UDC 004.8
In the context of the transition to the Industry 4.0 paradigm, traditional maintenance approaches for conveyor systems, based on reactive or time-based strategies, demonstrate low economic efficiency. The aim of this study is to develop a predictive maintenance architecture for bearing units based on telemetry data analysis and machine learning algorithms. The paper proposes a multi-level technology stack that combines edge analytics for primary signal filtering with server infrastructure for training predictive models. Vibration spectra, temperature gradients, and electrical load parameters were used as key condition indicators. Experimental validation on a representative industrial conveyor dataset showed a residual life prediction accuracy of 94.2%. Implementation of the proposed methodology reduced unplanned downtime by 31.5% and decreased operational maintenance costs by 24%. The results confirm the feasibility of integrating IIoT solutions into the continuous production control loop.
telemetry, predictive maintenance, rolling bearings, machine learning, vibration analysis, IIoT
1. Terent'ev, A. V. Prediktivnaya analitika v promyshlennosti: metody i tehnologii / A. V. Terent'ev, V. A. Smirnov. – Moskva : Tehnologii, 2023. – 248 s. – URL: https://tech-industry.ru/predictive-analytics (data obrascheniya: 15.03.2026).
2. Chen, T. XGBoost: A Scalable Tree Boosting System / T. Chen, C. Guestrin // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. – 2016. – P. 785–794. – doi:https://doi.org/10.1145/2939672.2939785. – URL: https://dl.acm.org/doi/10.1145/2939672.2939785 (data obrascheniya: 20.03.2026).
3. IoT Analytics. Industrial IoT Protocols in Manufacturing: MQTT vs OPC UA vs Modbus / IoT Analytics GmbH, 2024. – URL: https://iot-analytics.com/iiot-protocols-2024/ (data obrascheniya: 18.03.2026).
4. Deep Learning and Its Applications to Machine Health Monitoring: A Survey / R. Zhao, R. Yan, Z. Chen, K. Mao, P. Wang, R.X. Gao // Mechanical Systems and Signal Processing. – 2019. – Vol. 115. – P. 213–237. – doi:https://doi.org/10.1016/j.ymssp.2018.05.050. – URL: https://www.sciencedirect.com/science/article/pii/S0888327018302676 (data obrascheniya: 22.03.2026).
5. Jardine, A. K. S. A Review on Machinery Diagnostics and Prognostics Implementing Condition-Based Maintenance / A. K. S. Jardine, D. Lin, D. Banjevic // Mechanical Systems and Signal Processing. – 2006. – Vol. 20, No. 7. – P. 1483-1510. URL: https://www.researchgate.net/publication/222661820 (data obrascheniya: 10.03.2026).
6. IEEE Standards Association. IEEE 1451-2023: Standard for a Smart Transducer Interface for Sensors and Actuators / IEEE, 2023. – URL: https://standards.ieee.org/ieee/1451/10312/ (data obrascheniya: 12.03.2026).
