Integration of Operational Data into Maintenance Planning

  • Peter SchuhEmail author
  • Christian Perl
  • Kirsten Tracht
Part of the Decision Engineering book series (DECENGIN)


In machines a broad range of operational and failure information, like hours of operation, temperatures of components or information about surrounding conditions are available. However, this information is barely used for failure prediction or maintenance planning. At the same time, product life cycles shorten and machine variants increase, making estimation of replacement instances challenging. Stochastic models offer the opportunity of integrating operational and failure information and thereby utilize them for more accurate planning. Within this chapter, a literature overview about existing stochastic prognosis methods and an approach for cost minimal replacement are presented. Within that method data pre-processing, interpretation and utilizing takes place. It can be applied to any system exposed to mechanical wear. The novel planning approach is applied to wind energy turbine data and verified by comparison to established methods.


Hide Markov Model Kalman Filter Wind Turbine Cumulative Density Function Maintenance Planning 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



The results presented were developed in the research project “Service logistics for wind turbines” funded by the German Federal Ministry of Economics and Technology (BMWI), Industrial Collective Research for SMEs (AiF), Bundesvereinigung Logistik e.V. (BVL).


  1. 1.
    Jorgenson DW, McCall JJ, Radner R (1967) Optimal replacement policy. North-Holland Publishing, AmsterdamGoogle Scholar
  2. 2.
    Ghordrati B (2005) Reliability and operational environment based spare parts planning. Lulea University of Technology, LuleaGoogle Scholar
  3. 3.
    Louit D, Rodrigo P, Banjevic D, Jardine AKS (2011) Condition-based spares ordering for critical components. Mech Syst Sig Process 25:1837–1848CrossRefGoogle Scholar
  4. 4.
    Vlok P-J (2001) Dynamic residual life estimation of industrial equipment based on failure intensity proportions. University of Pretoria, PretoriaGoogle Scholar
  5. 5.
    Dietrich E (2009) Statistische Verfahren zur Maschinen—und Prozessqualifikation: mit 61 Tabellen, 6., vollst. überarb. Aufl. Hanser, München [u.a.]Google Scholar
  6. 6.
    Strunz M (2012) Instandhaltung, Grundlagen-Strategien-Werkstätten. doi: 10.1007/978-3-642-27390-2
  7. 7.
    Abernethy RB (2006) The new Weibull handbook. Robert B. Abernethy Publishing, North Palm BeachGoogle Scholar
  8. 8.
    Epstein B, Sobel M (1954) Some theorems relevant to life testing from an exponential distribution. Ann Math Stat 25:373–381CrossRefzbMATHMathSciNetGoogle Scholar
  9. 9.
    Schenk M (2010) Instandhaltung technischer Systeme—Methoden und Werkzeuge zur Gewährleistung eines sicheren und wirtschaftlichen Anlagenbetriebs. Springer, BerlinGoogle Scholar
  10. 10.
    Rosin P, Rammler E (1933) The laws governing the fineness of powdered coal. Inst Fuel 7:29–36Google Scholar
  11. 11.
    Große G (1976) Instandhaltungsstrategien für einfache und komplexe Systeme mit Berücksichtigung periodischer Kontrollen. Ingenieurhochschule ZittauGoogle Scholar
  12. 12.
    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 Manage 25:1184–1193. doi: 10.1016/j.jom.2007.01.021 CrossRefGoogle Scholar
  13. 13.
    Lanza G, Niggeschmidt S, Werner P (2009) Optimization of preventive maintenance and spare part provision for machine tools based on variable operational conditions. CIRP Ann Manuf Technol 58:429–432. doi: 10.1016/j.cirp.2009.03.030 CrossRefGoogle Scholar
  14. 14.
    Cox DR (1972) Regression models and life-tables. J Roy Stat Soc 34:187–220zbMATHGoogle Scholar
  15. 15.
    Hastie T, Sleeper L, Tirshirani R (1992) Flexible covariate effects in the proportional hazards model. Breast Cancer Res Treat Issue 3(22):241–250CrossRefGoogle Scholar
  16. 16.
    zu Eulenburg CHG (2009) Überleben, Progredienz und Tod: Multistate-Modelle zur Analyse konkurrierender und nachzeititger Ereignisse. Universität Hamburg, HamburgGoogle Scholar
  17. 17.
