Modelling Techniques to Support the Adoption of Predictive Maintenance

Part of the Decision Engineering book series (DECENGIN)


Contracting for availability and contracting for capability are becoming increasingly common practices in the defence world. With these new service-oriented contracts, the responsibility for through-life support, including maintenance, has been shifted from the user to the service provider. In this new environment, innovative approaches to improving maintenance and reliability are necessary and create new, unique opportunities for value co-creation between stakeholders. This chapter focuses on investigating the applicability and implementation of an approach to predictive maintenance which combines prognostic modelling with Condition Based Maintenance (CBM) and its role in providing improved service provision for the repair and maintenance of complex systems. The role of prognostic modelling and Health and Usage Monitoring Systems as the emerging technologies that enable a value-oriented approach to maintenance are discussed. Bayesian networks are discussed as a modelling framework that is appropriate to capture uncertainties related to predictive maintenance. Special focus is placed on reviewing practical challenges and proposing solutions to them. The discussion is summarised in the form of a practitioner’s guide to implementing prognostic modelling and CBM.


Bayesian Network Fault Diagnosis Domain Expert Prognostic Model Maintenance Policy 


  1. A.M. Agogino, K. Ramamurthi, Real-time influence diagrams for monitoring and controlling mechanical systems, in Influence diagrams, belief nets and decision analysis, ed. by R.M. Oliver, J.Q. Smith (Wiley, Chichester, 1990), pp. 199–228Google Scholar
  2. R. Barco, V. Wille, L. Diez, System for automated diagnosis in cellular networks based on performance indicators. Eur. Trans. Telecommun. 16, 399–409 (2005)CrossRefGoogle Scholar
  3. P. Baruah, R.B. Chinnam, HMMs for diagnostics and prognostics in machining processes. Int. J. Prod. Res. 43, 1275–1293 (2005)MATHCrossRefGoogle Scholar
  4. E.R. Brown, N.N. McCollom, E.E. Moore, A. Hess, Prognostics and health management: A data-driven approach to supporting the F-35 Lightning II. IEEE Aerospace Conference 2007 (2007)Google Scholar
  5. F. Cadini, E. Zio, D. Avram, Monte Carlo-based filtering for fatigue crack growth estimation. Probab. Eng. Mech. 24, 367–373 (2009)CrossRefGoogle Scholar
  6. A. Chan, K.R. McNaught, Using Bayesian networks to improve fault diagnosis during manufacturing tests of mobile telephone infrastructure. J. Oper. Res. Soc. 59, 423–430 (2008)MATHCrossRefGoogle Scholar
  7. R.G. Cowell, A.P. Dawid, S.L. Lauritzen, D.J. Spiegelhalter, Probabilistic Networks and Expert Systems (Springer, Berlin 1999)MATHGoogle Scholar
  8. T. Dean, K. Kanazawa, A model for reasoning about persistence and causation. Comput. Intell. 5, 142–150 (1989)CrossRefGoogle Scholar
  9. Department of Defense, MIL-STD-1629A: Procedures for performing a failure mode effects and criticality analysis (1980)Google Scholar
  10. G. Forman, M. Jain, M. Mansouri-Samani, J. Martinka, A. Snoeren, Automated end-to-end system diagnosis of networked printing services using model-based reasoning. Software Technology Laboratory, HPL-98-41 (R.1) (1998)Google Scholar
  11. E. Gilabert, A. Arnaiz, Intelligent automation systems for predictive maintenance: A case study. Robot. Comput. Integr. Manuf. 22, 543–549 (2006)CrossRefGoogle Scholar
  12. J. Gu, M. Pecht, New methods to predict reliability of electronics. Proceedings of 7th international conference on reliability, maintainability and safety (2007), pp. 440–451Google Scholar
  13. D. Heckerman, Bayesian networks for data mining. Data Min. Knowl. Discov. 1, 79–119 (1997)CrossRefGoogle Scholar
  14. D. Heckerman, J.S. Breese, K. Rommelse, Decision-theoretic troubleshooting. Commun. ACM 38, 49–57 (1995)CrossRefGoogle Scholar
  15. F.O. Heimes, Recurrent neural networks for remaining useful life estimation. International conference on prognostics and health management, PHM 2008Google Scholar
  16. A. Heng, S. Zhang, A.C.C. Tan, J. Mathew, Rotating machinery prognostics: State of the art, challenges and opportunities. Mech. Syst. Signal Process 23, 724–739 (2009a)CrossRefGoogle Scholar
  17. A. Heng, A.C.C. Tan, J. Mathew, N. Montgomery, D. Banjevic, A.K.S. Jardine, Intelligent condition-based prediction of machinery reliability. Mech. Syst. Signal Process 23, 1600–1614 (2009b)CrossRefGoogle Scholar
  18. A. Hess, G. Calvello, P. Frith, S.J. Engel, D. Hoitsma, Challenges, issues and lessons learned chasing the Big P: real predictive prognostics part 2. (IEEE Aerospace Conference 2006)Google Scholar
  19. G.J. Kacprzynski, M. Roemer, A.J. Hess, K.R. Bladen, Extending FMECA—health management design optimization for aerospace applications. IEEE Aerospace Conference (2001)Google Scholar
