PREDICTIVE MAINTENANCE OF PRODUCTION EQUIPMENT USING ARTIFICIAL INTELLIGENCE METHODS
DOI:
https://doi.org/10.5281/zenodo.21736013Keywords:
predictive, Artificial Intelligence, Machine learning, vtnjl, methods, equipment remaining useful life predictionAbstract
The work provides a comprehensive analysis of modern approaches to predictive maintenance of production equipment using artificial intelligence methods. It examines the features of reactive, preventive, and predictive maintenance strategies, as well as the principles for building predictive maintenance systems. Modern machine learning methods are analyzed, including Random Forest, LSTM, GRU, Isolation Forest, One-Class SVM, and autoencoders, highlighting their advantages, limitations, and suitability for tasks such as classifying equipment condition, predicting remaining equipment life, and detecting anomalies. The typical architecture of predictive maintenance systems has been summarized, and a comparative analysis of modern industrial predictive maintenance platforms has been carried out. Based on a review of the literature, an original qualitative comparison of machine learning methods and a generalized scheme of how predictive maintenance systems function have been developed. It was found that the effectiveness of such systems depends on a combination of quality data preparation, the choice of machine learning algorithms, and architectural decisions. The results obtained can be used as a methodological basis for designing intelligent predictive maintenance systems for production equipment in various industrial sectors.
References
[1] Chataut R. Unleashing the power of IoT: A comprehensive review of IoT applications and future prospects in healthcare, agriculture, smart homes, smart cities, and industry 4.0. R. Chataut, A. Phoummalayvane, R. Akl. Sensors. 2023. 23.16. 7194.
[2] Sotnik S. Performance and Simulation-Based Comparison of IoT Access Control Systems Using ESP32, Arduino Uno, and Raspberry Pi Pico W. S. Sotnik. Applied Cybersecurity & Internet Governance. 2026. vol. 5. №1. рр. 1-32.
[3] Rathi B. Realizing the potential of Internet of Things (IoT) in Industrial applications. B. Rathi, S. Thapaswi, et al. Discover Internet of Things. 2025. 5(1). 45.
[4] Marunich R. Approaches to ensuring the effective implementation of IoT technologies in various industries. R. Marunich, et al. International Conference «DIGITAL INNOVATION & SUSTAINABLE DEVELOPMENT 2024». 2024. рр. 22-23.
[5] Sotnik S. Integration of IoT into security systems: opportunities and risks. S. Sotnik. International Journal of Academic Engineering Research (IJAER). 2024. Vol. 8. Issue 11. рр. 56-61.
[6] Khalimonov Y. Approaches to ensuring proper working conditions using sensor technologies IoT. Y. Khalimonov, et al. International Conference «DIGITAL INNOVATION & SUSTAINABLE DEVELOPMENT 2024». 2024. рр. 24-25.
[7] Marunich R. V. Features of IoT application in the security sector. R.V. Marunich, et al. «Computer-integrated technologies, automation and robotics» CITAR-2025. 2025. pp. 80-84.
[8] Orumwense E. F. Internet of Things for smart energy systems: A review on its applications, challenges and future trends. E. F. Orumwense, K. M. Abo-Al-Ez. AIMS Electronics and Electrical Engineering. 2023. рр. 50-74.
[9] Jagatheesaperumal S. K. The Duo of Artificial Intelligence and Big Data for Industry 4.0: Applications, Techniques, Challenges, and Future Research Directions. S. K. Jagatheesaperumal, M. Rahouti, et al. IEEE Internet of Things Journal. 2022. 9(15). рр. 12861-12885.
[10] Ucar A. Artificial intelligence for predictive maintenance applications: key components, trustworthiness, and future trends. A. Ucar, M. Karakose, N. Kırımça. Applied Sciences. 2024. 14.2. 898.
[11] Cardoso D. Application of predictive maintenance concepts using artificial intelligence tools. D. Cardoso, L. Ferreira. Applied Sciences. 2020. 11(1). 18.
