Remaining useful life estimation: review

  • Farzaneh Ahmadzadeh
  • Jan Lundberg
Review Paper


This paper reviews the recent modelling developments in estimating the remaining useful life (RUL) of industrial systems. The RUL estimation models are categorized into experimental, data driven, physics based and hybrid approaches. The paper reviews some typical approaches and discusses their advantages and disadvantages. According to the literature, the selection of the best model depends on the level of accuracy and availability of data. In cases of quick estimations which are less accurate, the data driven method is preferred, while the physics based approach is applied when the accuracy of estimation is important.


Prognostic Remaining useful life Mean residual life Reliability modelling Data driven approach Physics based approach Experimental approach 


  1. Ahmadzadeh F, Lundberg J (2013a) Remaining useful life prediction of grinding mill liners using an artificial neural network. Miner Eng. doi: 10.1016/j.mineng.2013.05.026 MATHGoogle Scholar
  2. Ahmadzadeh F, Lundberg J (2013b) Application of multi regressive linear models and neural network for wear prediction of grinding mill liners. Int J Adv Comput Sci APPL 4(5):53–58Google Scholar
  3. Ahmadzadeh F, Ghodrati B, Kumar U (2012) Mean residual life estimation considering operating environment. ICQRITTM Proceedings, New DelhiGoogle Scholar
  4. Akers DW, Rideout CA (2004) Measurement-based prognostic models for service induced damage in turbine engine components. IEEE Aerospace Proceeding Google Scholar
  5. Altay N, Green WG (2006) OR/MS research in disaster operations management. Eur J Oper Res 175:475–493CrossRefMATHGoogle Scholar
  6. Bagul YG (2009) Assessment of current health and remaining useful life of hard disk drives. Dissertation, Northeastern UniversityGoogle Scholar
  7. Bagul YG, Zeid I, Kamarthi SV (2008) Overview of remaining useful life methodologies. ASME 2008 Proceedings, New York Google Scholar
  8. Banjevic D (2009) Remaining useful life in theory and practice. Metrika 69(2):337–349Google Scholar
  9. Banjevic D, Jardine AKS (2005) Calculation of reliability function and remaining useful life for a Markov failure time process, Ima J Manage Math: 1–16Google Scholar
  10. Baruah P, Chinnam RB (2003) HMMs for diagnostics and prognostics in machining processes. Int J Prod Res 43(6):1275–1293CrossRefGoogle Scholar
  11. Bhattacharjee MC (1982) The class of mean residual lives and some consequences. Siam J Algebraic Discrete M 3:56–65MathSciNetCrossRefMATHGoogle Scholar
  12. Brotherton T, Jahns J, Jacobs J, Wroblewski D (2000) Prognosis of faults in gas turbine engines. IEEE Aerospace Proceedings 6:163–171Google Scholar
  13. Bukkapatnam STS (1997) Monitoring and control issues in chaotic processes: an application to turning process. Pennsylvania State University, DissertationGoogle Scholar
  14. Butler KL (1996) An expert system based framework for an incipient failure detection and predictive maintenance system. Proceedings of Intelligent Sys Applications to Power Sys, Orlando, pp 321–326Google Scholar
  15. Byington CS, Watson M, Edwards D (2004) Data-driven neural network methodology to remaining life predictions for aircraft actuator components. IEEE, PiscatawayGoogle Scholar
  16. Chen C, Vachtsevanos G, Orchard M (2010) Machine remaining useful life prediction based on adaptive neuro-fuzzy and high-order particle filtering. Proceedings of the prognostics and health management society, PortlandGoogle Scholar
  17. Chinnam RB, Baruah P (2004) A neuro-fuzzy approach for estimating mean residual life in condition-based maintenance systems. Int J Mater Prod Technol 20:166–179CrossRefGoogle Scholar
  18. Choi SS, Kang KS, Kim HG, Chang SH (1995) Development of an on-line fuzzy expert system for integrated alarm processing in nuclear power plants. IEEE Trans Nucl Sci 42(4):1406–1418CrossRefGoogle Scholar
