Real-Time Assessment of the Technical Condition of Traction Motors Using Machine Learning and IoT Technologies

E. K. Manafov; H. B. Guliyev; F. H. Huseynov

doi:10.15802/stp2025/331096

Authors

E. K. Manafov National Aviation Academy, Azerbaijan https://orcid.org/0000-0001-5697-577X
H. B. Guliyev Azerbaijan Technical University, Azerbaijan https://orcid.org/0009-0005-7362-0619
F. H. Huseynov Azerbaijan State Oil and Industry University, Azerbaijan https://orcid.org/0000-0002-5325-0279

DOI:

https://doi.org/10.15802/stp2025/331096

Keywords:

predictive maintenance, machine learning algorithms, intelligent diаgnоstics, fаult detection, technical cоnditiоn mоnitоring, trаctiоn mоtоr

Abstract

Purpose. The purpose of this research is to analyze machine learning algorithms, select the most accurate and efficient algorithm for diagnosing the technical condition of an induction traction motor based on operating parameters such as temperature, noise, and vibration, and study the features of using Internet of Things (IoT) technology to assess technical conditions in real time. Methodology. The machine learning algorithm suitable for diagnosing the technical condition of asynchronous traction motors was identified through analysis and comparative methods. Findings. Machine learning algorithms were analyzed, and two distinct algorithms, K-means and Extreme Machine Learning (EML), were selected for diagnosing the technical condition of asynchronous motors. The algorithms were compared based on performance metrics such as accuracy, specificity, sensitivity, positive predictive value, and negative predictive value. The results revealed that the EML algorithm outperformed K-means in these metrics, achieving an overall performance score of 93%. Originality. A novel system was proposed that integrates a machine learning model with IoT technology for real-time diagnostics of the technical condition of traction electric motors. This innovative approach enables dynamic monitoring of the motor's technical state. Compared to traditional temperature diagnostic systems, such a multi-parameter system will allow you to determine a specific malfunction. Practical value. The proposed system, based on a machine learning model, evaluates the technical condition of traction motors in real-time using IoT. It provides recommendations on when maintenance should be performed, based on the actual condition of the motor. The system allows for maintenance planning based on real-time diagnostics, facilitating a shift from scheduled maintenance to predictive maintenance strategies. This, in turn, increases operational lifespan and minimizes unplanned downtime. By leveraging IoT, the diagnostic system can integrate with motor control systems or SCADA systems, enabling remote monitoring and control of motor operations.

References

Demirci, M., Gozde, H., & Taplamacioglu, M. C. (2021). Fault diagnosis of power transformers with machine learning methods using traditional methods data. International Journal on «Technical and Physical Problems of Engineering» (IJTPE), 49(13), 225-230. (in English)

Dineva, A., Mosavi, A., Gyimesi, M., Vajda, I., Nabipour, N., & Rabczuk, T. (2019). Fault Diagnosis of Rotating Electrical Machines Using Multi-Label Classification. Applied Sciences, 9(23), 5086. DOI: https://doi.org/10.3390/app9235086 (in English)

Gangsar, P., & Tiwari, R. (2017). Comparative investigation of vibration and current monitoring for prediction of mechanical and electrical faults in induction motor based on multiclass-support vector machine algorithms. Mechanical Systems and Signal Processing, 94, 464-481. DOI: https://doi.org/10.1016/j.ymssp.2017.03.016 (in English)

Guliyev, H. B., Mаnаfоv, E. K., & Huseynov, F. H. (2024). Traction electric motor condition monitoring based on machine learning and internet of Things. The 20th International Conference on «Technical and Physical Problems of Engineering» (ICTPE-2024), 47-52. (in English)

Halder, S., Bhat, S., Zychma, D., & Sowa, P. (2022). Broken Rotor Bar Fault Diagnosis Techniques Based on Motor Current Signature Analysis for Induction Motor-A Review. Energies, 15(22), 8569. DOI: https://doi.org/10.3390/en15228569 (in English)

Jha, R. K., & Swami, P. D. (2021). Fault diagnosis and severity analysis of rolling bearings using vibration image texture enhancement and multiclass support vector machines. Applied Acoustics, 182, 108243. DOI: https://doi.org/10.1016/j.apacoust.2021.108243 (in English)

Jigyasu, R., Sharma, A., Mathew, L., & Chatterji, S. (2018). A Review of Condition Monitoring and Fault Diagnosis Methods for Induction Motor. 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS), 1713-1721. DOI: https://doi.org/10.1109/iccons.2018.8662833 (in English)

