Skip to main content
SpringerLink
Log in

A novel unsupervised method for anomaly detection in time series based on statistical features for industrial predictive maintenance

  • Application
  • Published:
International Journal of Data Science and Analytics Aims and scope Submit manuscript

Abstract

Industrial production processes are increasingly collecting data from machines in operation due to the cost reduction and popularization of sensor technologies. Valuable information is generated by using the right sensors and proper techniques on the machine’s current state in operation. This extraction allows detecting whether the machine is operating in a degraded state and then, if necessary, interrupts its operation before it goes into a broken state. The detection of the abnormal behavior of a machine is relevant since detection at the right time can reduce financial costs due to machine breakdown and production downtime. This work proposes a novel unsupervised method to detect anomalies in industrial machines and interrupt their operation before this machine goes into a state of breakdown. The proposed method receives as input a set of time series data from several sensors. Using a collection of statistical features, it calculates an indicator that characterizes the failure’s severity, issuing an alert to the machine operator if necessary. The method was evaluated in two benchmarks with known univariate data and two proprietary datasets with multivariate data. Conducted experiments revealed the low computational time spent on training and on evaluation. Overall results measured in Area Under the Receiver Operating Characteristic Curve (AUC) in Yahoo’s benchmark were 89.3%; in Numenta, it was 70.3%, and in the two multivariate datasets evaluated, it was 92.4% and 91.2%. These high AUC values reveal the potential of the proposed method applied in predictive maintenance in a large soybean oil production industry.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Notes

  1. https://webscope.sandbox.yahoo.com/catalog.php?datatype.

  2. https://github.com/numenta/NAB.

  3. https://github.com/KDD-OpenSource/agots.

  4. https://github.com/jesimar/aod.

References

  1. Ahmad, S., Lavin, A., Purdy, S., Agha, Z.: Unsupervised real-time anomaly detection for streaming data. Neurocomputing 262, 134–147 (2017)

    Article  Google Scholar 

  2. Amarbayasgalan, T., Pham, V.H., Theera-Umpon, N., Ryu, K.H., et al.: Unsupervised anomaly detection approach for time-series in multi-domains using deep reconstruction error. Symmetry 12(8), 1251 (2020)

    Article  Google Scholar 

  3. Anderson, M.J., Thompson, A.A.: Multivariate control charts for ecological and environmental monitoring. Ecol. Appl. 14(6), 1921–1935 (2004)

    Article  Google Scholar 

  4. Attoui, I., Oudjani, B., Boutasseta, N., Fergani, N., Bouakkaz, M.S., Bouraiou, A.: Novel predictive features using a wrapper model for rolling bearing fault diagnosis based on vibration signal analysis. Int. J. Adv. Manuf. Technol. 106(7–8), 3409–3435 (2020)

    Article  Google Scholar 

  5. Blanchard, B.S., Verma, D.C., Peterson, E.L.: Maintainability: A Key to Effective Serviceability and Maintenance Management, vol. 13. Wiley, Hoboken (1995)

    Google Scholar 

  6. Blázquez-García, A., Conde, A., Mori, U., Lozano, J.A.: A review on outlier/anomaly detection in time series data. arXiv preprint arXiv:2002.04236 (2020)

  7. Carvalho, T.P., Soares, F.A., Vita, R., Francisco, Rd.P., Basto, J.P., Alcalá, S.G.: A systematic literature review of machine learning methods applied to predictive maintenance. Comput. Ind. Eng. 137, 106024 (2019)

    Article  Google Scholar 

  8. Xy, Chen, Yy, Zhan: Multi-scale anomaly detection algorithm based on infrequent pattern of time series. J. Comput. Appl. Math. 214(1), 227–237 (2008)

    Article  MathSciNet  Google Scholar 

  9. Dias, C.G., da Silva, L.C., Chabu, I.E.: Fuzzy-based statistical feature extraction for detecting broken rotor bars in line-fed and inverter-fed induction motors. Energies 12(12), 2381 (2019)

    Article  Google Scholar 

  10. Ding, N., Ma, H., Gao, H., Ma, Y., Tan, G.: Real-time anomaly detection based on long short-term memory and Gaussian mixture model. Comput. Electr. Eng. 79, 106458 (2019)

    Article  Google Scholar 

  11. Fernandez-Temprano, M., Gardel-Sotomayor, P., Duque-Perez, O., Morinigo-Sotelo, D.: Broken bar condition monitoring of an induction motor under different supplies using a linear discriminant analysis. In: 9th IEEE International Symposium on Diagnostics for Electric Machines. Power Electronics and Drives (SDEMPED), pp. 162–168. IEEE (2013)

  12. Hochenbaum, J., Vallis, O.S., Kejariwal, A.: Automatic anomaly detection in the cloud via statistical learning. arXiv preprint arXiv:1704.07706 (2017)

  13. ISO: Condition monitoring and diagnostics of machines-general guidelines. Standard, International Organization for Standardization (2018)

  14. Jimenez, J.J.M., Schwartz, S., Vingerhoeds, R., Grabot, B., Salaün, M.: Towards multi-model approaches to predictive maintenance: a systematic literature survey on diagnostics and prognostics. J. Manuf. Syst. 56, 539–557 (2020)