  19. Connor JT, Matinem RD, Atlas LE (1994) Recurrent neutral networks and robust time series prediction. IEEE Trans Neural Netw 5:240–254CrossRefGoogle Scholar
  20. Cox DR (1962) Renewal Theory. Methuen, LondonMATHGoogle Scholar
  21. Cui LR, Loh HT, Xie M (2004) Sequential inspection strategy for multiple systems under availability requirement. Eur J Oper Res 155:170–177MathSciNetCrossRefMATHGoogle Scholar
  22. Dandotiya R, Lundberg J, Wijaya A (2011) Evaluation of abrasive wear measurement devices of mill liners. Intl J COMADEM 14(2):3–17Google Scholar
  23. Dong M, He D (2007a) A segmental hidden semi-Markov model (HSMM) based diagnostics and prognostics framework and methodology. Mech Syst Signal Pr 21(5):2248–2266CrossRefGoogle Scholar
  24. Dong M, He D (2007b) Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis. Eur J Oper Res 178(3):858–878MathSciNetCrossRefMATHGoogle Scholar
  25. Dong M, Yang ZB (2008) Dynamic Bayesian network based prognosis in machining processes. J Shanghai Jiaotong Univ Sci 13(3):318–322CrossRefGoogle Scholar
  26. Dong M, He D, Banerjee P, Keller J (2006) Equipment health diagnosis and prognosis using hidden semi-markov models. Int J Adv Manuf Technol 30:738–749CrossRefGoogle Scholar
  27. Elandt-Johnson RC, Johnson NL (1980) Survival models and data analysis. Wiley, New YorkMATHGoogle Scholar
  28. El-Koujok M, Gouriveau R, Zerhouni N (2008) From monitoring data to remaining useful life: an evolving approach including uncertainty. SReDA ESReDA/ESRA Proceeding, SpainGoogle Scholar
  29. Elwany AH, Gebraeel NZ (2008) Sensor-driven prognostic models for equipment replacement and spare parts inventory. IIE Trans 40:629–639CrossRefGoogle Scholar
  30. Engel SJ, Gilmartin BJ, Bongort K, Hess A (2000) Prognostics: the real issues involved with predicting life remaining. IEEE Aerospace Proc. 6:457–469Google Scholar
  31. Essawy MA (2001) Methods to estimate machine remaining useful life using artificial neural networks. Defense Technical Information CenterGoogle Scholar
  32. Galar D, Kumar U, Lee J, Zhao W (2012) Estimation of remaining useful life time trajectory using support vector machines. COMADEM Proceeding, HudderieldsGoogle Scholar
  33. Garga AK, McClintic KT, Campbell RL, Yang CC, Lebold MS, Hay TA, Byington CS (2001) Hybrid reasoning for prognostic learning in CBM systems. IEEE Aerospace Proceeding 6:2957–2969Google Scholar
  34. Gasperin M, Baskoski P, Juricic D, Jozef V (2011) Model-based prognostics of gear health using stochastic dynamic models. Mech Syst Signal Pr 25:537–538CrossRefGoogle Scholar
  35. Gebraeel NZ, Lawley MA (2008) A neural network degradation model for computing and updating residual life distributions. IEEE T Autom Sci Eng 5(1):154–163CrossRefGoogle Scholar
  36. Gebraeel N, Lawley MA, Liu R (2004) Residual life predictions from vibration-based degradation signals: A neural network approach. IEEE T Ind Electron 51(3):694–700CrossRefGoogle Scholar
  37. Gebraeel NZ, Lawley MA, Li R, Ryan JK (2005) Residual-life distributions from component degradation signals: a Bayesian approach. IIE Trans 37:543–557CrossRefGoogle Scholar
  38. Ghodrati B, Ahmadzadeh F, Kumar U (2012) Remaining useful life estimation of mining equipment: a case study. ISMPES Proceeding, New DelhiGoogle Scholar
  39. Goebel K, Saha B, Saxena A (2005) Prognostics in battery health management. IEEE Instrum Meas Mag 11(4):33–40CrossRefGoogle Scholar
  40. Goh KM, Tjahjono B, Bainers T, Subramaniam SA (2006) Review of research in manufacturing prognostics. Proceedings of the IEEE on Industrial Informatics, pp 1–6Google Scholar
  41. Gouriveau R, Dragomiri O, Dragomir F, Minca E, Zerhouni N (2009) Review of prognostic problem in condition-based maintenance. Proceeding of European Control, BudapestGoogle Scholar
  42. Groer P (2000) Analysis of time-to-failure with a weibull model. MARCON Proceeding, KnoxvilleGoogle Scholar
