Skip to main content

Prediction of Failures that Have Never Occured: Exponential Case

  • Conference paper
Industrial Statistics

Part of the book series: Contributions to Statistics ((CONTRIB.STAT.))

Abstract

Failures of some components, rotors of turbines or critical parts of aircraft etc., belong to extremely rare events even if respective components have been in service for a long time. Sometimes it even happens, that components of given type are observed for years (several decades) and no failures have occurred all the while. In this paper we shall describe several possibilities what to do in such a situation under the assumption, that the stream of failures form Poisson process. Advantages and disadvantages of MLE, UMVE and Bayesian estimators are covered and thoroughly discussed.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Antoch J., KlaschkaJ., Machek J. and Straka F., Prediction of failures that have never occurred — Weibull case. Proceedings of ASMDA’97. (Lauro N. C., ed.), 1997 (to appear).

    Google Scholar 

  2. Antoch J., Linka A. and BrzezinaM. Asymptotic approximation of Bayes risk of estimators of reliability for exponentially distributed data. Statistics & Decision (1997) (to appear).

    Google Scholar 

  3. Antoch J. and Machek J. Risk of appearance of turbine missiles. Technical report, Charles University, Deparment of Statistics, Praha, 1996a, (in Czech).

    Google Scholar 

  4. Antoch J. and Machek J. Risk of the crash of turbine’s rotor Technical report, Charles University, Department of Statistics Praha 1996b, (in Czech).

    Google Scholar 

  5. Harris B. and Soms A. Sensitivity and asymptotic properties of Bayesian reliability estimates in the exponential case. Statistics & Decision, 33-47 1988.

    Google Scholar 

  6. Hurt J. On estimation of reliability in exponential case. Aplikace matem-atiky, 263-272, 1976.

    Google Scholar 

  7. Jeffreys H. Theory of Probability, 3rd ed. Clarendon Press, Oxford, 1961.

    Google Scholar 

  8. Jones S. P. Prediction of failure events when no failure have occurred. COMPSTAT’96, Physica-Verlag, Heidelberg. (Prat A., ed.), pages 307–312, 1996.

    Google Scholar 

  9. Lehmann E. L. Theory of Point Estimation, 2nd ed. Wadsworth & Brooks/Cole, California, 1991.

    Book  Google Scholar 

  10. Martz H. F. and Waller R. A. Bayesian Reliability Analysis. J. Wiley, New York, 1982.

    Google Scholar 

  11. Pugh E. L. The best estimate of reliability in exponential case. Oper. Res., 11/17, 57–61, 1963.

    Article  Google Scholar 

  12. US Nuclear Regulatory Commission. Protection against Low Trajectory Turbine Missiles. Regulatory Guide 1.115, 1977.

    Google Scholar 

  13. US Nuclear Regulatory Commission. Safety Analysis Reports for Nuclear Power Plants. Regulatory Guide 1.70, Revision 3, 1978.

    Google Scholar 

  14. US Nuclear Regulatory Commission Standard Review Plan. NUREG-0800, 1981.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Antoch, J., Machek, J. (1997). Prediction of Failures that Have Never Occured: Exponential Case. In: Kitsos, C.P., Edler, L. (eds) Industrial Statistics. Contributions to Statistics. Physica, Heidelberg. https://doi.org/10.1007/978-3-642-59268-3_9

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-59268-3_9

  • Publisher Name: Physica, Heidelberg

  • Print ISBN: 978-3-7908-1042-4

  • Online ISBN: 978-3-642-59268-3

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics