1. Proceedings
  2. I3M
  3. 2019
  4. IMAACA
  5. 10.46354/i3m.2019.imaaca.005

Time series model improving with automatic Savitzky-Golay filter for Remaining Useful Life estimation

  • a Youssouf Diaf  , 
  • b Samir Benmoussa  , 
  • c Mohand Djeziri 
  • aAgence Spatiale Algérienne, Bouzareah Alger, 16000 Algeria
  • bLaboratoire d'Automatique et de Signaux de Annaba (LASA), University Badji Mokhtar Annaba, 23000 Algeria
  • cLaboratoire des Sciences de l'Information et des Systemes (LSIS), UMR CNRS 7296 France
Cite as
Diaf Y., Benmoussa S., Djeziri M. (2019). Time series model improving with automatic Savitzky-Golay filter for Remaining Useful Life estimation. Proceedings of the 12th International Conference on Integrated Modeling and Analysis in Applied Control and Automation (IMAACA 2019), pp. 32-37. DOI: https://doi.org/10.46354/i3m.2019.imaaca.005

Abstract

The performance of fault diagnosis and failure prognosis methods is directly related to the quality of sensor measurements. When the systems evolve under extreme conditions of use as in the aeronautical field, the sensors measure are often impacted by strong noise and disturbances. This paper deals with the using of an automatic Savitzky-Golay filter to smooth the sensors data for time series model training and remaining useful life estimation. A proposed window value calculation for the Savitzky-Golay filter is used to improve signal quality. The NARX neuronal network is used as a datadriven approach to model the trend of the smoothed time series data. The proposed approach is successfully applied for degradation-trend modeling and remaining useful life prediction in turbo engines. These systems are considered as a high noise device which mean more challenge in data processing. The results show an improvement in the prediction of the remaining useful life compared to previous works.