  43. Gross AJ, Clark VA (1975) Survival distributions: reliability applications in the biomedical sciences. Wiley, New YorkMATHGoogle Scholar
  44. Guess F, Proschan F (1985) Mean residual life: theory and applications. Handbook of Statistics7. North Holland, New York: 215–224Google Scholar
  45. Heng A, Zhang S, Tan A, Mathew J (2009) Rotating machinery prognostics: state of the art, challenges and opportunities. Mech Syst Signal Pr 23:724–739CrossRefGoogle Scholar
  46. Hongmou L, Zein-Sabatto S (2001) Analysis of vibration signal’s time-frequency patterns for prediction of bearing’s remaining useful life. IEEE Proceeding, PiscatawayGoogle Scholar
  47. Huang R (2007) Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods. Mech Syst Signal Pr 21(1):193–207CrossRefGoogle Scholar
  48. ISO (2004) 13381-1 Condition Monitoring and diagnostics of machines prognostics, Part1: general guidelines. Int Standard, ISOGoogle Scholar
  49. Jardine AKS, Lin D, Banjevic D (2006) A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech Syst and Signal Pr 20:1483–1510CrossRefGoogle Scholar
  50. Kacprzynski GJ, Gumina M, Roemer MJ, Caguiat DE (2001) A prognostic modeling approach for predicting recurring maintenance for shipboard propulsion systems. ASME Turbo Expo Proceeding, New OrleansGoogle Scholar
  51. Keller A, Perera U, Kamath A (1982) Reliability analysis of CNC machine tools. Reliab Eng 3:449–473CrossRefGoogle Scholar
  52. Kiddy JS (2003) Remaining useful life prediction based on known usage data. SPIE Int Soc Opt EngGoogle Scholar
  53. Kim KO, Kuo W (2009) Optimal burn-in for maximizing reliability of repairable non-series systems. Eur J Oper Res 193:140–151CrossRefMATHGoogle Scholar
  54. Kim HE, Tan A, Mathew J, Kim E, Choi BK (2009) Integrated diagnosis and prognosis model for high pressure LNG pump. Pacific vibration Proceedings, ChristchurchGoogle Scholar
  55. Kim HE, Tan A, Mathew J, Kim E, Choi BK (2010) Machine prognostics based on health state probability estimation. Queensland University of Technology, DissertationGoogle Scholar
  56. Kim HE, Tan A, Mathew J, Kim E, Choi BK (2013) Machine prognostics based on health state estimation using SVM. Engineering Asset Management Review 2. Springer, 169–186Google Scholar
  57. Kothamasu R, Huang S, VerDuin W (2006) System health monitoring and prognostics—a review of current paradigms and practices. Int J Adv Manuf Technol 28:1012–1024Google Scholar
  58. Kotz S, Shanbhag DN (1980) Some new approaches to probability distributions. Adv in Aply Probab 12:903–921MathSciNetCrossRefMATHGoogle Scholar
  59. Kuo W (1984) Reliability enhancement through optimal burn-in. IRBS Trans Reliab 33:145–156CrossRefMATHGoogle Scholar
  60. Lebold M, Thurston M (2001) Open standards for condition-based maintenance and prognostic systems. MARCON ProceedingGoogle Scholar
  61. Lee MLT, Whitmore GA (2006) Threshold regression for survival analysis: modeling event times by a stochastic process reaching a boundary. Stat Sci 21(4):501–513MathSciNetCrossRefMATHGoogle Scholar
  62. Lee J, Ni J, Djurdjanovic D, Qiu H, Liao LT (2006) Intelligent prognostics tools and e-maintenance. Comput Ind 57:476–489CrossRefGoogle Scholar
  63. Li CJ, Lee H (2005) Gear fatigue crack prognosis using embedded model, gear dynamic model and fracture mechanics. Mech Syst and Signal Pr 19:836–846CrossRefGoogle Scholar
  64. Li Y, Billington S, Zhang C, Kurfess T, Danyluk S, Liang S (1999) Adaptive prognostics for rolling element bearing condition. Mech Syst and Signal Pr 13:103–113CrossRefGoogle Scholar
  65. Liao H (2005) A predictive tool for remaining useful life estimation of rotating machinery components. Am S Mech Eng, New YorkGoogle Scholar
  66. Lloyd GM, Hasselman T, Paez T (2005) A proportional hazards neural network for performing reliability estimates and risk prognostics for mobile systems subject to stochastic covariates. Eng Tech Manag: 97–106 Google Scholar
