Centrifugal pump and electrical motor fault detection with motor current signature analysis  and automated machine learning

Roman R. Khalikov; Mikhail Yu. Chernetskiy; Ilia E. Revin; Vadim A. Potemkin

Vol 275

Pages:

42-55

Download volume:

RUS ENG

Article

Geotechnical Engineering and Engineering Geology

Centrifugal pump and electrical motor fault detection with motor current signature analysis and automated machine learning

Authors:

Roman R. Khalikov¹

Mikhail Yu. Chernetskiy²

Ilia E. Revin³

Vadim A. Potemkin⁴

About authors

1 — Specialist ROTEC Digital Solutions JSC ▪ Orcid
2 — Ph.D. Head of Department ROTEC Digital Solutions JSC ▪ Orcid
3 — Ph.D. Researcher ITMO University ▪ Orcid
4 — Ph.D. Researcher ITMO University ▪ Orcid

Date submitted:

2025-04-09

Date accepted:

2025-08-25

Online publication date:

2025-10-13

Date published:

2025-10-31

Abstract

Centrifugal pumps, as key components of hydraulic systems, play a fundamental role in ensuring the reliable operation of numerous industrial processes in sectors such as energy, chemical production, and oil refining, where uninterrupted equipment performance is of critical importance. Failures of centrifugal pumps can result in substantial financial losses due to costly repairs and unplanned production downtime. This paper presents an innovative approach to diagnosing and detecting faults in centrifugal pumps. The method is based on the application of Motor Current Signature Analysis (MCSA) in combination with automated machine learning (AutoML) technologies. Such an approach enables efficient and highly accurate identification of early signs of equipment malfunction. The experimental study was conducted using an open dataset collected under conditions close to real-world operation. The proposed method achieved a fault detection accuracy of 89 %, which significantly exceeds the performance of the traditional gradient boosting method. This confirms the advantage of a comprehensive model developed through AutoML. Further improvement in diagnostic accuracy was made possible by applying an enhanced Park’s vector transformation to the raw current and voltage data. This approach makes it possible to detect even subtle anomalies in pump operation, thereby strengthening the capability for early fault prediction. The study not only highlights the potential of MCSA as a non-invasive and scalable tool for equipment condition monitoring but also demonstrates the promise of AutoML for technical diagnostics of industrial pumps.

Область исследования:

Geotechnical Engineering and Engineering Geology

Keywords:

machine learning electric motor gradient boosting composite model AutoML fault detection time series

