Skip to content
Licensed Unlicensed Requires Authentication Published by Oldenbourg Wissenschaftsverlag September 5, 2019

Machine learning in industrial measurement technology for detection of known and unknown faults of equipment and sensors

Machine Learning in der industriellen Messtechnik zur Erkennung bekannter und unbekannter Anlagen- und Sensorfehler
  • Tizian Schneider

    Tizian Schneider studied Microtechnologies and Nanostructures at Saarland University and received his Master of Science degree in January 2016. Since that time he has been working at Centre for Mechatronics and Automation Technology (ZeMA), division ‘Sensors and Actuators’ and leads the field of data-based condition monitoring for industrial applications such as fluid power and electromechanical drive systems.

    EMAIL logo
    , Steffen Klein

    Steffen Klein studied Mechatronics and received Master of Science degree in May 2018. Since that time he has been working at Saarland University at the Laboratory for Measurement Technology (LMT), in the field of data-based condition monitoring for industrial applications such as fluid power and electromechanical drive systems.

    and Andreas Schütze

    Andreas Schütze received his diploma in physics from RWTH Aachen in 1990 and his doctorate in Applied Physics from Justus-Liebig-Universität in Gießen in 1994 with a thesis on microsensors and sensor systems for the detection of reducing and oxidizing gases. From 1994 until 1998 he worked for VDI/VDE-IT, Teltow, Germany, mainly in the fields of microsystems technology. From 1998 until 2000 he was professor for Sensors and Microsystem Technology at the University of Applied Sciences in Krefeld, Germany. Since April 2000 he is professor for Measurement Technology in the Department of Mechatronics at Saarland University, Saarbrücken, Germany and head of the Laboratory for Measurement Technology (LMT). His research interests include microsensors and microsystems, especially intelligent gas sensor systems for security applications.

From the journal tm - Technisches Messen

Abstract

This paper focuses on the application of novelty detection in combination with supervised fault classification for industrial condition monitoring. Its goal is to provide a guideline for engineers on how to apply novelty detection for outlier detection, monitoring of supervised classification and detection of unknown faults without the need of a data scientist. All guidelines are demonstrated by means of a publicly available condition monitoring dataset. In each application case the results achieved with different common novelty detection algorithms are compared, advantages and disadvantages of the respective algorithms are shown. To increase applicability of the suggested approach visualization of results is emphasized and all algorithms have been included in a publicly available data analysis software toolbox with graphical user interface.

Zusammenfassung

Dieser Aufsatz befasst sich mit der Anwendung von Anomaliedetektion in Kombination mit überwachter Schadensklassifikation in der industriellen Messtechnik. Ziel ist es Ingenieuren einen Leitfaden an die Hand zu geben, wie Anomaliedetektion auch ohne Data Scientist zur Erkennung von Ausreißern, zur Kontrolle der überwachten Schadenserkennung und zur Erkennung bisher unbekannter Maschinenstörungen eingesetzt werden kann. Alle empfohlenen Vorgehensweisen werden an einem öffentlich zugänglichen Datensatz zum Thema Zustandsüberwachung demonstriert. In jedem Anwendungsszenario werden die mit unterschiedlichen und weit verbreiteten erreichten Algorithmen zur Anomaliedetektion verglichen und Vor- und Nachteile aufgezeigt. Um die Hemmschwelle beim Einsatz der vorgeschlagenen Herangehensweise zu senken wird großer Wert auf Visualisierungen von Ergebnissen gelegt. Weiterhin sind alle verwendeten Algorithmen Teil einer kostenlosen Software zur Datenanalyse mit grafischem Benutzerinterface.

Award Identifier / Grant number: 16ES0419K

Funding statement: The research presented in this paper was in part performed during the projects MoSeS-Pro and iCM Hydraulics at ZeMA – Center for Mechatronics and Automation Technology gGmbH; MoSeS-Pro: German Federal Ministry of Education and Research, funding code 16ES0419K; iCM Hydraulics: EFI program (support of development, research, and innovation in Saarland), research by ZeMA was financed by HYDAC Filter Systems.

