IMPROVING PREDICTIVE MAINTENANCE BASED ON THE ANALYSIS OF PACKAGING EQUIPMENT CONDITION DEGRADATION PROCESS
Abstract
Predictive Maintenance (PdM) is a condition-based maintenance strategy that relies on real-time equipment monitoring to perform maintenance actions only when necessary, avoiding unnecessary preventive measures. This research aims to develop a comprehensive PdM methodology that integrates the assessment of the Remaining Useful Life (RUL) of technological equipment (TE) and its main mechanisms by analyzing their condition degradation process. To this end, it is proposed to equip the TE with a continuous monitoring system for constant automatic collection and processing of statistical data from the current operation of the TE and other diagnostic parameters accompanying the machine's operation (vibration, currents, sound, temperature, performance, recovery rate, etc.). Data collection, combined with software, enables their real-time transformation into a history of the degradation process and, as a result of the analysis, to determine whether there are significant changes indicating a defect in the production process, as well as to specify the requirements for the types and timing of maintenance. An algorithm is proposed for modeling the degradation process and optimizing the maintenance schedule of industrial equipment based on degradation models and an expert system (ES) to support decision-making based on RUL for determining the optimal time for maintenance. A feature of the TE condition research methodology is its two-stage implementation: the first stage investigates the technical condition of the TE as a whole, and the second – its mechanisms. It is in the second stage that the mechanisms requiring maintenance and the type of maintenance are determined. This methodological approach not only increases the intervals between maintenance operations but also assesses the technical condition of the main mechanisms, which increases operational efficiency and minimizes costly downtime. A key feature of this research work lies in its real applicability to TE with multiple mechanisms, as the effectiveness of the proposed framework is evaluated within a real packaging production system.
References
Bousdekis, D. Apostolou and G. Mentzas. Predictive maintenance in the 4th industrial revolution: benefits business opportunities and man-agerial implications. IEEE Engineering Management Review, vol. 48, no. 1, pp. 57-62, 2020. DOI: 10.1109/EMR.2019.2958037
D. Jung and C. Sundstrom. A combined data-driven and model-based residual selection algorithm for fault detection and isolation. IEEE Transactions on Control Systems Technology, vol. 27, no. 2, pp. 616-630, 2017. DOI: 10.1109/TCST.2017.2773514
D. B. Durocher and G. R. Feldmeier. Predictive versus preventive maintenance. IEEE Industry Applications Magazine, vol. 10, no. 5, pp. 12-21, 2004. DOI: 10.1109/MIA.2004.1330766
E. F. Swana, W. Doorsamy and P. Bokoro. Tomek link and SMOTE approaches for machine fault classification with an imbalanced dataset. Sensors, vol. 22, no. 9, pp. 3246, 2022. https://doi.org/10.3390/s22093246
S. Wickramasinghe, K. Amarasinghe, D. L. Marino, C. Rieger and M. Manic. Explainable unsupervised machine learning for cyber-physical systems. IEEE Access, vol. 9, pp. 131 824-13 143, 2021. DOI: 10.1109/ACCESS.2021.3112397
L. Yuanyuan and S. Jiang. Research on equipment predictive mainte-nance strategy based on big data technology. IEEE 2015 International Conference on Intelligent Transportation Big Data and Smart City, pp. 641-644, December 2015. DOI: 10.1109/ICITBS.2015.163
W. Yu, T. Dillon, F. Mostafa, W. Rahayu and Y. Liu. A global manufacturing big data ecosystem for fault detection in predictive maintenance. IEEE Transactions on Industrial Informatics, vol. 16, no. 1, pp. 183-192, 2021. DOI: 10.1109/TII.2019.2915846
Palchevskyi B., Krestyanpol L. Application of Predictive Maintenance in the Packaging Production. Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska – IAPGOS, № 3, 2022, рр. 27–33. DOI: 10.35784/iapgos.3051
Jardine A.K. Review of Current Approaches for Defining the Remaining Useful Life of Mechanical Equipment, Mechanical Systems and Signal Processing, 20(4), 2006, рр.719-737.
Copyright (c) 2025 Б. О. Пальчевський
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
