APPLIED RESEARCH

Anomalous operating mode detection in a technological process from multichannel telemetry accounting for the duration and consistency of deviations

Authors

  • Natalya A. Naumova MIREA – Russian Technological University, 119454, Moscow, Vernadskogo Avenue, 78
  • Elizaveta A. Knyazeva MIREA – Russian Technological University, 119454, Moscow, Vernadskogo Avenue, 78
  • Marina O. Zhuravleva https://orcid.org/0009-0001-9282-2807 MIREA – Russian Technological University, 119454, Moscow, Vernadskogo Avenue, 78
  • Mikhail N. Samokhin https://orcid.org/0009-0008-6259-0073 MIREA – Russian Technological University, 119454, Moscow, Vernadskogo Avenue, 78
  • Timur R. Maksumov MIREA – Russian Technological University, 119454, Moscow, Vernadskogo Avenue, 78

How to cite

GOST Naumova N. A., Knyazeva E. A., Zhuravleva M. O., Samokhin M. N., Maksumov T. R. Anomalous operating mode detection in a technological process from multichannel telemetry accounting for the duration and consistency of deviations // STROITEL'NYE I DOROZHNYE MASHINY. 2026. Vol. 70. No. 10. P. 177-193. DOI: 10.25726/b3606-9398-4387-w
APA Naumova, N. A., Knyazeva, E. A., Zhuravleva, M. O., Samokhin, M. N. & Maksumov, T. R. (2026). Anomalous operating mode detection in a technological process from multichannel telemetry accounting for the duration and consistency of deviations. STROITEL'NYE I DOROZHNYE MASHINY, 70(10), 177-193. https://doi.org/10.25726/b3606-9398-4387-w

Abstract

The three-sigma rule applied to each telemetry channel separately reacts to single noise extremes and responds poorly to slow changes. The paper proposes a decision rule that supplements the threshold on the normalized deviation with three checks: the duration of the exceedance, coincident exceedances in several channels, and the slope of the parameter in a sliding window. A false alarm probability estimate under Gaussian noise is derived for each check, so the thresholds can be chosen before testing. The rule was tested on synthetic telemetry of a CNC milling machine (spindle current, vibration and spindle speed) with four types of injected anomalies and a series of runs with different noise realizations. Compared with the three-sigma rule, false events decreased several-fold at the same detection recall, and the advantage held in every run. The analytical estimates agreed with the simulation results. Disabling the checks one at a time showed that the slope check produces almost all remaining false alarms, while the channel coincidence check duplicates the others when anomalies are pronounced. Neither method detects the initial part of a slow trend.

Keywords

anomaly detection multichannel telemetry statistical process control run of exceedances false alarm probability CNC milling machine synthetic data F1 score

Funding

The authors did not declare any external funding for this research.

References

Vasilyev V.I., Vulfin A.M., Gvozdev V.E., Kartak V.M., Atarskaya E.A. Ensuring information security of cyber-physical objects based on forecasting and detection of anomalies in their state // Systems of Control, Communication and Security. 2021. no. 6. pp. 90-119.

GOST R ISO 17359-2015. Condition monitoring and diagnostics of machines. General guidelines: national standard of the Russian Federation: introduced 2016-12-01. Moscow: Standartinform, 2016. 32 pp.

GOST R ISO 7870-2-2015. Statistical methods. Control charts. Part 2. Shewhart control charts: national standard of the Russian Federation: introduced 2016-12-01. Moscow: Standartinform, 2016. 32 pp.

Novikova E.S., Bukhtiyarov M.A., Kotenko I.V., Saenko I.B., Fedorchenko E.V. An approach to explainable anomaly detection in data streams from technological processes // Cybersecurity Issues. 2025. no. 4 (68). pp. 142-151.

Tugengold A.K., Voloshin R.N., Yushchenko S.V. Monitoring the condition of multi-operation machine tools based on the e-Mind Machine concept // Vestnik of Don State Technical University. 2016. no. 1 (83). pp. 77-86.