About the authors

Tizian Schneider

Tizian Schneider studied Microtechnologies and Nanostructures at Saarland University and received his Master of Science degree in January 2016. Since that time he has been working at Centre for Mechatronics and Automation Technology (ZeMA), division ‘Sensors and Actuators’ and leads the field of data-based condition monitoring for industrial applications such as fluid power and electromechanical drive systems.

Steffen Klein

Steffen Klein studied Mechatronics and received Master of Science degree in May 2018. Since that time he has been working at Saarland University at the Laboratory for Measurement Technology (LMT), in the field of data-based condition monitoring for industrial applications such as fluid power and electromechanical drive systems.

Andreas Schütze

Andreas Schütze received his diploma in physics from RWTH Aachen in 1990 and his doctorate in Applied Physics from Justus-Liebig-Universität in Gießen in 1994 with a thesis on microsensors and sensor systems for the detection of reducing and oxidizing gases. From 1994 until 1998 he worked for VDI/VDE-IT, Teltow, Germany, mainly in the fields of microsystems technology. From 1998 until 2000 he was professor for Sensors and Microsystem Technology at the University of Applied Sciences in Krefeld, Germany. Since April 2000 he is professor for Measurement Technology in the Department of Mechatronics at Saarland University, Saarbrücken, Germany and head of the Laboratory for Measurement Technology (LMT). His research interests include microsensors and microsystems, especially intelligent gas sensor systems for security applications.

Acknowledgment

The authors thank Pragya Pande for her overview of novelty detection [16] and for making her implementation of the used novelty detection algorithms available. Also the authors thank Jannis Morsch for implementing the reconstruction error based algorithm selection for feature extraction used in Section 5 and for porting the novelty detection algorithms and their visualizations to DAV3E.

References

1. “Industrial Internet Consortium.” [Online]. Available: http://www.iiconsortium.org. [Accessed: 10-Jun-2019].Search in Google Scholar

2. T. Schneider, N. Helwig, and A. Schütze, “Industrial condition monitoring with smart sensors using automated feature extraction and selection,” Meas. Sci. Technol., vol. 29, no. 9, p. 094002, Sep. 2018.10.1088/1361-6501/aad1d4Search in Google Scholar

3. P. Henriquez, J. B. Alonso, M. A. Ferrer, and C. M. Travieso, “Review of automatic fault diagnosis systems using audio and vibration signals,” IEEE Trans. Syst. Man, Cybern. Syst., vol. 44, no. 5, pp. 642–652, 2014.10.1109/TSMCC.2013.2257752Search in Google Scholar

4. M. A. F. Pimentel, D. A. Clifton, L. Clifton, and L. Tarassenko, “A review of novelty detection,” Signal Processing, vol. 99, pp. 215–249, 2014.10.1016/j.sigpro.2013.12.026Search in Google Scholar

5. E. Keogh and S. Kasetty, “On the Need for Time Series Data Mining Benchmarks: A Survey and Empirical Demonstration,” Data Min. Knowl. Discov., vol. 7, no. 4, pp. 349–371, 2003.10.1023/A:1024988512476Search in Google Scholar

6. M. Bastuck, T. Baur, and A. Schütze, “DAV3E – a MATLAB toolbox for multivariate sensor data evaluation,” J. Sensors Sens. Syst., vol. 7, no. 2, pp. 489–506, Sep. 2018.10.5194/jsss-7-489-2018Search in Google Scholar

7. M. Markou and S. Singh, “Novelty detection: a review – part 1: statistical approaches,” vol. 83, pp. 2481–2497, 2003.10.1016/j.sigpro.2003.07.018Search in Google Scholar

8. D. Miljković, “Review of Novelty Detection Methods,” Proc. Int. Conv. MIPRO, no. June, pp. 593–598, 2010.Search in Google Scholar