  20. K.A.H. Kobbacy, B.B. Fawzy, D.F. Percy, A full history of proportional hazards model for preventive maintenance scheduling. Qual. Reliab. Eng. Int. 13, 187–198 (1997)CrossRefGoogle Scholar
  21. P. Kraaijeveld, M.J. Druzdzel, GeNIeRate: An interactive generator of diagnostic Bayesian network models. Working notes of the 16th international workshop on principles of diagnosis (DX-05): (2005), pp. 175–180Google Scholar
  22. D. Kumar, B. Klefsjo, Proportional hazards model: A review. Reliab. Eng. Syst. Saf. 44, 177–188 (1994)CrossRefGoogle Scholar
  23. H. Langseth, L. Portinale, Bayesian networks in reliability. Reliab. Eng. Syst. Saf. 92, 92–108 (2007)CrossRefGoogle Scholar
  24. U. Lerner, R. Parr, D. Koller, G. Biswas, Bayesian fault detection and diagnosis in dynamic systems. Proceedings of the 17th national conference on artificial intelligence (AAAI) (2000), pp. 531–537Google Scholar
  25. Y. Li, T.R. Kurfess, S.Y. Liang, Stochastic prognostics for rolling element bearings. Mech. Syst. Signal Process 14, 747–762 (2000)CrossRefGoogle Scholar
  26. J.K. Line, N.S. Clements, Prognostics usefulness criteria. IEEE aerospace conference 2006 (2006)Google Scholar
  27. Z. Ma, A new life system approach to the prognostic and health management (PHM) with survival analysis, dynamic hybrid fault models, evolutionary game theory, and three-layer survivability analysis. IEEE aerospace conference 2009 (2009)Google Scholar
  28. A. Muller, M.C. Suhner, B. Iung, Maintenance alternative integration to prognosis process engineering. J. Qual. Maint. Eng. 13, 198–211 (2007)CrossRefGoogle Scholar
  29. A. Muller, M.C. Suhner, B. Iung, Formalisation of a new prognosis model for supporting proactive maintenance implementation on industrial system. Reliab. Eng. Syst. Saf 93, 234–253 (2008)CrossRefGoogle Scholar
  30. M. Neil, M. Tailor, D. Marquez, N. Fenton, P. Hearty, Modelling dependable systems using hybrid Bayesian networks. Proceedings of 1st international conference on availability, reliability and security (2006), pp. 817–821Google Scholar
  31. R. Normann, R. Ramirez, From value chain to value constellation: designing interactive strategy. Harv. Bus. Rev. (July–August): (1993), pp. 65–77Google Scholar
  32. O. Ogunyemi, J.R. Clarke, B. Webber, Using Bayesian networks for diagnostic reasoning in penetrating injury assessment. Proceedings of the 13th IEEE symposium on computer-based medical systems (CBMS’00): (2000), pp. 115–120Google Scholar
  33. R.M. Oliver, H.J. Yang, Updating of event tree parameters to predict high risk incidents, in Influence diagrams, belief nets and decision analysis, ed. by R.M. Oliver, J.Q. Smith (Wiley, Chichester, 1990), pp. 277–296Google Scholar
  34. R.F. Orsagh, D.W. Brown, P.W. Kalgren, C.S. Byington, A.J. Hess, T. Dabney, Prognostic health management for avionic systems. IEEE Aerospace Conference 2006 (2006)Google Scholar
  35. J. Pearl, Probabilistic reasoning in intelligent systems: Networks of plausible inference (Morgan Kaufmann, San Mateo, 1988)Google Scholar
  36. L. Peel, Data driven prognostics using a Kalman filter ensemble of neural network models. International conference on prognostics and health management (2008)Google Scholar
  37. O. Pourret, P. Naïm, B. Marcot, Bayesian networks: a practical guide to applications (Wiley, New York 2008)MATHGoogle Scholar
  38. K.W. Przytula, D. Thompson. in Proceedings of SPIE Component and Systems Diagnostics, Prognosis, and Health Management, ed. by P.K. Willett, T. Kirubarajan. Development of Bayesian diagnostic models using troubleshooting flow diagrams. 4389: 110–120 (2001)Google Scholar
  39. C. Romessis, K. Mathioudakis, Bayesian network approach for gas path fault diagnosis. J. Eng. Gas. Turbines Power Trans. ASME 128, 64–72 (2006)CrossRefGoogle Scholar
  40. M. Sanseverino, F. Cascio, Model-based diagnosis for automotive repair. IEEE Expert. 12, 33–37 (1997)CrossRefGoogle Scholar
  41. H. Saranga, J. Knezevic, Reliability analysis using multiple relevant condition parameters. J. Qual. Maint. Eng. 6, 165–176 (2000)CrossRefGoogle Scholar
  42. M.A. Shwe, B. Middleton, D.E. Heckerman, M. Henrion, E.J. Horvitz, H.P. Lehmann, G.F. Cooper, Probabilistic diagnosis using a reformulation of the INTERNIST–1/QMR knowledge base: I. The probabilistic model and inference algorithms. Methods Inform. Med. 30, 241–255 (1991)Google Scholar
  43. W. Wang, A.H. Christer, Towards a general condition based maintenance model for a stochastic dynamic system. J. Oper. Res. Soc. 51, 145–155 (2000)MATHGoogle Scholar
  44. G. Wen, X. Zhang, Prediction method of machinery condition based on recurrent neural network models. J. Appl. Sci. 4, 675–679 (2004)CrossRefGoogle Scholar
  45. J. Yan, M. Koc, J. Lee, A prognostic algorithm for machine performance assessment and its application. Prod. Plan Control 15, 796–801 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited  2011

Authors and Affiliations

  1. 1.Department of Engineering Systems and Management, Defence Academy of the UKCranfield UniversityShrivenhamUK

Personalised recommendations