Professional Documents
Culture Documents
LEER
LEER
net/publication/318917280
CITATIONS READS
4 346
4 authors, including:
Wei Zhang
Beihang University (BUAA)
18 PUBLICATIONS 135 CITATIONS
SEE PROFILE
Some of the authors of this publication are also working on these related projects:
Reliability Modeling of the dependent competing failure systems with multiple degradation processes and random shocks View project
Relative entropy based Bayesian design for accelerated degradation testing View project
All content following this page was uploaded by Fuqiang Sun on 13 September 2017.
Received June 1, 2017, accepted July 18, 2017, date of publication August 4, 2017, date of current version September 6, 2017.
Digital Object Identifier 10.1109/ACCESS.2017.2735966
ABSTRACT Degradation modeling and remaining useful life (RUL) prediction for products with multiple
degradation features are hot topics in the prognostic and health management. The key to this problem is
to describe the dependence among multiple degradation features effectively. In this paper, a multivariate
degradation modeling approach based on the Bayesian dynamic linear model (BDLM) is proposed to
calculate the RULs of degradation features, and the Copula function is employed to capture the dependence
among RUL distributions. A combined BDLM is used to establish the multivariate degradation model,
which includes two typical BDLMs, namely, the linear growth model and seasonal factors model. After
the model parameters get calibrated by the maximum likelihood estimation, the model can predict the
degradation process of features. Once the failure thresholds are given, the probability density function
and cumulative distribution function (CDF) of RUL for each degradation feature can be obtained. Since
these RUL distributions are not independent of each other, the Copula function is adopted herein to couple
the CDFs. Finally, some practical testing data of a microwave component, which has two degradation
features, are utilized to validate our proposed method. This paper provides a new idea for the multivariate
degradation modeling and RUL prediction.
INDEX TERMS Multiple dependent features, Bayesian dynamic linear model, remaining useful life,
copulas.
I. INTRODUCTION They are low cost approaches and have the advantage
Prognostic and health management (PHM) has been inten- of better applicability [3]. Due to these advantages, data-
sively studied as an effective tool for managing life cycles of driven approaches have become the popular RUL predic-
machines and reducing maintenance cost. Degradation mod- tion methods. There have been excellent literature reviews
eling and remaining useful life (RUL) prediction is the core over the last decade on data driven approaches for RUL
of prognostics [1]. An accurate RUL prediction could provide prediction. Si et al. [2] reviewed the developments of the
the basis for maintenance decisions, spare parts provision, RUL estimation models based on statistical data driven
and preventing fatal failures. approaches. Javed et al. [3] performed a comprehensive sur-
The existing RUL prediction methods can be categorized vey on prognostics approaches and discussed the application
into two broad classes, i.e., physics of failure (PoF) models point of view for each category. They classified data-driven
and data-driven approaches [1]. The PoF models are achieved approaches as machine learning and statistical learning
on the basis of acquired knowledge of the failure mechanisms. approaches, and elaborated their close links. These reviews
However, it is difficult, if not impossible, to understand the papers cover most of RUL prediction methods. However, they
physical failure mechanisms of a complex component or sys- share one thing in common in that they only discussed the
tem. On the other hand, the data-driven approaches do not cases involving a single degradation feature.
rely on the failure mechanisms of machines, which only rely However, the machine degradation is usually reflected
on available past observed data and statistical models [2]. by several interrelated features. Such features may include
2169-3536
2017 IEEE. Translations and content mining are permitted for academic research only.
VOLUME 5, 2017 Personal use is also permitted, but republication/redistribution requires IEEE permission. 16277
See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
F. Sun et al.: RUL Prediction for a Machine With Multiple Dependent Features
II. A BAYESIAN DYNAMIC LINEAR MODEL FOR random changes of state vector, N (0, W ) is the multivariate
RUL PREDICTION normal distribution with mean 0 and covariance variance W .