Kumar, P., & Hati, A. S. (2020). Review on Machine Learning Algorithm Based Fault Detection in Induction Motors. Archives of Computational Methods in Engineering, 28(3), 1929-1940. DOI: https://doi.org/10.1007/s11831-020-09446-w (in English)

Kumar, R. R., Andriollo, M., Cirrincione, G., Cirrincione, M., & Tortella, A. (2022). A Comprehensive Review of Conventional and Intelligence-Based Approaches for the Fault Diagnosis and Condition Monitoring of Induction Motors. Energies, 15(23), 8938. DOI: https://doi.org/10.3390/en15238938 (in English)

Kunthong, J., Sapaklom, T., Konghirun, M., Prapanavarat, C., Ayudhya, P. N. N., Mujjalinvimut, E., & Boonjeed, S. (2017, Dec.). IoT-based traction motor drive condition monitoring in electric vehicles: Part 1. In 2017 IEEE 12th International Conference on Power Electronics and Drive Systems (PEDS) (pp. 1,184-1,188). Honolulu, HI, USA. DOI: https://doi.org/10.1109/peds.2017.8289143 (in English)

Lei, Y., Yаng, B., Jiаng, X., Jiа, F., Li, N., & Nаndi, А. K. (2020). Аpplicаtiоns оf Mаchine Leаrning tо Mаchine Fаult Diаgnоsis: А Review аnd Rоаdmаp. Mechаnicаl Systems аnd Signаl Prоcessing, 138, 106587. (in English)

Manafov, E. & Huseynov, F. (2023). Applıcatıon of artıfıcıal neuron networks and fuzzy logıc ın dıagnostıc and forecastıng the technıcal condıtıon of tractıon motors. PIRETC-Proceeding of The International Research Education & Training Centre, 27(06), 233-239. DOI: https://doi.org/10.36962/piretc27062023-233 (in English)

Manafov, E., Isgandarov, I., & Huseynov, F. (2022). Investıgatıng the protectıon system of electrıc motors based on ıts maın workıng parameters. Scientific Journal of Silesian University of Technology. Series Transport, 115, 63-74. DOI: https://doi.org/10.20858/sjsutst.2022.115.5 (in English)

Misra, S., Kumar, S., Sayyad, S., Bongale, A., Jadhav, P., Kotecha, K., Abraham, A., & Gabralla, L. A. (2022). Fault Detection in Induction Motor Using Time Domain and Spectral Imaging-Based Transfer Learning Approach on Vibration Data. Sensors, 22(21), 8210. DOI: https://doi.org/10.3390/s22218210 (in English)

Moosavian, A., Ahmadi, H., Tabatabaeefar, A., & Khazaee, M. (2013). Comparison of Two Classifiers;

K-Nearest Neighbor and Artificial Neural Network, for Fault Diagnosis on a Main Engine Journal-Bearing. Shock and Vibration, 20(2), 263-272. DOI: https://doi.org/10.1155/2013/360236 (in English)

Nekrouf, D., & Boughanmi N. (2023). Application of root-music and SVM to induction motor faults diagnosis. International Journal on «Technical and Physical Problems of Engineering» (IJTPE), 15(56), 111-119. (in English)

Singh, R., & Bhushan, B. (2021). Condition Monitoring Based Control Using Wavelets and Machine Learning for Unmanned Surface Vehicles. IEEE Transactions on Industrial Electronics, 68(8), 7464-7473. DOI: https://doi.org/10.1109/tie.2020.3001855 (in English)

Tun, W., Wong, J. K.-W., & Ling, S.-H. (2021). Hybrid Random Forest and Support Vector Machine Modeling for HVAC Fault Detection and Diagnosis. Sensors, 21(24), 8163. DOI: https://doi.org/10.3390/s21248163 (in English)

Xu, Z., Li, Q., Qian, L., & Wang, M. (2022). Multi-Sensor Fault Diagnosis Based on Time Series in an Intelligent Mechanical System. Sensors, 22(24), 9973. DOI: https://doi.org/10.3390/s22249973 (in English)

Zamudio-Ramírez, I., Osornio-Ríos, R. A., Antonino-Daviu, J. A., & Quijano-Lopez, A. (2020). Smart-Sensor for the Automatic Detection of Electromechanical Faults in Induction Motors Based on the Transient Stray Flux Analysis. Sensors, 20(5), 1477. DOI: https://doi.org/10.3390/s20051477 (in English)