Episode Rule-Based Prognosis Applied to Complex Vacuum Pumping Systems Using Vibratory Data

  • Florent Martin
  • Nicolas Méger
  • Sylvie Galichet
  • Nicolas Becourt
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6171)


This paper presents a local pattern-based method that addresses system prognosis. It also details a successful application to complex vacuum pumping systems. More precisely, using historical vibratory data, we first model the behavior of systems by extracting a given type of episode rules, namely First Local Maximum episode rules (FLM-rules). A subset of the extracted FLM-rules is then selected in order to further predict pumping system failures in a vibratory datastream context. The results that we got for production data are very encouraging as we predict failures with a good time scale precision. We are now deploying our solution for a customer of the semi-conductor market.


episode rules FLM-rules predictive maintenance prognosis vibratory signals 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Abu-Hanna, A., Lucas, P.J.F.: Prognostic models in medicine: AI and statistical approaches. Jr. of Methods of Information in Medicine 40, 1–5 (2001)Google Scholar
  2. 2.
    Agrawal, R., Srikant, R.: Mining sequential patterns. In: Proc. of the 11th Intl. Conf. on Data Engineering, pp. 3–14 (1995)Google Scholar
  3. 3.
    Cho, C., Zheng, Y., Chen, A.L.P.: Continuously Matching Episode Rules for Predicting Future Events over Event Streams. In: Dong, G., Lin, X., Wang, W., Yang, Y., Yu, J.X. (eds.) APWeb/WAIM 2007. LNCS, vol. 4505, pp. 884–891. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  4. 4.
    Fiot, C., Masseglia, F., Laurent, A., Teisseire, M.: Gradual trends in fuzzy sequential patterns. In: Proc. of the 12th Intl. Conf. on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU), pp. 456–463 (2008)Google Scholar
  5. 5.
    Giannella, C., Han, J., Pei, J., Yan, X., Yu, P.S.: Mining frequent patterns in data streams at multiple time granularities. Next Generation Data Mining 212, 191–212 (2003)Google Scholar
  6. 6.
    Grabill, P., Brotherton, T., Berry, J., Grant, L.: The us army and national guard vibration management enhancement program: data analysis and statistical results. In: Annual proceeding of American helicopter society, vol. 58, pp. 105–119 (2002)Google Scholar
  7. 7.
    Hatonen, K., Klemettinen, M., Mannila, H., Ronkainen, P., Toivonen, H.: TASA: Telecomunications Alarm Sequence Analyzer or: How to enjoy faults in your network. In: IEEE Network Operations and Management Symposium, pp. 520–529 (1996)Google Scholar
  8. 8.
    Harding, J.A., Shahbaz, M., Kusiak, A.: Data mining in manufacturing: a review. Jr. of Manufacturing Science and Engineering 128(4), 969–976 (2006)CrossRefGoogle Scholar
  9. 9.
    Letourneau, S., Famili, F., Matwin, S.: Data mining for prediction of aircraft component replacement. IEEE Intelligent Systems and their Applications 14(6), 59–66 (1999)Google Scholar
  10. 10.
    Lalanne, C.: Vibrations aléatoires. Hermes Science (1999)Google Scholar
  11. 11.
    Le Normand, N., Boissiere, J., Meger, N., Valet, L.: Supply chain management by means of FLM-rules. In: 12th European Conf. on Principles and Practice of Knowledge Discovery in Databases (PKDD), pp. 29–36 (2008)Google Scholar
  12. 12.
    Magoulas, G.D., Prentza, A.: Machine learning in medical applications. Jr. Machine Learning and Its Applications 2049, 300–307 (2001)CrossRefGoogle Scholar
  13. 13.
    Meger, N., Rigotti, C.: Constraint-based mining of episode rules and optimal window sizes. In: Chin, W.-N. (ed.) APLAS 2004. LNCS, vol. 3302, pp. 313–324. Springer, Heidelberg (2004)Google Scholar
  14. 14.
    Mannila, H., Toivonen, H.: Discovering generalized episodes using minimal occurrences. In: Proc. of the 2nd Intl. Conf. on Knowledge Discovery and Data Mining (KDD), pp. 146–151 (1996)Google Scholar
  15. 15.
    Mannila, H., Toivonen, H., Verkamo, A.I.: Discovery of frequent episodes in event sequences. Jr. of Data Mining and Knowledge Discovery 1(3), 259–298 (1997)CrossRefGoogle Scholar
  16. 16.
    Raghavan, V., Hafez, A.: Dynamic data mining. In: Logananthara, R., Palm, G., Ali, M. (eds.) IEA/AIE 2000. LNCS (LNAI), vol. 1821, pp. 220–229. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  17. 17.
    Schwabacher, M., Goebel, K.: A Survey of Artificial Intelligence for Prognostics. In: Working Notes of 2007 American Institute in Aeronautics and Astronautics Fall Symposium: AI for Prognostics (2007)Google Scholar
  18. 18.
    Jens, T.B.: Mechanical Vibration and Shock Measurements. Bruel & Kjaer (1973)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Florent Martin
    • 1
    • 2
  • Nicolas Méger
    • 1
  • Sylvie Galichet
    • 1
  • Nicolas Becourt
    • 2
  1. 1.University of Savoie, Polytech’Savoie, LISTIC laboratoryAnnecy-le-VieuxFrance
  2. 2.Alcatel Vacuum technologyAnnecyFrance

Personalised recommendations