Remaining useful life prediction for engineering systems under dynamic operational conditions: A semi-Markov decision process-based approach
|
摘要
For critical engineering systems such as aircraft and aerospace vehicles, accurate Remaining Useful Life(RUL) prediction not only means cost saving, but more importantly, is of great significance in ensuring system reliability and preventing disaster. RUL is affected not only by a system's intrinsic deterioration, but also by the operational conditions under which the system is operating. This paper proposes an RUL prediction approach to estimate the mean RUL of a continuously degrading system under dynamic operational conditions and subjected to condition monitoring at short equi-distant intervals. The dynamic nature of the operational conditions is described by a discrete-time Markov chain, and their influences on the degradation signal are quantified by degradation rates and signal jumps in the degradation model. The uniqueness of our proposed approach is formulating the RUL prediction problem in a semi-Markov decision process framework, by which the system mean RUL can be obtained through the solution to a limited number of equations. To extend the use of our proposed approach in real applications, different failure standards according to different operational conditions are also considered. The application and effectiveness of this approach are illustrated by a turbofan engine dataset and a comparison with existing results for the same dataset.
For critical engineering systems such as aircraft and aerospace vehicles, accurate Remaining Useful Life(RUL) prediction not only means cost saving, but more importantly, is of great significance in ensuring system reliability and preventing disaster. RUL is affected not only by a system's intrinsic deterioration, but also by the operational conditions under which the system is operating. This paper proposes an RUL prediction approach to estimate the mean RUL of a continuously degrading system under dynamic operational conditions and subjected to condition monitoring at short equi-distant intervals. The dynamic nature of the operational conditions is described by a discrete-time Markov chain, and their influences on the degradation signal are quantified by degradation rates and signal jumps in the degradation model. The uniqueness of our proposed approach is formulating the RUL prediction problem in a semi-Markov decision process framework, by which the system mean RUL can be obtained through the solution to a limited number of equations. To extend the use of our proposed approach in real applications, different failure standards according to different operational conditions are also considered. The application and effectiveness of this approach are illustrated by a turbofan engine dataset and a comparison with existing results for the same dataset.
For critical engineering systems such as aircraft and aerospace vehicles, accurate Remaining Useful Life(RUL) prediction not only means cost saving, but more importantly, is of great significance in ensuring system reliability and preventing disaster. RUL is affected not only by a system's intrinsic deterioration, but also by the operational conditions under which the system is operating. This paper proposes an RUL prediction approach to estimate the mean RUL of a continuously degrading system under dynamic operational conditions and subjected to condition monitoring at short equi-distant intervals. The dynamic nature of the operational conditions is described by a discrete-time Markov chain, and their influences on the degradation signal are quantified by degradation rates and signal jumps in the degradation model. The uniqueness of our proposed approach is formulating the RUL prediction problem in a semi-Markov decision process framework, by which the system mean RUL can be obtained through the solution to a limited number of equations. To extend the use of our proposed approach in real applications, different failure standards according to different operational conditions are also considered. The application and effectiveness of this approach are illustrated by a turbofan engine dataset and a comparison with existing results for the same dataset.
引文
1.Bian L,Gebraeel N,Kharoufeh JP.Degradation modeling for real-time estimation of residual lifetimes in dynamic environments.IIE Trans 2015;47(5):471-86.
2.Gebraeel N,Lawley M,Li R,Ryan JK.Residual-life distributions from component degradation signals:A Bayesian approach.IIETrans 2005;37(6):543-57.
3.Chen X,Yu J,Tang D,Wang Y.A novel PF-LSSVR-based framework for failure prognosis of nonlinear systems with timevarying parameters.Chin J Aeronaut 2012;25(5):715-24.
4.Si XS,Wang W,Hu CH,Chen MY,Zhou DH.A Wiener-processbased degradation model with a recursive filter algorithm for remaining useful life estimation.Mech Syst Signal Process 2013;35(1-2):219-37.
5.Wang ZQ,Hu CH,Fan HD.Real-time remaining useful life prediction for a nonlinear degrading system in service:Application to bearing data.IEEE/ASME Trans Mechatronics 2018;23(1):211-22.