9. C. Chow, “On optimum recognition error and reject tradeoff,” IEEE Trans. Inf. Theory, vol. 16, no. 1, pp. 41–46, Jan. 1970.10.1109/TIT.1970.1054406Search in Google Scholar

10. C. Keribin, “Consistent Estimate of the Order of Mixture Models,” Sankhy, Ser. A, vol. 64, no. 01, pp. 49–66, Jul. 2000.Search in Google Scholar

11. T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning. New York, NY: Springer New York, 2009.10.1007/978-0-387-84858-7Search in Google Scholar

12. M. Zhao and V. Saligrama, “Anomaly Detection with Score functions based on Nearest Neighbor Graphs,” Neural Information Processing Systems, pp. 1–9, 2009.Search in Google Scholar

13. A. DasGupta, Probability for Statistics and Machine Learning. New York, NY: Springer New York, 2011.10.1007/978-1-4419-9634-3Search in Google Scholar

14. A. Beghi, L. Cecchinato, C. Corazzol, M. Rampazzo, F. Simmini, and G. A. Susto, “A One-Class SVM Based Tool for Machine Learning Novelty Detection in HVAC Chiller Systems,” IFAC Proc. Vol., vol. 47, no. 3, pp. 1953–1958, 2014.10.3182/20140824-6-ZA-1003.02382Search in Google Scholar

15. B. B. Thompson, R. J. Marks, J. J. Choi, M. A. El-Sharkawi, Ming-Yuh Huang, and C. Bunje, “Implicit learning in autoencoder novelty assessment,” in Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN’02 (Cat. No. 02CH37290), pp. 2878–2883.Search in Google Scholar

16. Pragya Pande, “Novelty detection for unknown faults in industrial condition monitoring and further applications,” Saarland University, 2018.Search in Google Scholar

17. K. Beyer, J. Goldstein, R. Ramakrishnan, and U. Shaft, “When Is ‘Nearest Neighbor’ Meaningful?,” in 7th International Conference on Database Theory – ICDT’99, 1999, pp. 217–235.10.1007/3-540-49257-7_15Search in Google Scholar

18. N. Helwig, E. Pignanelli, and A. Schutze, “Condition monitoring of a complex hydraulic system using multivariate statistics,” in 2015 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings, 2015, pp. 210–215.10.1109/I2MTC.2015.7151267Search in Google Scholar

19. D. Dua and C. Graff, “UCI Machine Learning Repository,” 2017. [Online]. Available: http://archive.ics.uci.edu/ml. [Accessed: 10-Jun-2019].Search in Google Scholar

20. K. Backhaus, B. Erichson, W. Plinke, and R. Weiber, Multivariate Analysemethoden: Eine anwendungsorientierte Einführung, 9 überarbe, Berlin Heidelberg New York: Springer-Verlag, 2000.10.1007/978-3-662-08893-7Search in Google Scholar

21. X. Wang, A. Mueen, H. Ding, G. Trajcevski, P. Scheuermann, and E. Keogh, “Experimental comparison of representation methods and distance measures for time series data,” Data Min. Knowl. Discov., vol. 26, no. 2, pp. 275–309, Mar. 2013.10.1007/s10618-012-0250-5Search in Google Scholar

22. N. Helwig, E. Pignanelli, and A. Schütze, “Detecting and Compensating Sensor Faults in a Hydraulic Condition Monitoring System,” in Proceedings SENSOR, 2015, pp. 641–646.10.5162/sensor2015/D8.1Search in Google Scholar

Received: 2019-06-11
Accepted: 2019-08-12
Published Online: 2019-09-05
Published in Print: 2019-11-26

© 2019 Walter de Gruyter GmbH, Berlin/Boston

Downloaded on 29.3.2024 from https://www.degruyter.com/document/doi/10.1515/teme-2019-0086/pdf
Scroll to top button