Modern products have tended to gain increasingly complex structures, and most of them have multiple dependent performance indicators (PIs), which makes the degradation modeling and reliability prediction of such products challenging. For some products, based on the design of the products, their PIs are influenced by some common underlying components called clusters in this paper, thus they are correlated. Besides, in engineering practice, products may suffer from a dynamic environment that causes difficulties in reliability analyses. To address these situations, this paper proposes a multivariate degradation model based on the Wiener process and establishes the correlation among the PIs in a flexible and intelligible way. The effect of the dynamic environment on the degradation rate is considered to be a multiplication form. The expectation-maximization (EM) algorithm is utilized to achieve an accurate estimation of the model parameters. The expression of the reliability function of the product is obtained by a tangent approximation approach. In the end, a simulation study and a case study are presented to demonstrate the effectiveness and application of the proposed model.
ZioE. Some challenges and opportunities in reliability engineering. IEEE Trans Reliab2016; 65(4): 1769–1782.
2.
ChookahMNuhiMModarresM. A probabilistic physics-of-failure model for prognostic health management of structures subject to pitting and corrosion-fatigue. Reliab Eng Syst Saf2011; 96(12): 1601–1610.
3.
XuDWeiQElsayedEA, et al. Multivariate degradation modeling of smart electricity meter with multiple performance characteristics via vine copulas. Qual Reliab Eng Int2017; 33(4): 803–821.
4.
MeekerWQEscobarLA. Statistical Methods for Reliability Data. New York, NY: Wiley, 1998.
5.
LuCJMeekerWO. Using degradation measures to estimate a time-to-failure distribution. Technometrics1993; 35(2): 161–174.
6.
NelsonW. Accelerated testing statistical models, test plans, and data analysis. New York, NY: John Wiley, 1990.
7.
GebraeelNElwanyAPanJ. Residual life predictions in the absence of prior degradation knowledge. IEEE Trans Reliab2009; 58(1): 106–117.
8.
ParkCPadgettWJ. New cumulative damage models for failure using stochastic processes as initial damage. IEEE Trans Reliab2005; 54(3): 530–540.
9.
JiangLFengQCoitDW. Modeling zoned shock effects on stochastic degradation in dependent failure processes. IIE Trans2015; 47(5): 460–470.
10.
WangXBalakrishnanNGuoB. Residual life estimation based on a generalized Wiener degradation process. Reliab Eng Syst Saf2014; 124: 13–23.
11.
KongDBalakrishnanNCuiL. Two-phase degradation process model with abrupt jump at change point governed by wiener process. IEEE Trans Reliab2017; 66(4): 1345–1360.
12.
LawlessJCrowderM. Covariates and random effects in a gamma process model with application to degradation and failure. Lifetime Data Anal2004; 10(3): 213–227.
YeZSChenN. The inverse Gaussian process as a degradation model. Technometrics2014; 56(3): 302–311.
15.
PanDLiuJ-BCaoJ. Remaining useful life estimation using an inverse Gaussian degradation model. Neurocomputing2016; 185(12): 64–72.
16.
ShuYFengQKaoEPC, et al. Lévy-driven non-Gaussian Ornstein–Uhlenbeck processes for degradation-based reliability analysis. IIE Trans2016; 48(11): 993–1003.
17.
ShiYFengQShuY, et al. Multi-dimensional Lévy processes with Lévy copulas for multiple dependent degradation processes in lifetime analysis. Qual Eng2020; 32(3): 434–448.
18.
PanZBalakrishnanNSunQ, et al. Bivariate degradation analysis of products based on Wiener processes and copulas. J Stat Comput Simul2013; 83(7): 1316–1329.
19.
LiPLiuKDangW, et al. Reliability assessment of NAND SSD based on acceleration degradation test. In: 2017 IEEE International conference on industrial engineering and engineering management (IEEM), Singapore, 10–13 December 2017, pp.1945–1949.
20.
XiaogangLPengX. Multivariate storage degradation modeling based on copula function. Adv Mech Eng2014; 6: 1–7.
21.
WangPCoitDW. Reliability prediction based on degradation modeling for systems with multiple degradation measures. In: Annual symposium reliability and maintainability, 2004 - RAMS, Los Angeles, CA, 26–29 January 2004, pp.302–307.
22.
PanJWangXChenW, et al. Statistical analysis on accelerated degradation test data based on multiple performance parameters. In: International conference on Frontiers of advanced materials and engineering technology (FEMET 2012), Xiamen, China, 4–5 January 2012, vol. 430–432, pp.1417–1423.
23.
JinGMatthewsD. Measurement plan optimization for degradation test design based on the bivariate Wiener process. Qual Reliab Eng Int2014; 30: 1215–1231.
24.