Shiryaev A.N. On optimal methods in problems of quickest detection // Theory of Probability and Its Applications. 1963. vol. 8. no. 1. pp. 26-51.

Agogino A., Goebel K. Milling data set // NASA Prognostics Data Repository. Moffett Field, CA: NASA Ames Research Center, 2007. https://www.nasa.gov/intelligent-systems-division/discovery-and-systems-health/pcoe/pcoe-data-set-repository/

Basseville M., Nikiforov I.V. Detection of abrupt changes: theory and application. Englewood Cliffs, NJ: Prentice Hall, 1993. xxvi, 528 p.

Blázquez-García A., Conde A., Mori U., Lozano J.A. A review on outlier/anomaly detection in time series data // ACM Computing Surveys. 2021. Vol. 54. no. 3. pp. 1-33.

Chandola V., Banerjee A., Kumar V. Anomaly detection: a survey // ACM Computing Surveys. 2009. Vol. 41. no. 3. pp. 1-58.

Hundman K., Constantinou V., Laporte C., Colwell I., Soderstrom T. Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding // Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. London, 2018. pp. 387-395.

Kim S., Choi K., Choi H.-S., Lee B., Yoon S. Towards a rigorous evaluation of time-series anomaly detection // Proceedings of the AAAI Conference on Artificial Intelligence. 2022. Vol. 36. no. 7. pp. 7194-7201.

Lai K.-H., Zha D., Xu J., Zhao Y., Wang G., Hu X. Revisiting time series outlier detection: definitions and benchmarks // Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks. 2021. Vol. 1.

Lavin A., Ahmad S. Evaluating real-time anomaly detection algorithms – the Numenta Anomaly Benchmark // 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA). Miami, 2015. pp. 38-44.

Liu F.T., Ting K.M., Zhou Z.-H. Isolation forest // 2008 Eighth IEEE International Conference on Data Mining. Pisa, 2008. pp. 413-422.

Lowry C.A., Woodall W.H., Champ C.W., Rigdon S.E. A multivariate exponentially weighted moving average control chart // Technometrics. 1992. Vol. 34. no. 1. pp. 46-53.

Nelson L.S. The Shewhart control chart – tests for special causes // Journal of Quality Technology. 1984. Vol. 16. no. 4. pp. 237-239.

Page E.S. Continuous inspection schemes // Biometrika. 1954. Vol. 41. no. 1-2. pp. 100-115.

Roberts S.W. Control chart tests based on geometric moving averages // Technometrics. 1959. Vol. 1. no. 3. pp. 239-250.

Schmidl S., Wenig P., Papenbrock T. Anomaly detection in time series: a comprehensive evaluation // Proceedings of the VLDB Endowment. 2022. Vol. 15. no. 9. pp. 1779-1797.

Ströbel R., Kuck M., Oexle F., Kader H., Puchta A., Noack B., Fleischer J. A multimodal dataset for process monitoring and anomaly detection in industrial CNC milling // Data in Brief. 2025. Vol. 63. Art. 112207.

Tatbul N., Lee T.J., Zdonik S., Alam M., Gottschlich J. Precision and recall for time series // Advances in Neural Information Processing Systems 31 (NeurIPS 2018). Montréal, 2018.

Teti R., Jemielniak K., O’Donnell G., Dornfeld D. Advanced monitoring of machining operations // CIRP Annals. 2010. Vol. 59. no. 2. pp. 717-739.

Wu R., Keogh E. J. Current time series anomaly detection benchmarks are flawed and are creating the illusion of progress // IEEE Transactions on Knowledge and Data Engineering. 2023. Vol. 35. no. 3. pp. 2421–2429.

Metrics

12 views
0 downloads
Want to publish with us?
Submit an article

Similar Articles

1 2 3 4 > >> 

You may also start an advanced similarity search for this article.