A. BAYESIAN FORECASTING FRAMEWORK Both vt and wt are white-noise errors following normal dis-
The Bayesian forecasting establishes a relationship between tribution with a priori known variance matrices V and W ,
the prior information Dt−1 and the posteriori distribution respectively.
considering the new measurements from the updated infor- Next, two typical DLMs, namely linear growth and sea-
mation Dt . It can be represented by Bayes theorem as [23] sonal factors model, are briefly introduced.
p ŷt dt ∝ p ŷt dt−1 × p yt | ŷt , dt−1
(1)
1) LINEAR GROWTH MODEL
where ŷt is the predicted value in time t, yt is the obser- Linear growth model is a commonly used class of dynamic
vation data at time
t,p ŷt
dt is the posteriori distribution linear model, which assumes that the current level changes
given Dt , p ŷt dt−1 is the prior distribution given Dt−1 , linearly through time [7]. The state vector of linear growth
p yt | ŷt , dt−1 is the distribution of yt given ŷt and Dt−1 . model is θ t = [µt , βt ]0 , where µt and βt are the parameters
Equation (1) use the historical data and observation data of state vector θ t at time t, which are related to the corre-
for prediction, which is a standard Bayesian forecasting link- sponding state parameters at t − 1 by the state equation. The
priori information Dt−1 and posteriori distribution
ing the observation matrix Z and state matrix T can be expressed as
p ŷt dt using the new observation data yt from the updated Z = [1, 0], T = [1, 1; 0, 1]. Then, according to (2) and (3),
information Dt [23]. the linear growth model can be expressed as
establish a bivariate Bayesian dynamic linear model, in order where T2,i is state matrix of seasonal factors model for each
to model the bivariate dependent degradation process. degradation feature, i = 1, 2,
1) BIVARIATE LINEAR GROWTH MODEL −1 −1 ··· −1
(1) 1 0 ··· 0
In a bivariate linear growth model, yi,t is the ith observa-
T2,i = ..
(1)
tion data at time t, i = 1, 2. θ t is the state vector at .
time t. Z1 and T1 are the observation matrix and state matrix 0 0 1 0 (s−1)×(s−1)
respectively.
The observation equation is 3) COMBINED BIVARIATE BDLM
"
(1)
# The bivariate linear growth model and bivariate seasonal
y1,t (1)
(1) = Z1 θ t + vt (7) factors model are combined to establish the bivariate BDLM,
y2,t yi,t is the ith observation data at time t, i = 1, 2.
The state vector θ t consists of the state vector of linear
where vt is the observation error, vt ∼ N (0, V ), (1)
growth model θ t and the state vector of seasonal factors
(2)
1 0 0 0
model θ t , and can be expressed as θ t = [µ1,t , β1,t ,
Z1 = . µ2,t , β2,,t , α1 α2, , . . . , αs−1 , τ1 , τ2, , . . . , τs−1 ]0 . Then the
0 0 1 0
observation matrix Z and state matrix T can be
The state equation can be expressed as reformulated as
(1) (1)
θt = T1 θ t−1 + wt (8) Z = [Z1 , Z2 ] (11)
T1 0
(1) 0 T = (12)
where θ t = µ1,t , β1,t , µ2,t , β2,t , wt
is the state error, and 0 T2
1 1 0 0 Then, the observation equation can be represented by
0 1 0 0
wt ∼ N (0, V ), T1 = .
0 0 1 1 y1,t
0 0 0 1 = Z θ t + vt (13)
y2,t
2) BIVARIATE SEASONAL FACTORS MODEL Finally, the state equation can be expressed as
In a bivariate seasonal factors model, suppose the periods for
both of the degradation features are s, then a pure seasonal θ t = T θ t−1 + wt (14)
factors model without fluctuation is used to model the peri-
(2)
odic data. yi,t is the ith observation data at time t, i = 1, 2. D. PARAMETER ESTIMATION AND ITERATIVE UPDATING
(2)
θ t is the state vector at time t. Z2 and T2 are the observation 1) PARAMETER ESTIMATION
matrix and state matrix respectively. Maximum likelihood estimation (MLE) is used for the esti-
The observation equation is mation of model parameters, namely the covariance variance
V and W , which can be denoted as 9 = [V , W ].