    Article  Google Scholar 

  15. Kagermann, H., Wahlster, W., Helbig, J.: Recommendations for implementing the strategic initiative industrie 4.0. Report, ACATECH-National Academy of Science and Engineering. http://alvarestech.com/temp/tcn/CyberPhysicalSystems-Industrial4-0.pdf (2013)

  16. Kim, T.H., White, H.: On more robust estimation of skewness and kurtosis. Financ. Res. Lett. 1(1), 56–73 (2004)

    Article  Google Scholar 

  17. Laptev, N., Amizadeh, A., Billawala, Y.: Yahoo labs news: announcing a benchmark dataset for time series anomaly detection [online blog]. https://research.yahoo.com/news/announcing-benchmark-dataset-time-series-anomaly-detection (2015a)

  18. Laptev, N., Amizadeh, S., Flint, I.: Generic and scalable framework for automated time-series anomaly detection. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1939–1947 (2015b)

  19. Lavin, A., Ahmad, S.: Evaluating real-time anomaly detection algorithms–the numenta anomaly benchmark. In: IEEE 14th International Conference on Machine Learning and Applications (ICMLA), pp. 38–44. IEEE (2015)

  20. Lee, J., Bagheri, B., Kao, H.: A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manuf. Lett. 3, 18–23 (2015)

    Article  Google Scholar 

  21. Munir, M., Siddiqui, S.A., Dengel, A., Ahmed, S.: DeepAnT: a deep learning approach for unsupervised anomaly detection in time series. IEEE Access 7, 1991–2005 (2018)

    Article  Google Scholar 

  22. Nemeth, T., Ansari, F., Sihn, W.: A maturity assessment procedure model for realizing knowledge-based maintenance strategies in smart manufacturing enterprises. Procedia Manuf. 39, 645–654 (2019)

    Article  Google Scholar 

  23. Olive, D.J.: Applied robust statistics. Preprint M-02-006 (2008)

  24. Shukla, S., Yadav, R., Sharma, J., Khare, S.: Analysis of statistical features for fault detection in ball bearing. In: IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), pp. 1–8. IEEE (2015)

  25. Stern, S., Farioli, S., Eisenschmidt, E., Morachioli, S., Kienzler, C., Jeske, D., Schaal, N.: The future of maintenance for distributed fixed assets. Technical report, McKinsey Company In collaboration with Lumics (2020)

  26. Sullivan, G. P, Pugh, R., Melendez, A. P.: Operations and maintenance best practices—a guide to achieving operational efficiency. Technical report, Pacific Northwest National Lab., Richland, WA (US) (2002)

  27. Susto, G.A., Schirru, A., Pampuri, S., McLoone, S., Beghi, A.: Machine learning for predictive maintenance: a multiple classifier approach. IEEE Trans. Ind. Inf. 11(3), 812–820 (2014)

    Article  Google Scholar 

  28. Wang, J., Zhao, R., Gao, R.X.: Probabilistic transfer factor analysis for machinery autonomous diagnosis cross various operating conditions. IEEE Trans. Instrum. Meas. 69, 5335–5344 (2020)

    Article  Google Scholar 

  29. Wu, J., Zeng, W., Yan, F.: Hierarchical temporal memory method for time-series-based anomaly detection. Neurocomputing 273, 535–546 (2018)

    Article  Google Scholar 

  30. Xia, Z., Xia, S., Wan, L., Cai, S.: Spectral regression based fault feature extraction for bearing accelerometer sensor signals. Sensors 12(10), 13694–13719 (2012)

    Article  Google Scholar 

  31. Yaacob, A. H., Tan, I. K., Chien SF, Tan, H. K.: Arima based network anomaly detection. In: Second International Conference on Communication Software and Networks, pp. 205–209. IEEE (2010)

  32. Zheng, D., Li, F., Zhao, T.: Self-adaptive statistical process control for anomaly detection in time series. Expert Syst. Appl. 57, 324–336 (2016)

    Article  Google Scholar 

Download references

Acknowledgements

The authors of this work thank the SENAI Institute of Innovation in Embedded Systems for its support in research development.

Author information

Authors and Affiliations

  1. SENAI Institute of Embedded Systems, Av. Luiz Boiteux Piazza, Florianópolis, Santa Catarina, Brazil

    Jesimar da Silva Arantes, Márcio da Silva Arantes & Renan Bonnard

  2. SENAI Institute of Embedded Systems, Federal University of Santa Catarina, Campus Universitário, Av. Luiz Boiteux Piazza, Florianópolis, Brazil

    Herberth Birck Fröhlich

  3. École Polytechnique Montréal, Montreal, QC, Canada

    Laure Siret

Authors
  1. Jesimar da Silva Arantes
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Márcio da Silva Arantes
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Herberth Birck Fröhlich
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Laure Siret
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Renan Bonnard
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jesimar da Silva Arantes.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

da Silva Arantes, J., da Silva Arantes, M., Fröhlich, H.B. et al. A novel unsupervised method for anomaly detection in time series based on statistical features for industrial predictive maintenance. Int J Data Sci Anal 12, 383–404 (2021). https://doi.org/10.1007/s41060-021-00283-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s41060-021-00283-z

Keywords

Search

Navigation