6.Wang ZQ,Hu CH,Si XS,Zio E.Remaining useful life prediction of degrading systems subjected to imperfect maintenance:Application to draught fans.Mech Syst Signal Process 2018;100:802-13.
7.Wang ZQ,Hu CH,Wang WB,Si XS.An additive Wiener processbased prognostic model for hybrid deteriorating systems[J].IEEETrans Reliab 2014;63(1):208-22.
8.Liao H,Tian Z.A framework for predicting the remaining useful life of a single unit under time-varying operating conditions.IIETrans 2013;45(9):964-80.
9.Bocchetti D,Giorgio M,Guida M,Pulcini G.A competing risk model for the reliability of cylinder liners in marine Diesel engines.Reliab Eng Syst Saf 2009;94(8):1299-307.
10.Si XS,Hu CH,Kong X,Zhou DH.A residual storage life prediction approach for systems with operation state switches.IEEE Trans Ind Electron 2014;61(11):6304-15.
11.Lu C,Meeker W.Using degradation measures to estimate a timeto-failure distribution.Technometrics 1993;35(2):161-74.
12.Tang D,Makis V,Jafari L,Yu J.Optimal maintenance policy and residual life estimation for a slowly degrading system subject to condition monitoring.Reliab Eng Syst Saf 2015;134:198-207.
13.Wang X.Wiener processes with random effects for degradation data.J Multivariate Anal 2010;101(2):340-51.
14.Lawless J,Crowder M.Covariates and random effects in a gamma process model with application to degradation and failure.Lifetime Data Anal 2004;10(3):213-27.
15.Wang X,Xu D.An inverse gaussian process model for degradation data.Technometrics 2010;52(2):188-97.
16.Zio E,Peloni G.Particle filtering prognostic estimation of the remaining useful life of nonlinear components.Reliab Eng Syst Saf2011;96(3):403-9.
17.Heimes FO.Recurrent neural networks for remaining useful life estimation.International conference on prognostics and health management;2008 Oct 6-9;Denver,USA.Piscataway(NJ):IEEEPress;2008.p.1-6.
18.Tobon-Mejia DA,Medjaher K,Zerhouni N.CNC machine tools wear diagnostic and prognostic by using dynamic Bayesian networks.Mech syst signal process 2012;28:167-82.
19.Ross S.Introduction to probability models.10th ed.New York:Academic Press;2010.
20.Tijms H.A first course in stochastic models.New York:John Wiley&Sons Inc;2003.
21.Saxena A,Goebel K.Turbofan engine degradation simulation dataset[Internet].[2013-09-12].Available from:http://ti.arc.nasa.gov/project/prognostic-data-repository.
22.Saxena A,Goebel K,Simon D,Eklund N.Damage propagation modeling for aircraft engine run-to-failure simulation.International conference on prognostics and health management;2008 Oct6-9;Denver,USA.Piscataway(NJ):IEEE Press;2008.p.1-9.
23.Wang T,Yu J,Siegel D,Lee J.A similarity-based prognostics approach for remaining useful life estimation of engineered systems.International conference on prognostics and health management;2008 Oct 6-9;Denver,USA.Piscataway(NJ):IEEEPress;2008.p.1-6.
24.Peel L.Data driven prognostics using a Kalman filter ensemble of neural network models.International conference on prognostics and health management;2008.Oct 6-9;Denver,USA.Piscataway(NJ):IEEE Press;2008.p.1-6.
25.Le Son K,Fouladirad M,Barros A,Levrat E,Iung B.Remaining useful life estimation based on stochastic deterioration models:Acomparative study.Reliab Eng Syst Saf 2013;112(4):165-75.
2.Gebraeel N,Lawley M,Li R,Ryan JK.Residual-life distributions from component degradation signals:A Bayesian approach.IIETrans 2005;37(6):543-57.
3.Chen X,Yu J,Tang D,Wang Y.A novel PF-LSSVR-based framework for failure prognosis of nonlinear systems with timevarying parameters.Chin J Aeronaut 2012;25(5):715-24.