(2)
" #
y1,t (2) The joint log-likelihood function for the measurement
(2) = Z2 θ t (9)
y2,t sequence y1:t and the state sequence θ1:t can be formulated
as [25]
where
L ( y1:t , θ 1:t | 9)
1 0 ··· 0 0 0 ··· 0
.
hYt Yt
Z2 =
i
0 0 ··· 0 1 0 ··· 0 2×(2s−2)
= log p ( y1:i | θ 1:i , 9) p ( θ 1:i | θ 1:i−1 , 9)
i=1 i=1
t t
The state equation can be expressed as = const − log |V | − log |W |
2 2
(2) (2) t
θt = T2 θ t−1 (10) −
1 X
(yi − Z θ i )T V −1 (yi − Z θ i )
2
(2) i=1
where θ t = [α1 , α2 , · · · , αs−1 , τ1 , τ2 , · · · , τs−1 ]0 , αj and τj t
are the seasonal factors of each degradation feature, j = 1X
− (θ i − T θ i−1 )T W −1 (θ i − T θ i−1 ) (15)
1, 2, . . . , s − 1. T2 is the state matrix of bivariate seasonal 2
i=1
factors model,
where p(·) represents the normal distribution.
T2,1 0 Then, the model parameters could be estimated by maxi-
T2 =
0 T2,2 mizing the joint log-likelihood function (15).
2) ITERATIVE UPDATING If all information has been known as Dall , and θ t+1 | Dall ∼
After constructing the degradation model using Bayesian N (st+1 , St+1 ), then θ t | Dall ∼ N (st , St ), where
dynamic linear model, it is significant to estimate the degra-
dation state. Once the new observation data are available, t+1 (st+1 − at+1 )
st = mt + Ct T 0 R−1 (23)
we could utilize the forward-recursive algorithm Kalman fil- St = t+1 (Rt+1
Ct − Ct T 0 R−1 − St+1 ) R−1
t+1 TCt (24)
tering and backward-recursive algorithm Kalman smoothing
to update the model parameters. This step is implemented until t = 0, then all the smooth-
ing data can be obtained.
a: KALMAN FILTERING
E. RUL PREDICTION OF EACH FEATURE
Kalman filtering can update the BDLM based on observed
data under Bayesian framework. It is a suitable choice for Using the established BDLM, it is convenient to predict the
the state estimating, due to the observation data yt and state degradation model, and calculate the corresponding RUL
vector θt follow normal distribution for any t ≥ 1 [9]. distribution for each degradation feature.
For a normal distribution, it can be determined once the The remaining useful life is defined as the time from the
mean and variance are given. The details of the filtering in current moment to the end of its useful life [2]. Commonly,
the Bayesian framework are presented as follows [24]. the end of useful life is the degradation curve passes through
Given the initial information: θ 0 |D0 ∼ N (m0 , C0 ), where a predefined failure threshold in the first time. The principle
m0 and C0 are the initial mean and standard deviation of state of the RUL prediction is illustrated as Fig. 3.
vector θ0 , θ 0 |D0 represents the initial knowledge given the
information D0 .
Step 1 initialization: At time t = 0, given the informa-
tion D0 , the initial parameters of θ is specified as
( θ 0 | D0 ) ∼ N (m0 , C0 ) (16)
A. COPULA THEORY
Copulas model separately the marginal distributions and
the joint-dependence structure [21]. The theoretical basis of
Copula function is Sklar ’s theorem [28], which proves the
existence and uniqueness of Copula function.
Sklar ’s theorem: Let H be a bivariate joint distribution
function with margins F(x) and G(y). Then there exists a
copula C such that for all x, y in R,
III. THE ESTIMATION OF JOINT RULs DISTRIBUTION where q denotes the number of unknown parameters in the
Section II has predicted the RUL distribution for each degra- model, ln(L) is the maximum value of the log-likelihood
dation feature. While, the machine’s RUL prediction is more function.
significant and meaningful in PHM, which reflects the con-
dition of a system. Since the multiple degradation features B. THE PDF OF THE MACHINE’S RUL DISTRIBUTION
are not independent with each other, it is not appropriate to Suppose Mi is the failure threshold for ith degradation fea-
ignore the dependency among multiple RUL distributions. tures, the remaining useful life RULi for ith degradation
FIGURE 10. The prediction of power gain B. (a) The prediction result.
(b) Partial enlarged view.
monitoring time of 374 day, 474 day and 574 day, Gaussian [14] J. Zhang, X. Ma, and Y. Zhao, ‘‘A stress-strength time-varying correlation
Copula is selected with the minimum AIC of −13.5743, interference model for structural reliability analysis using copulas,’’ IEEE
Trans. Rel., vol. 66, no. 2, pp. 351–365, Jun. 2017.