  67. Lorton A, Fouladirad M, Grall A (2013) Computation of remaining useful life on a physic-based model and impact of a prognosis on the maintenance process. J Risk Reliab. doi: 10.1177/1748006X13481926 MATHGoogle Scholar
  68. Luo J., Namburu M., Pattipati K., Qiao L., Kawamoto M, Chigusa S (2003) Model-based prognostic techniques. In: Proceedings of IEEE Autotestcon, pp 330–340Google Scholar
  69. Mazhar MI, Kara S, Kaebernick H (2007) Remaining life estimation of used components in consumer products: life cycle data analysis by Weibull and artificial neural networks. J Oper Manag 25:1184–1193CrossRefGoogle Scholar
  70. Medjaher K, Tobon-mejia DA, Zerhouni N (2012) Remaining useful life estimation of critical components with application to bearings. IEEE T Reliab 61:292–302CrossRefGoogle Scholar
  71. Morrison DG (1978) On linearly increasing mean residual lifetimes. J APP Probab 1:617–620CrossRefGoogle Scholar
  72. Oppenheimer CH, Loparo KA (2002) Physically based diagnosis and prognosis of cracked rotor shafts. SPIE Proceedings 4733:122–132CrossRefGoogle Scholar
  73. Papakostas N, Papachatzakis P, Xanthakis V, Mourtzis D, Chryssolouris G (2010) An approach to operational aircraft maintenance planning. Decis Support Syst 48:604–612CrossRefGoogle Scholar
  74. Pecht M (2008) Prognostics and health management of electronics. John Wiley, New JerseyCrossRefGoogle Scholar
  75. Pecht M, Jaai R (2010) A prognostics and health management roadmap for information and electronics-rich system. Microelectron Reliab 50:317–323CrossRefGoogle Scholar
  76. Peng Y, Dong M, Jian Zuo M (2010) Current status of machine prognostics in condition-based maintenance: a review. Int J Adv Manuf Technol 50:297–313CrossRefGoogle Scholar
  77. Przytula KW, Choi A (2007) Reasoning framework for diagnosis and prognosis. IEEE Aerospace Proceeding, Big Sky 4161649Google Scholar
  78. Redtenbacher F (1852) Prinzipen der Mechanic und des Maschinenbaus. Basserman, Mannheim, pp 257–290Google Scholar
  79. Sankararaman S, Goebel K (2013) Uncertainty quantification in remaining useful life of aerospace components using state space models and inverse form. ASME Proceeding, BostonGoogle Scholar
  80. Satish B, Sarma NDR (2005) A fuzzy bp approach for diagnosis and prognosis of bearing faults in induction motors. IEEE Power Eng Soc Gen Meet 3:2291–2294Google Scholar
  81. Shao Y, Nezu K (2000) Prognosis of remaining bearing life using neural networks. J Syst Control Eng 214(3):217–230Google Scholar
  82. Sheppard JW, Kaufman MA (2005) Bayesian diagnosis and prognosis using instrument uncertainty. AUTOTESTCON Proceedings, Orlando, pp 417–423Google Scholar
  83. Sikorska JZ, Hodkiewicz M, Ma L (2011) Prognostic modelling options for remaining useful life estimation by industry. Mech Syst Signal Pr 25(5):1803–1836CrossRefGoogle Scholar
  84. Sutrisno E, Oh E, Vasan A, Pecht M (2012) Estimation of remaining useful life of ball bearings using data driven methodologies. IEEE Proceedings on Prognostic and Health Management, BeijingGoogle Scholar
  85. Tian Z (2009) An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring. J Intell Manuf. doi: 10.1007/s10845-009-0356-9 Google Scholar
  86. Tian Z, Wong L, Safaei N (2009) A neural network approach for remaining useful life prediction utilizing both failure and suspension histories. Mech Syst Signal Pr 24(5):1542–1555CrossRefGoogle Scholar
  87. Tobon-mejia DA, Medjaher K, Zerhouni N (2012) CNC machine tool’s wear diagnostics and prognostics by using dynamic Bayesian networks. Mech Syst Signal Pr Euro 28:167–182CrossRefGoogle Scholar
  88. Todinov MT (2005) Limiting the probability of failure for components containing flaws. Comp Mater Sci 32:156–166Google Scholar
  89. Usynin AV (2007) A Generic prognostic framework for remaining useful life prediction of complex engineering systems. University of Tennessee, Knoxville, DissertationGoogle Scholar