References

  1. Abraham, Savitzky, and Marcel J. E. Golay. 1964. "Smoothing and Differentiation of Data by Simplified Least Squares Procedures." Analytical Chemistry (American Chemical Society) 36 (8):
    1627–1639. doi:10.1021/ac60214a047
  2. Al-Dahidi, Sameer, Francesco Di Maio, Piero Baraldi, and Enrico Zio. 2016. "Remaining useful life estimation in heterogeneous fleets working under variable operating conditions." Reliability
    Engineering & System Safety 156: 109–124.
  3. B., Scholkopf, and Smola A. J. 2001. Learning with kernels:support vector machines, regularization, optimization, and beyond. The MIT Press.
  4. Bektas, Oguz, and Jeffrey A. Jones. 2016. "NARX Time Series Model for Remaining Useful Life Estimation of Gas Turbine Engines." EUROPEAN CONFERENCE OF THE PROGNOSTICS AND
    HEALTH MANAGEMENT SOCIETY 2016.
  5. Benmoussa, Samir, and Mohand Arab Djeziri. 2017. "Remaining useful life estimation without needing for prior knowledge of the degradation features." IET Science, Measurement & Technology 11 (8): 1071 - 1078.
  6. Billings, Stephen A. 2013. Nonlinear System Identification: NARMAX Methods in the Time,
    Frequency and Spatio-Temporal Domains. Wiley.
  7. Bluvband, Zigmund, and Sergey Porotsky. 2016. Prognostic and Health Management: God Is in
    Details
  8. Bowman, Adrian W., and Adelchi Azzalini. 1997. Applied Smoothing Techniques for Data Analysis: The Kernel Approach with S-Plus Illustrations . New York: CLARENDON PRESS OXFORD.
  9. Cichocki, Andrzej, Shun-ichi Amari, Krzysztof Siwek, and Toshihisa Tanaka and al. n.d.
    http://www.bsp.brain.riken.jp/ICALAB. ICALAB Toolboxes.
  10. Coble, Jamie, and J. Wesley Hines. 2012. "Identifying Suitable Degradation Parameters for Individual- Based Prognostics." In Diagnostics and Prognostics of Engineering Systems_ Methods and Techniques, 145. IGI Global.
  11. Djeziri, Mohand Arab, Samir Benmoussa, and Roberto Sanchez. 2018. "Hybrid method for remaining useful life prediction in wind turbine systems." Renewable Energy 116: 173 - 187.
  12. Dombi, József, and Adrienn Dineva. 2018. "Adaptive Multi-round Smoothing Based on the Savitzky- Golay Filter." International Workshop Soft Computing Applications. 446-454.
  13. Dombi, József, and Adrienn Dineva. 2018. "Adaptive Multi-round Smoothing Based on the Savitzky- Golay Filter." In Advances in Intelligent Systems and Computing, by József Dombi and Adrienn Dineva, 446-454.
  14. Heimes, Felix O. 2008. "Recurrent neural networks for remaining useful life estimation." Proceedings of the Annual Conference on Prognostics and Health Management Society
  15. javed, kamran, rafael gouriveau, ryad zemouri, and noureddine zerhouni. 2011. "Improving data-driven prognostics by assessing predictability of features." Proceedings of the Annual Conference of the Prognostics and Health Management Society.
  16. K., Javed, Gouriveau R., Zemouri R., and Zerhouni N. 2011. "Improving data-driven prognostics by assessing predictability of features." Proceedings of the Annual Conference of the Prognostics and Health Management Society.
  17. M, Tipping. 2001. "Sparse Bayesian learning and the Relevance Vector Machine." Journal of Machine Learning Research 1 (3): 211–244.
  18. Michael, E. Tipping. 2001. "Sparse Bayesian learning and the Relevance Vector Machine." Journal of Machine Learning Research 1 (3): 211–244.
  19. Narendra, Kumpati S., and Kannan Parthasarathy. 1991. "Learning Automata Approach to Hierarchical Multiobjective Analysis." IEEE Transactions on Systems, Man and Cybernetics 20 (1): 263–272
  20. NASA. n.d. prognostic-data-repository. NASA. https://ti.arc.nasa.gov/tech/dash/pcoe/prognosticdata- repository/.
  21. O., Heimes F. 2008. "Recurrent neural networks for remaining useful life estimation." Proceedings of the Annual Conference on Prognostics and Health Management Society
  22. Rai, Akhand, and S.H. Upadhyay. 2017. "The use of MD-CUMSUM and NARX neural network for anticipating the remaining useful life of bearings." Measurement 111: 397-410.
  23. Santoso, Gunawan Budi, Toni Prahasto, and Achmad Widodo. 2013. "Prognosis of bearing damage performance to industrial system using nonlinear autoregressive with exogenous (NARX)." 2013 International Conference on QiR.
  24. Saxena, Abhinav, and Kai Goebel. 2008. Turbofan Engine Degradation Simulation Data Set. Edited by NASA Ames Research Center. Moffett Field, CA. http://ti.arc.nasa.gov/project/prognostic-datarepository.
  25. Saxena, Abhinav, Jose Celaya, Edward Balaban, Kai Goebel, Bhaskar Saha, Sankalita Saha, and Mark Schwabacher. 2008. "Metrics for evaluating performance of prognostic techniques." 2008
    International Conference on Prognostics and Health Management. 1-17
  26. Saxena, Abhinav, Kai Goebel, Don Simon, and Neil Eklund. 2008. "Damage Propagation Modeling for Aircraft Engine Run-to-Failure Simulation." Proceedings of the Ist International Conference on Prognostics and Health Management (PHM08). Denver CO.
  27. Schölkopf, Bernhard, and Alexander J. Smola. 2001 Learning with kernels:support vector machines, regularization, optimization, and beyond. The MIT Press.
  28. Steinier, Jean, Yves Termonia, and Jules Deltour. 1972."Smoothing and differentiation of data by simplified least square procedure." AnalyticalChemistry 44 (11): 1906-1909. doi:10.1021/ac60319a045.
  29. T., Wang, Yu J., Siegel D., and Lee J. 2008. "A similarity-based prognostics approach for
    Remaining Useful Life estimation of engineered systems." Proceedings of the Annual Conference on Prognostics and Health Management Society.
  30. Tianyi, Wang, Jianbo Yu, David Siegel, and Jay Lee. 2008. "A similarity-based prognostics approach for Remaining Useful Life estimation of engineered systems." Proceedings of the Annual Conference on Prognostics and Health Management Society.
  31. Vichare, Nikhil M., and Michael G. Pecht. 2006. "Prognostics and Health Management of
    Electronics." IEEE Transactions on Components and Packaging Technologies 29 (1): 222-229.
  32. Zhu, Gao Feng, Hong Qiu Zhu, Chun Hua Yang, and Wei Hua Gui. 2017. "Improved Savitzky-Golay filtering algorithm for measuring a pharmaceutical vial’s oxygen content based on wavelength modulation spectroscopy." Journal of Optical Technology 84
    (5): 355.