    Klein JP, Moeschberger ML (2010) Survival analysis: techniques for censored and truncated data, 2nd edn. Springer, New York (corr. 3. print)Google Scholar
  18. 18.
    Vlok PJ, Coetzee JL, Banjevic D, Jardine AKS, Makis V (2002) Optimal component replacement decisions using vibration monitoring and the proportional-hazards model. J Oper Res Soc 53:193–202CrossRefzbMATHGoogle Scholar
  19. 19.
    Banjevic D, Jardine AKS (2006) Calculation of reliability function and remaining useful life for a Markov failure time process. J Manage Math 17:115–130zbMATHMathSciNetGoogle Scholar
  20. 20.
    Zhao X, Bordes L, Fouladirad M, Bèrenguer C (2010) Condition-based inspection/replacement policies for non-monotone deteriorating systems with environmental covariates. Reliab Eng Sys Saf 95:921–934CrossRefGoogle Scholar
  21. 21.
    Kalman RE (1960) A new approach to linear filtering and prediction problems. ASME-J Basic Eng 83:35–45CrossRefGoogle Scholar
  22. 22.
    Wang W, Christer AH (2000) Towards a general condition based maintenance model for a stochastic dynamic system. J Oper Res Soc 51:145–155CrossRefzbMATHGoogle Scholar
  23. 23.
    Gomes JPP, Leao BP, Vianna WOL et al (2012) Failure prognostics of a hydraulic pump using kalman filter. Ann Conf Prognostics Health Manage Soc 3:1–5Google Scholar
  24. 24.
    Wang W (2007) A prognosis model for wear prediction based on oil-based monitoring. J Oper Res Soc 58:887–893CrossRefzbMATHGoogle Scholar
  25. 25.
    Baruah P, Chinnam RB (2005) HMMs for diagnostics and prognostics in machining processes. Int J Prod Res 43:1275–1293CrossRefzbMATHGoogle Scholar
  26. 26.
    Baum LE, Petrie T (1966) Statistical inference for probabilistic functions of finite state markov chains. Ann Math Stat 37:1554–1563CrossRefzbMATHMathSciNetGoogle Scholar
  27. 27.
    Rigoll G, Schenk J (2010) Mensch-Maschine-Kommunikation. Springer, BerlinGoogle Scholar
  28. 28.
    Bunks C, Mc Carhy D, Al-Ani T (2000) Condition-based maintenance of machines using hidden markov models. Mech Syst Sig Process 14:597–612. doi: 10.1006/mssp.2000.1309 CrossRefGoogle Scholar
  29. 29.
    Zhou Z-J, Hu C-H, Xu D-L et al (2010) A model for real-time failure prognosis based on hidden Markov model and belief rule base. Eur J Oper Res 207:269–283. doi: 10.1016/j.ejor.2010.03.032 CrossRefzbMATHMathSciNetGoogle Scholar
  30. 30.
    Neves ML, Santiago LP, Maia CA (2011) A condition-based maintenance policy and input parameters estimation for deteriorating systems under periodic inspection. Comput Ind Eng 61:503–511. doi: 10.1016/j.cie.2011.04.005 CrossRefGoogle Scholar
  31. 31.
    Tracht K, Goch G, Schuh P, Sorg M, Westerkamp JF (2013) Failure probability prediction based on condition monitoring data of wind energy systems for spare parts supply. CIRP Ann Manufact Technol 62:127–130.
  32. 32.
    Sachs J, Hedderich L (2009) Angewandte Statistik: Methodensammlung mit R, 13., aktualisierte und erweiterte Auflage. Springer, DordrechtGoogle Scholar
  33. 33.
    Kumar DBK (1994) Proportional hazards model: a review. Reliab Eng Sys Saf 44:177–188CrossRefGoogle Scholar
  34. 34.
    Andy Field ZF, Miles J (2012) Discovering statistics using R. Sage, Thousand OaksGoogle Scholar
  35. 35.
    Thall PF, Lachin JM (1986) Assessment of stratum-covariate interactions in cox’s proportional hazards regression model. Stat Med 5:73–83CrossRefGoogle Scholar
  36. 36.
    Kaplan EL, Meiers P (1958) Nonparametric estimation from incomplete observations. J Am Stat Assoc 53:457–481CrossRefzbMATHGoogle Scholar
  37. 37.
    Hosmer DW, Lemeshow S, May S (2008) Applied survival analysis: regression modeling of time-to-event data, 2nd edn. Wiley, HobokenCrossRefGoogle Scholar
  38. 38.
    Andersen PK, Gill RD (1982) Cox’s regression model for counting processes: a large sample study. Ann Stat 10:1100–1120CrossRefzbMATHMathSciNetGoogle Scholar
  39. 39.
    Fleming TR, Harrington DP (1991) Counting processes and survival analysis. Wiley, New YorkzbMATHGoogle Scholar
  40. 40.
    Beichelt F (1970) Zuverlässigkeit und Erneuerung: die optimale Instandhaltung. Verlag Technik, BerlinGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Bremen Institute for Mechanical Engineering (BIME)University of BremenBremenGermany

Personalised recommendations