−13.3552, and −588.9102. Then, the joint PDFs of the [15] X. Zhang and A. Wilson, ‘‘System reliability and component importance
microwave machine’s RUL distribution at different monitor under dependence: A copula approach,’’ Technometrics, vol. 59, no. 2,
point are calculated and illustrated in Fig. 15, which can be pp. 215–224, 2017.
[16] F. Sun, L. Liu, X. Li, and H. Liao, ‘‘Stochastic modeling and analysis of
further used for maintenance decision-making. multiple nonlinear accelerated degradation processes through information
fusion,’’ Sensors, vol. 16, no. 8, p. 1242, Aug. 2016.
V. CONCLUSIONS [17] W. Peng, Y.-F. Li, Y.-J. Yang, S.-P. Zhu, and H.-Z. Huang, ‘‘Bivariate
analysis of incomplete degradation observations based on inverse Gaussian
This paper proposes a multivariate degradation modeling processes and copulas,’’ IEEE Trans. Rel., vol. 65, no. 2, pp. 624–639,
approach based on BDLM to calculate the RULs of degrada- Jun. 2016.
tion features. And the Copula method is employed to capture [18] Y. Wang and H. Pham, ‘‘Modeling the dependent competing risks with
multiple degradation processes and random shock using time-varying cop-
the dependency among RUL distributions. A practical testing ulas,’’ IEEE Trans. Rel., vol. 61, no. 1, pp. 13–22, Mar. 2012.
of the microwave machine with bivariate degradation features [19] S. K. Gupta, S. De, and A. Chatterjee, ‘‘Some reliability issues for
are utilized to validate the method. Some conclusions can be incomplete two-dimensional warranty claims data,’’ Rel. Eng., Syst. Safety,
vol. 157, pp. 64–77, Jan. 2017.
drawn. [20] Z. Xi, R. Jing, P. Wang, and C. Hu, ‘‘A copula-based sampling method
In the proposed method, the dependence of different degra- for data-driven prognostics,’’ Rel. Eng., Syst. Safety, vol. 132, pp. 72–82,
dation features is considered both in multivariate degradation Dec. 2014.
[21] H. Joe, Multivariate Models and Multivariate Dependence Concepts,
modeling and RUL prediction, which can account for the 1st ed. Boca Raton, FL, USA: CRC Press, 1997.
dependence sufficiently and effectively. It provides a good [22] X. Wang, N. Balakrishnan, and B. Guo, ‘‘Residual life estimation based on
alternative for the degradation modeling with multiple degra- nonlinear-multivariate Wiener processes,’’ J. Stat. Comput. Simul., vol. 85,
pp. 1742–1764, Jun. 2015.
dation features. [23] X. Fei, C. C. Lu, and K. Liu, ‘‘A Bayesian dynamic linear model approach
The current study just selects two typical BDLMs, linear for real-time short-term freeway travel time prediction,’’ Transp. Res. C-
growth model and seasonal factors model. In the future, more Emerg. Technol., vol. 19, pp. 1306–1318, Dec. 2011.
[24] G. Petris, S. Petrone, and P. Campagnoli, Dynamic Linear Models With R.
types of BDLM should be investigated. New York, NY, USA: Springer-Verlag, 2009.
[25] X. Xu and N. Chen, ‘‘A state-space-based prognostics model for lithium-
REFERENCES ion battery degradation,’’ Rel. Eng., Syst. Safety, vol. 159, pp. 47–57,
[1] M. Pecht, Prognostics and Health Management of Electronics. New York, Mar. 2017.
NY, USA: Wiley, 2008. [26] R. Prado and M. West, Time Series Modeling, Computation, and Inference.
[2] X.-S. Si, W. Wang, C.-H. Hu, and D.-H. Zhou, ‘‘Remaining useful life New York, NY, USA: Taylor & Francis, 2010.
estimation—A review on the statistical data driven approaches,’’ Eur. J. [27] A. W. Bowman and A. Azzalini, Applied Smoothing Techniques for Data
Oper. Res., vol. 213, pp. 1–14, Aug. 2011. Analysis, 2nd ed. New York, NY, USA: Oxford Univ. Press, 1997.