  90. Vachtsevanos G, Lewis F, Roemer M, Hess A,  Wu B (2006) Intelligent fault diagnosis and prognosis for engineering systems. Wiley, New JerseyGoogle Scholar
  91. Victor L, Riquelme M, Balakrishnan N, Sanhueza A (2008) Lifetime analysis based on the generalized Birnbaum–Saunders distribution. Comput Stat Data An 52:2079–2097CrossRefMATHGoogle Scholar
  92. Wang W (2002) A model to predict the residual life of rolling element bearings given monitored condition information to date. Ima J Manag Math 13:3–16MathSciNetCrossRefMATHGoogle Scholar
  93. Wang W (2007) A prognosis model for wear prediction based oil-based monitoring. J Oper Res Soc 58:887–893CrossRefMATHGoogle Scholar
  94. Wang P, Vachtsevanos G (2001) Fault prognosis using dynamic wavelet neural networks. Artif Intell Eng Des Anal Manuf (AIEDAM) 15(4):349–365CrossRefMATHGoogle Scholar
  95. Wang W, Zhang W (2008) An asset residual life prediction model based on expert judgments. Eur J Oper Res 188:496–505CrossRefMATHGoogle Scholar
  96. Wang WQ, Golnaraghi MF, Ismail F (2004) Prognosis of machine health condition using neuro-fuzzy systems. Mech Syst Signal Pr 18:813–831CrossRefGoogle Scholar
  97. Wang L, Chu J, Mao W (2009) A condition-based replacement and spare provisioning policy for deteriorating systems with uncertain deterioration to failure. Eur J Oper Res 194:184–205CrossRefMATHGoogle Scholar
  98. Watson M (2005) Dynamic modeling and wear-based remaining useful life prediction of high power clutch systems. Tribol T 48(2):208–217CrossRefGoogle Scholar
  99. Watson GS, Wells WT (1961) On the possibility of improving the mean useful life of items by eliminating those with short lives. Technometrics 3:281–298MathSciNetCrossRefMATHGoogle Scholar
  100. Wijaya A, Lundberg J (2012) The effect of the operator, the mine room and their interaction on the measured vibration level of a scaling machine. Int J Syst Assurance Eng Manag 3(2):145–152Google Scholar
  101. Xiao-Sheng S, Wang W, Hu CH, Zhou DH (2011) Remaining useful life estimation: a review on the statistical data driven approaches. Eur J Oper Res 213:1–14CrossRefGoogle Scholar
  102. Xiao-Sheng S, Wang W, Chen M, Hu C, Zhou D (2013) A degradation path-dependent approach for remaining useful life estimation with an exact and closed-form solution. Eur J Oper Res 226:53–66CrossRefMATHGoogle Scholar
  103. Hall WJ, Wellner JA (1981) Mean residual life. Statistics and related topics. North-Holland, Amsterdam, 169–184Google Scholar
  104. Yan J, Koc M, Lee J (2004) A prognostic algorithm for machine performance assessment and its application. Prod Plan Control 15:796–801CrossRefGoogle Scholar
  105. Yang J, Jay L (2007) A hybrid method for on-line performance assessment and life prediction in drilling operations. IEEE, PiscatawayGoogle Scholar
  106. Yu G, Qiu H, Djurdjanovic D, Jay L (2006) Feature signature prediction of a boring process using neural network modeling with confidence bounds. Int J Adv Manuf Technol 30:614–621CrossRefGoogle Scholar
  107. Zhang S, Ganesan R (1997) Multivariable trend analysis using neural networks for intelligent diagnostics of rotating machinery, Trans ASME. J Eng Gas Turbine Power 119:378–384CrossRefGoogle Scholar
  108. Zhang XD, Xu R, Chiman K, Liang SY, Xie QL, Haynes L (2005) An integrated approach to bearing fault diagnostics and prognostics. Proceedings of American Control 4:2750–2755Google Scholar
  109. Zhou Y, Li X, Ye X, Zhai G (2012) A remaining useful life prediction method based on condition monitoring for LED driver. IEEE Proceeding on prognostic and health management, BeijingGoogle Scholar

Copyright information

© The Society for Reliability Engineering, Quality and Operations Management (SREQOM), India and The Division of Operation and Maintenance, Lulea University of Technology, Sweden 2013

Authors and Affiliations

  1. 1.Division of Operation and MaintenanceLuleå University of TechnologyLuleåSweden

Personalised recommendations