References

Zhukovskiy Y., Buldysko A., Revin I. Induction Motor Bearing Fault Diagnosis Based on Singular Value Decomposition of the Stator Current. Energies. 2023. Vol. 16. Iss. 8. N 3303. DOI: 10.3390/en16083303
Korolev N.A., Zhukovskiy Y.L., Buldysko A.D. et al. Energy resource evaluation from technical diagnostics of electromechanical devices in minerals sector. Mining Informational and Analytical Bulletin. 2024. N 5, p. 158-181 (in Russian). DOI: 10.25018/0236_1493_2024_5_0_158
Bolón-Canedo V., Morán-Fernández L., Cancela B., Alonso-Betanzos A. A review of green artificial intelligence: Towards a more sustainable future. Neurocomputing. 2024. Vol. 599. N 128096. DOI: 10.1016/j.neucom.2024.128096
Garcia-Calva T., Morinigo-Sotelo D., Fernandez-Cavero V., Romero-Troncoso R. Early Detection of Faults in Induction Motors – A Review. Energies. 2022. Vol. 15. Iss. 21. N 7855. DOI: 10.3390/en15217855
Atta M.E.E.-D., Ibrahim D.K., Gilany M.I. Broken Bar Fault Detection and Diagnosis Techniques for Induction Motors and Drives: State of the Art. IEEE Access. 2022. Vol. 10, p. 88504-88526. DOI: 10.1109/ACCESS.2022.3200058
Ghanbari T., Mehraban A., Farjah E. Inter-turn fault detection of induction motors using a method based on spectrogram of motor currents. Measurement. 2022. Vol. 205. N 112180. DOI: 10.1016/j.measurement.2022.112180
Bruinsma S., Geertsma R.D., Loendersloot R., Tinga T. Motor current and vibration monitoring dataset for various faults in an E-motor-driven centrifugal pump. Data in Brief. 2024. Vol. 52. N 109987. DOI: 10.1016/j.dib.2023.109987
Sunal C.E., Dyo V., Velisavljevic V. Review of Machine Learning Based Fault Detection for Centrifugal Pump Induction Motors. IEEE Access. 2022. Vol. 10, p. 71344-71355. DOI: 10.1109/ACCESS.2022.3187718
Sunal C.E., Velisavljevic V., Dyo V. et al. Centrifugal Pump Fault Detection with Convolutional Neural Network Transfer Learning. Sensors. 2024. Vol. 24. Iss. 8. N 2442. DOI: 10.3390/s24082442
Chao Zhao, Zio E., Weiming Shen. Domain generalization for cross-domain fault diagnosis: An application-oriented perspective and a benchmark study. Reliability Engineering & System Safety. 2024. Vol. 245. N 109964. DOI: 10.1016/j.ress.2024.109964
Kim M.-C., Lee J.-H., Wang D.-H., Lee I.-S. Induction Motor Fault Diagnosis Using Support Vector Machine, Neural Networks, and Boosting Methods. Sensors. 2023. Vol. 23. Iss. 5. N 2585. DOI: 10.3390/s23052585
Jiusi Zhang, Ke Zhang, Yiyao An et al. An Integrated Multitasking Intelligent Bearing Fault Diagnosis Scheme Based on Representation Learning Under Imbalanced Sample Condition. IEEE Transactions on Neural Networks and Learning Systems. 2024. Vol. 35. Iss. 5, p. 6231-6242. DOI: 10.1109/TNNLS.2022.3232147
Kumar P., Hati A.S. Review on Machine Learning Algorithm Based Fault Detection in Induction Motors. Archives of Computational Methods in Engineering. 2021. Vol. 28. Iss. 3, p. 1929-1940. DOI: 10.1007/s11831-020-09446-w
Yakhni M.F., Cauet S., Sakout A. et al. Variable speed induction motors’ fault detection based on transient motor current signatures analysis: A review. Mechanical Systems and Signal Processing. 2023. Vol. 184. N 109737. DOI: 10.1016/j.ymssp.2022.109737
Yuejiang Han, Jiamin Zou, Bo Gong et al. The use of model-based voltage and current analysis for torque oscillation detection and improved condition monitoring of centrifugal pumps. Mechanical Systems and Signal Processing. 2025. Vol. 222. N 111781. DOI: 10.1016/j.ymssp.2024.111781
Chen Liang, Yan Hao, Xie Tengzhou, Li Zhiguo. Identification of cavitation state of centrifugal pump based on current signal. Frontiers in Energy Research. 2023. Vol. 11. N 1204300. DOI: 10.3389/fenrg.2023.1204300
Gospodarikov A.P., Revin I.E., Morozov K.V. Composite model of seismic monitoring data analysis during mining operations on the example of the Kukisvumchorrskoye deposit of AO Apatit. Journal of Mining Institute. 2023. Vol. 262, p. 571-580. DOI: 10.31897/PMI.2023.9