PanZBalakrishnanN. Reliability modeling of degradation of products with multiple performance characteristics based on gamma processes. Reliab Eng Syst Saf2011; 96(8): 949–957.
25.
SariJKNewbyMJBrombacherAC, et al. Bivariate constant stress degradation model: LED lighting system reliability estimation with two-stage modelling. Qual Reliab Eng Int2009; 25(8): 1067–1084.
26.
WangXBalakrishnanNGuoB, et al. Residual life estimation based on bivariate non-stationary gamma degradation process. J Stat Comput Simul2015; 85(2): 405–421.
27.
PengWLiYFYangY-J, et al. Bivariate analysis of incomplete degradation observations based on inverse Gaussian processes and copulas. IEEE Trans Reliab2016; 65(2): 624–639.
28.
FangGPanRHongY. Copula-based reliability analysis of degrading systems with dependent failures. Reliab Eng Syst Saf2020; 193: 106618.
29.
XuAShenLWangB, et al. On modeling bivariate wiener degradation process. IEEE Trans Reliab2018; 67(3): 897–906.
30.
SunQYeZSHongY. Statistical modeling of multivariate destructive degradation tests with blocking. Technometrics2020; 62(4): 536–548.
31.
YousefiNCoitDWSongS. Reliability analysis of systems considering clusters of dependent degrading components. Reliab Eng Syst Saf2020; 202: 1–14.
32.
BianLGebraeelN. Stochastic methodology for prognostics under continuously varying environmental profiles. Stat Anal Data Min ASA Data Sci J2013; 6(3): 260–270.
33.
LiaoHTianZ. A framework for predicting the remaining useful life of a single unit under time-varying operating conditions. IIE Trans2013; 45(9): 964–980.
34.
HongYDuanYMeekerWQ, et al. Statistical methods for degradation data with dynamic covariates information and an application to outdoor weathering data. Technometrics2015; 57(2): 180–193.
35.
RafieeKFengQCoitDW. Reliability assessment of competing risks with generalized mixed shock models. Reliab Eng Syst Saf2017; 159: 1–11.
36.
HuangTPengBCoitDW, et al. Degradation modeling and lifetime prediction considering effective shocks in a dynamic environment. IEEE Trans Reliab2019; 68(3): 819–830.
37.
MercierSMeier-HirmerCRoussignolM. Bivariate gamma wear processes for track geometry modelling, with application to intervention scheduling. Struct Infrastruct Eng2012; 8(4): 357–366.
38.
LiuYFanX. Gaussian copula–Bayesian dynamic linear model–based time-dependent reliability prediction of bridge structures considering nonlinear correlation between failure modes. Adv Mech Eng2016; 8(11): 1–15.
39.
PanJBaiGChenW. Lifetime estimation of nitrile butadiene rubber O-rings under storage conditions using time-varying copula. Proc IMechE, Part O: J Risk and Reliability2018; 232(6): 635–646.
40.
LiJWangZLiuX, et al. A Wiener process model for accelerated degradation analysis considering measurement errors. Microelectron Reliab2016; 65: 8–15.
41.
ShiauJ-JHLinH-H. Analyzing accelerated degradation data by nonparametric regression. IEEE Trans Reliab1999; 48(2): 149–158.
42.
LiaoC-MTsengS-T. Optimal design for step-stress accelerated degradation tests. IEEE Trans Reliab2006; 55(1): 59–66.
43.
PadgettWJTomlinsonMA. Inference from accelerated degradation and failure data based on Gaussian process models. Lifetime Data Anal2004; 10(2): 191–206.
44.
ParkCPadgettWJ. Accelerated degradation models for failure based on geometric Brownian motion and gamma processes. Lifetime Data Anal2005; 11: 511–527.
45.
DempsterAPLairdNMRubinDB. Maximum likelihood from incomplete data via theEMAlgorithm. J R Stat Soc Ser B1977; 39(1): 1–22.
46.
EfronBTibshiraniR. An introduction to the Bootstrap. Teach Stat2001; 23(2): 49–54.
47.
WangXBalakrishnanNGuoB. Residual life estimation based on nonlinear-multivariate Wiener processes. J Stat Comput Simul2015; 85(9): 1742–1764.
48.
DanielsHE. Approximating the first crossing-time density for a curved boundary. Bernoulli1996; 2(2): 133–143.
49.
ElsayedEA. Reliability engineering. 2nd ed.New York, NY: Jhon Wiley, 2013.
50.
YangZChenYXLiYF, et al. Smart electricity meter reliability prediction based on accelerated degradation testing and modeling. Int J Electr Power Energy Syst2014; 56: 209–219.
51.
LiaoHElsayedEA. Reliability inference for field conditions from accelerated degradation testing. Nav Res Logist2006; 53(6): 576–587.
