiding the problem mentioned. In addition, for reliability estimation and condition monitoring, an innovative model-building method based on identical statistical features extracted from multi-signals is developed, in which the features are considered to be dependent and governed by a copula function. An example is provided to illustrate the application of the proposed two-step methods. The result shows that this method is more convincible and realistic for reliability estimation.
LuCJMeekerWQ. Using degradation measures to estimate a time-to-failure distribution. Technometrics1993; 35: 161–174.
2.
ZuoMJJiangRYYamRCMet al. Approaches for reliability modeling of continuous-state devices. IEEE T Reliab1999; 48: 9–18.
3.
HongSZhouZZioEet al. An adaptive method for health trend prediction of rotation bearings. Digit Signal Process2014; 35: 117–123.
4.
LiaoLXKöttigF. Review of hybrid prognostic approaches for remaining useful life prediction of engineered systems, and an application to battery life prediction. IEEE T Reliab2014; 63: 191–207.
5.
ZhaoZYQuanQCaiKY. A profust reliability based approach to prognostics and health management. IEEE T Reliab2014; 63: 26–41.
6.
LiRYSoponPHeDet al. Fault features extraction for bearing prognostics. J Intell Manuf2012; 23: 313–321.
7.
CobleJHinesJW. Identifying optimal prognostic parameters from data: a genetic algorithms approach. In: IEEE international conference on prognostics and health management society, San Diego, CA, USA, 27 September-1 October 2009, pp. 1–11. New York: IEEE.
8.
LiaoLX. Discovering prognostic features using genetic programming in remaining useful life prediction. IEEE T Ind Electron2014; 61: 2464–2472.
9.
JavedKGouriveauRZerhouniNet al. Enabling health monitoring approach based on vibration data for accurate prognostics. IEEE T Ind Electron2015; 62: 647–656.
10.
NembhardADSinhaJKPinkertonAJet al. Combined vibration and thermal analysis for the condition monitoring of rotating machinery. Struct Health Monit2014; 13: 281–295.
11.
WangPCoitDW. Reliability prediction based on degradation modeling for systems with multiple degradation measures. In: IEEE symposium on reliability and maintainability, Los Angeles, CA, 26–29 January 2004, pp. 302–307. New York: IEEE.
12.
MosallamAMedjaherKZerhouniN. Time series trending for condition assessment and prognostics. J Manuf Tech Manag2013; 25: 550–567.
13.
LiuKBGebraeelNZShiJJ. A data-level fusion model for developing composite health indices for degradation modeling and prognostic analysis. IEEE T Autom Sci Eng2013; 10: 652–664.
14.
PanZQBalakrishnanNSunQet al. Bivariate degradation analysis of products based on Wiener processes and copulas. J Stat Comput Sim2013; 83: 1316–1329.
15.
NectouxPGouriveauRMedjaherKet al. PRONOSTIA: an experimental platform for bearings accelerated degradation test. In: IEEE international conference on prognostics and health management, Denver, CO, 18–21 June, 2012, pp. 1–8. New York: IEEE.
16.
PanYChenJGuoL. Robust bearing performance degradation assessment method based on improved wavelet packet-support vector data description. Mech Syst Signal Pr2009; 23: 669–681.
17.
CongFYChenJDongGMet al. Vibration model of rolling element bearings in a rotor-bearing system for fault diagnosis. J Sound Vib2013; 332: 2081–2097.
18.
CrkV. Reliability assessment from degradation data. In: IEEE symposium on reliability and maintainability, Los Angeles, CA, 24–27 January 2000, pp. 155–161. New York: IEEE.
19.
XuDZhaoWB. Reliability prediction using multivariate degradation data. In: IEEE symposium on reliability and maintainability, Alexandria, VA, USA, 24–27 January 2005, pp. 337–341.
20.
WangYPPhamH. Modeling the dependent competing risks with multiple degradation processes and random shock using time-varying copulas. IEEE T Reliab2012; 61: 13–22.
21.
YangQYHongYLZhangNLet al. A copula-based trend-renewal process model for analysis of repairable systems with multitype failures. IEEE T Reliab2017; 66: 1–13.
22.
XuDSuiSB. Bivariate degradation modeling and reliability evaluation of accelerometer based on physics-statistics model and copula function. In: International conference on reliability system engineering, Beijing, China, 21–23 October 2015, pp. 1–7. New York: IEEE.
23.
ZhangXPShangJZChenXet al. Statistical inference of accelerated life testing with dependent competing failures based on copula theory. IEEE T Reliab2014; 63: 764–780.
24.
GillSStephenBGallowayS. Wind turbine condition assessment through power curve copula modeling. IEEE T Sustain Energ2012; 3: 94–101.
25.
NelsenRB. An introduction to copulas. 2nd ed.New York: Springer2006.
26.
MaruBZotosPA. Anti-friction bearing temperature rise for NEMA frame motors. In: Annual petroleum & chemical industry conference, Dallas, TX, 12–14 September 1988, pp. 883–888. New York: IEEE.
27.
ZhouWHabetlerTGHarleyRG. Bearing condition monitoring methods for electric machines: a general review. In: IEEE international symposium on diagnostics for electric machines, power electronics & drives, Cracow, 6–8 September 2007, pp. 3–6. New York: IEEE.
28.
WangPCoitDW. Reliability and degradation modeling with random or uncertain failure threshold. In: IEEE symposium on reliability and maintainability, Orlando, FL, 22–25 January 2007, pp. 392–397. New York: IEEE.