Nath A.G., Udmale S.S., Singh S.K. Role of artificial intelligence in rotor fault diagnosis: a comprehensive review. Artificial Intelligence Review. 2021. Vol. 54. Iss. 4, p. 2609-2668. DOI: 10.1007/s10462-020-09910-w
Salehin I., Islam S., Saha P. et al. AutoML: A systematic review on automated machine learning with neural architecture search. Journal of Information and Intelligence. 2024. Vol. 2. Iss. 1, p. 52-81. DOI: 10.1016/j.jiixd.2023.10.002
Baratchi M., Can Wang, Limmer S. et al. Automated machine learning: past, present and future. Artificial Intelligence Review. 2024. Vol. 57. Iss. 5. N 122. DOI: 10.1007/s10462-024-10726-1
Alsharef A., Aggarwal K., Sonia et al. Review of ML and AutoML Solutions to Forecast Time-Series Data. Archives of Computational Methods in Engineering. 2022. Vol. 29. Iss. 7, p. 5297-5311. DOI: 10.1007/s11831-022-09765-0
Barandier P., Mendes M., Cardoso A.J.M. Comparative analysis of four classification algorithms for fault detection of heat pumps. Energy and Buildings. 2024. Vol. 316. N 114342. DOI: 10.1016/j.enbuild.2024.114342
Barbudo R., Ventura S., Romero J.R. Eight years of AutoML: categorisation, review and trends. Knowledge and Information Systems. 2023. Vol. 65. Iss. 12, p. 5097-5149. DOI: 10.1007/s10115-023-01935-1
Bischl B., Binder M., Lang M. et al. Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges. WIREs Data Mining and Knowledge Discovery. 2023. Vol. 13. Iss. 2. N e1484. DOI: 10.1002/widm.1484
Morales-Hernández A., Van Nieuwenhuyse I., Rojas Gonzalez S. A survey on multi-objective hyperparameter optimization algorithms for machine learning. Artificial Intelligence Review. 2023. Vol. 56. Iss. 8, p. 8043-8093. DOI: 10.1007/s10462-022-10359-2
Dahiya S., Nanda H., Artwani J., Varshney J. Using Clustering techniques and Classification Mechanisms for Fault Diagnosis. International Journal of Advanced Trends in Computer Science and Engineering. 2020. Vol. 9. N 2, p. 2138-2146. DOI: 10.30534/ijatcse/2020/188922020
Maliuk A.S., Ahmad Z., Kim J.-M. A Technique for Bearing Fault Diagnosis Using Novel Wavelet Packet Transform-Based Signal Representation and Informative Factor LDA. Machines. 2023. Vol. 11. Iss. 12. N 1080. DOI: 10.3390/machines11121080
Hadi R.H., Hady H.N., Hasan A.M. et al. Improved Fault Classification for Predictive Maintenance in Industrial IoT Based on AutoML: A Case Study of Ball-Bearing Faults. Processes. 2023. Vol. 11. Iss. 5. N 1507. DOI: 10.3390/pr11051507
Cerrada M., Trujillo L., Hernández D.E. et al. AutoML for Feature Selection and Model Tuning Applied to Fault Severity Diagnosis in Spur Gearboxes. Mathematical and Computational Applications. 2022. Vol. 27. Iss. 1. N 6. DOI: 10.3390/mca27010006
Hutter F., Kotthoff L., Vanschoren J. Automated Machine Learning. Methods, Systems, Challenges. Springer, 2019, p. 219. DOI: 10.1007/978-3-030-05318-5
Revin I., Potemkin V.A., Balabanov N.R., Nikitin N.O. Automated machine learning approach for time series classification pipelines using evolutionary optimization. Knowledge-Based Systems. 2023. Vol. 268. N 110483. DOI: 10.1016/j.knosys.2023.110483
Javed K., Gouriveau R., Zerhouni N. State of the art and taxonomy of prognostics approaches, trends of prognostics applications and open issues towards maturity at different technology readiness levels. Mechanical Systems and Signal Processing. 2017. Vol. 94, p. 214-236. DOI: 10.1016/j.ymssp.2017.01.050
Khan A.A., Chaudhari O., Chandra R. A review of ensemble learning and data augmentation models for class imbalanced problems: Combination, implementation and evaluation. Expert Systems with Applications. 2024. Vol. 244. N 122778. DOI: 10.1016/j.eswa.2023.122778
Ozaki Y., Tanigaki Y., Watanabe S. et al. Multiobjective Tree-Structured Parzen Estimator. Journal of Artificial Intelligence Research. 2022. Vol. 73, p. 1209-1250. DOI: 10.1613/jair.1.13188

Centrifugal pump and electrical motor fault detection with motor current signature analysis and automated machine learning

Abstract

References

Similar articles