[3] K. Javed, R. Gouriveau, and N. Zerhouni, ‘‘State of the art and taxonomy [28] A. Sklar, Fonctions de Répartition à n Dimensions et Leurs Marges, vol. 8.
of prognostics approaches, trends of prognostics applications and open l’Institut de Statistique de L’Université de Paris, 1959, pp. 229–231.
issues towards maturity at different technology readiness levels,’’ Mech. [29] R. B. Nelsen, An Introduction to Copulas, 2nd ed. New York, NY, USA:
Syst. Signal Process., vol. 94, pp. 214–236, Sep. 2017. Springer, 2007.
[4] S. Kumar and M. Pecht, ‘‘Modeling approaches for prognostics and health
management of electronics,’’ Int. J. Performability Eng., vol. 6, no. 5,
pp. 467–476, Sep. 2010.
[5] J. Lee, F. Wu, W. Zhao, M. Ghaffari, L. Liao, and D. Siegel, ‘‘Prognostics
and health management design for rotary machinery systems-reviews,
methodology and applications,’’ Mech. Syst. Signal Process., vol. 42, FUQIANG SUN received the Ph.D. degree in
pp. 314–334, Jan. 2014. systems engineering from Beihang University,
[6] L. M. M. Lima, E. Popova, and P. Damien, ‘‘Modeling and forecasting of Beijing, China, in 2012, where he is currently an
Brazilian reservoir inflows via dynamic linear models,’’ Int. J. Forecasting, Assistant Professor with the Science and Technol-
vol. 30, no. 3, pp. 464–476, 2014. ogy on Reliability and Environmental Engineer-
[7] S. Zhang and W. Zhou, ‘‘Bayesian dynamic linear model for growth of ing Laboratory, School of Reliability and Systems
corrosion defects on energy pipelines,’’ Rel. Eng., Syst. Safety, vol. 128, Engineering. His research interests include accel-
pp. 24–31, 2014. erated degradation/life testing, prognostics, com-
[8] S. Bouaddi, A. Ihlal, and A. Fernández-García, ‘‘Soiled CSP solar reflec-
peting risk, and multivariate statistical analysis.
tors modeling using dynamic linear models,’’ Solar Energy, vol. 122,
pp. 847–863, Dec. 2015.
[9] M. West and J. Harrison, Bayesian Forecasting and Dynamic Models,
2nd ed. New York, NY, USA: Springer-Verlag, 1997.
[10] K. Triantafyllopoulos, ‘‘Multivariate stochastic volatility with Bayesian
dynamic linear models,’’ J. Stat. Planning Inference, vol. 138, no. 4,
pp. 1021–1037, Apr. 2008.
[11] E. H. Lau, C. K. Cheng, D. K. Ip, and B. J. Cowling, ‘‘Situational awareness
NING WANG received the B.S. degree in product
of influenza activity based on multiple streams of surveillance data using quality engineering from China Jiliang University
multivariate dynamic linear model,’’ PLoS One, vol. 7, no. 5, p. e38346, in 2015. He is currently pursuing the master’s
2012. degree with the Science and Technology on Relia-
[12] H.-S. Lee, Y.-C. Shih, H.-M. Wang, and S.-K. Jeng, ‘‘Subspace-based bility and Environmental Engineering Laboratory,
phonotactic language recognition using multivariate dynamic linear mod- School of Reliability and Systems Engineering,
els,’’ in Proc. 38th IEEE Int. Conf. Acoust., Speech, Signal Pro- Beihang University. His research interests focus on
cess., (ICASSP), Vancouver, BC, Canada, May 2013, pp. 6870–6874. life prediction and accelerated test modeling.
[13] S. Lu, H. Lu, and W. J. Kolarik, ‘‘Multivariate performance reliability pre-
diction in real-time,’’ Rel. Eng., Syst. Safety, vol. 72, pp. 39–45, Apr. 2001.
XIAOYANG LI received the Ph.D. degree in WEI ZHANG received the Ph.D. degree in engi-
aerospace systems engineering from Beihang Uni- neering from Clarkson University in 2012. He was
versity, Beijing, China, in 2007. She is currently an with Arizona State University as an Assistant
Associate Professor with the School of Reliabil- Research Scientist. He is currently an Associate
ity and Systems Engineering, Beihang University. Professor of reliability and systems engineer-
Her research interests include life modeling and ing with Beihang University. His research areas
optimal test design for accelerated testing, and include fatigue and fracture mechanics, structure
quantification method of uncertainty. reliability, and life prediction.