4.Si XS,Wang W,Hu CH,Chen MY,Zhou DH.A Wiener-processbased degradation model with a recursive filter algorithm for remaining useful life estimation.Mech Syst Signal Process 2013;35(1-2):219-37.
5.Wang ZQ,Hu CH,Fan HD.Real-time remaining useful life prediction for a nonlinear degrading system in service:Application to bearing data.IEEE/ASME Trans Mechatronics 2018;23(1):211-22.
6.Wang ZQ,Hu CH,Si XS,Zio E.Remaining useful life prediction of degrading systems subjected to imperfect maintenance:Application to draught fans.Mech Syst Signal Process 2018;100:802-13.
7.Wang ZQ,Hu CH,Wang WB,Si XS.An additive Wiener processbased prognostic model for hybrid deteriorating systems[J].IEEETrans Reliab 2014;63(1):208-22.
8.Liao H,Tian Z.A framework for predicting the remaining useful life of a single unit under time-varying operating conditions.IIETrans 2013;45(9):964-80.
9.Bocchetti D,Giorgio M,Guida M,Pulcini G.A competing risk model for the reliability of cylinder liners in marine Diesel engines.Reliab Eng Syst Saf 2009;94(8):1299-307.
10.Si XS,Hu CH,Kong X,Zhou DH.A residual storage life prediction approach for systems with operation state switches.IEEE Trans Ind Electron 2014;61(11):6304-15.
11.Lu C,Meeker W.Using degradation measures to estimate a timeto-failure distribution.Technometrics 1993;35(2):161-74.
12.Tang D,Makis V,Jafari L,Yu J.Optimal maintenance policy and residual life estimation for a slowly degrading system subject to condition monitoring.Reliab Eng Syst Saf 2015;134:198-207.
13.Wang X.Wiener processes with random effects for degradation data.J Multivariate Anal 2010;101(2):340-51.
14.Lawless J,Crowder M.Covariates and random effects in a gamma process model with application to degradation and failure.Lifetime Data Anal 2004;10(3):213-27.
15.Wang X,Xu D.An inverse gaussian process model for degradation data.Technometrics 2010;52(2):188-97.
16.Zio E,Peloni G.Particle filtering prognostic estimation of the remaining useful life of nonlinear components.Reliab Eng Syst Saf2011;96(3):403-9.
17.Heimes FO.Recurrent neural networks for remaining useful life estimation.International conference on prognostics and health management;2008 Oct 6-9;Denver,USA.Piscataway(NJ):IEEEPress;2008.p.1-6.
18.Tobon-Mejia DA,Medjaher K,Zerhouni N.CNC machine tools wear diagnostic and prognostic by using dynamic Bayesian networks.Mech syst signal process 2012;28:167-82.
19.Ross S.Introduction to probability models.10th ed.New York:Academic Press;2010.
20.Tijms H.A first course in stochastic models.New York:John Wiley&Sons Inc;2003.
21.Saxena A,Goebel K.Turbofan engine degradation simulation dataset[Internet].[2013-09-12].Available from:http://ti.arc.nasa.gov/project/prognostic-data-repository.
22.Saxena A,Goebel K,Simon D,Eklund N.Damage propagation modeling for aircraft engine run-to-failure simulation.International conference on prognostics and health management;2008 Oct6-9;Denver,USA.Piscataway(NJ):IEEE Press;2008.p.1-9.
23.Wang T,Yu J,Siegel D,Lee J.A similarity-based prognostics approach for remaining useful life estimation of engineered systems.International conference on prognostics and health management;2008 Oct 6-9;Denver,USA.Piscataway(NJ):IEEEPress;2008.p.1-6.
24.Peel L.Data driven prognostics using a Kalman filter ensemble of neural network models.International conference on prognostics and health management;2008.Oct 6-9;Denver,USA.Piscataway(NJ):IEEE Press;2008.p.1-6.
25.Le Son K,Fouladirad M,Barros A,Levrat E,Iung B.Remaining useful life estimation based on stochastic deterioration models:Acomparative study.Reliab Eng Syst Saf 2013;112(4):165-75.