1. Proceedings
  2. I3M
  3. 2018
  4. EMSS
  5. 10.46354/i3m.2018.emss.016

Comparing machine learning methods on concept drift detection for Predictive Maintenance

  • a Jan Zenisek  ,
  • b Josef Wolfartsberger  ,
  • c Christoph Sievi  ,  
  • d Michael Affenzeller  
  • a , b, c, dUniversity of Applied Sciences Upper Austria, Hagenberg, (a)(d)Institute for Formal Models and Verification, Johannes Kepler University Linz, Austria
Cite as
Zenisek J., Wolfartsberger J., Sievi C., Affenzeller M. (2018). Comparing machine learning methods on concept drift detection for Predictive Maintenance. Proceedings of the 30th European Modeling & Simulation Symposium (EMSS 2018), pp. 115-122. DOI: https://doi.org/10.46354/i3m.2018.emss.016

Abstract

In this work we present a comparison of various machine learning algorithms with the objective of detecting concept drifts in data streams characteristical for condition monitoring of industrial production plants. Although there is a fair number of contributions employing machine learning algorithms in related fields such as traditional time series forecasting or concept drift learning, data sets with sensor streams from a production plant are rarely covered. This work aims at shedding some light on the matter of how efficient the depicted algorithms perform on concept drift detection to pave the way for Predictive Maintenance (PdM) and which intermediate data processing steps therefore might be beneficial.

References

  1. Affenzeller M., Wagner S., Winkler S. and Beham A., 2009. Genetic Algorithms and Genetic Programming: Modern Concepts and Practical Applications. Chapman & Hall / CRC Press.
  2. Ahmed N. K., Atiya A. F., Gayar N. E. and El-Shishiny H., 2010. An empirical comparison of machine learning models for time series forecasting. Econometric Reviews, 29 (5-6), 594-621.
  3. Altman N. S., 1992. An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician, 46 (3), 175-185.
  4. Bauer D., 2009. Estimating ARMAX systems for0 multivariate time series using the state approach to subspace algorithms. Journal of Multivariate Analysis, 100 (3), 397-421.
  5. Box G. E. and Jenkins G. M., 1970. Time series analysis: forecasting and control. Holden-Day, San Francisco, CA.
  6. Breiman L., 2001. Random forests. Machine Learning, 45 (1), 5-32. Cartella F., Lemeire J., Dimiccoli L. and Sahli, H., 2015. Hidden semi-Markov models for predictive maintenance. Mathematical Problems in Engineering, 2015.
  7. Cleveland R. B., Cleveland W. S. and Terpenning I., 1990. STL: A seasonal-trend decomposition
    procedure based on loess. Journal of Official Statistics, 6 (1), 3.
  8. Cortes C. and Vapnik V., 1995. Support-vector networks. Machine Learning, 20 (3), 273-297.
  9. Graff M., Escalante H. J., Ornelas-Tellez F. and Tellez E. S., 2017. Time series forecasting with genetic programming. Natural Computing, 16 (1), 165-174.
  10. Koza J., 1992. Genetic Programming: On the Programming of Computers by Means of Natural
    Selection. MIT Press, Cambridge, MA, 1992.
  11. Krawczyk B., Minku L. L., Gama J., Stefanowski J. and Woźniak, M., 2017. Ensemble learning for data stream analysis: A survey. Information Fusion, 37, 132-156.
  12. Lee J., Kao H. A., and Yang S., 2014. Service Innovation and Smart Analytics for Industry 4.0 and Big Data Environment. Procedia Cirp, 16, 3-8.
  13. Mattes A., Schöpka U., Schellenberger M.,Scheibelhofer P. and Leditzky G., 2012. Virtual
    equipment for benchmarking predictive maintenance algorithms. In Simulation Conference (WSC), Proceedings of the 2012 Winter, pp. 1-12. IEEE.
  14. Ryll F., and Freund C., 2010. Grundlagen der Instandhaltung. In Instandhaltung technischer
    Systeme, 23-101. Springer, Berlin, Heidelberg.
  15. Saxena A., Goebel K., Simon D. and Eklund N., 2008. Damage Propagation Modeling for Aircraft Engine Run-To-Failure Simulation. Prognostics and Health Management, 2008. Proceedings of 2008 IEEE International Conference on PHM, 1-9.
  16. Stein E. M., 1993. Harmonic Analysis: Real-Variable Methods, Orthogonality, and Oscillatory Integrals.Princeton University Press.
  17. Tsymbal A., 2004. The problem of concept drift: definitions and related work. Computer Science
    Department, Trinity College Dublin, 106 (2).
  18. Wagner S., Kronberger G., Beham A., Kommenda M., Scheibenpflug A., Pitzer E., ... and Affenzeller M., 2014. Architecture and Design of the HeuristicLab Optimization Environment. In Advanced Methods and Applications in Computational Intelligence, pp. 197-261. Springer, Heidelberg.
  19. Winkler S.M., Affenzeller M., Kronberger G, Kommenda M., Burlacu B. and Wagner S., 2015.
    Sliding window symbolic regression for detecting changes of system dynamics. Genetic Programming Theory and Practice XII. Springer 91-107.
  20. Widodo A., and Yang B. S., 2007. Support vector machine in machine condition monitoring and fault diagnosis. Mechanical systems and signal processing, 21 (6), 2560-2574.
  21. Zenisek J., Wolfartsberger J., Sievi C. and Affenzeller M., 2018. Streaming Synthetic Time Series for Simulated Condition Monitoring. IFACPapersOnLine, 51, pp. 6.