[12] Fordal J. M. Application of sensor data based predictive maintenance and artificial neural networks to enable Industry 4.0. J. M. Fordal, P. Schjølberg, et al. Advances in Manufacturing. 2023. 11(2). рр. 248-263.
[13] Narayanan L. K. Machine learning-based predictive maintenance for industrial equipment optimization. L. K. Narayanan, S. Loganayagi. In: 2024 International Conference on Trends in Quantum Computing and Emerging Business Technologies. IEEE. 2024. p. 1-5.
[14] Nayak S. Leveraging predictive maintenance with machine learning and IoT for operational efficiency across industries. S. Nayak. International Journal of Science and Research Archive. 2025. 15(1). рр. 1892-1910.
[15] Do K. Data processing and analysis methods in IOT using machine learning. K. Do, I. Klymova, E. Naumova, et al. Systemy upravlinnia, navihatsii ta zviazku. Zbirnyk naukovykh prats. 2025. 2(80). рр. 119-124.
[16] Gurrapu O. A machine learning framework for fault detection in IoT enabled smart sensor networks. O. Gurrapu, J. V. Suman. In 2025 Global Conference on Information Technology and Communication Networks (GITCON). 2025. pp. 1-6.
[17] Noor-A-Rahim M. Wireless communications for smart manufacturing and industrial IoT: Existing technologies, 5G and beyond. M. Noor-A-Rahim, J. John, F. Firyaguna, H. H. R. Sherazi. Sensors. 2022. 23(1), 73.
[18] Nestorenko D. O. Analysis of modern IoT solutions for automation of urban parking spaces. D. O. Nestorenko, et al. Modern science: trends, challenges, solutions. Proceedings of the 8th International scientific and practical conference. Cognum Publishing House. Liverpool, United Kingdom. 2026. pp. 94-103.
[19] Alfarizi M. G. Optimized random forest model for remaining useful life prediction of experimental bearings. M. G., et al. Alfarizi IEEE Transactions on Industrial Informatics. 2022. 19.6. рр. 7771-7779.
[20] Yang N. Remaining useful life prediction of lithium-ion batteries with limited degradation history using random forest. N. Yang, H. Hofmann, J. Sun. IEEE Transactions on Transportation Electrification. 2023. 10(3). рр. 5049-5060.
[21] Yunita A. Performance analysis of neural network architectures for time series forecasting: A comparative study of RNN, LSTM, GRU, and hybrid models. A. Yunita, M. H. D. I. Pratama, et al. MethodsX. 2025. 15. 103462.
[22] Mateus B. C. Hybrid Deep Learning for Predictive Maintenance: LSTM, GRU, CNN, and Dense Models Applied to Transformer Failure Forecasting. B. C. Mateus, M. Mendes. Energies. 2025. 18(21). 5634.
[23] Ali W. Spectrogram-driven unsupervised autoencoder with isolation forest and one-class SVM for lab-scale wind turbine blade fault detection. W. Ali, I. El-Thalji, et al. Energy and AI. 2026. 100681.
[24] Zahoor A. Robust iot security using isolation forest and one class svm algorithms. A. Zahoor, W. Abbasi, M. Z. Babar, A. Aljohani. Scientific Reports. 2025. 15(1). 36586.
[25] Yu W. Edge computing-assisted IoT framework with an autoencoder for fault detection in manufacturing predictive maintenance. W. Yu, et al. IEEE Transactions on Industrial Informatics. 2022. 19.4. рр. 5701-5710.
[26] Kapoor D. Analyzing the impact of edge, fog and cloud computing on predictive maintenance in the Industrial Internet of Things. D. Kapoor, D. Gupta, M. Uppal. Discover Computing. 2025. 28(1). 207.
[27] Wolniak R. Predictive maintenance-the business analytics usage in Industry 4.0 conditions. R. Wolniak, W. Grebski. Zeszyty Naukowe Politechniki Śląskiej. Organizacja i Zarządzanie. 2023. 187. рр. 709-726.
[28] Li X. S. Harnessing Digital Twin Development Tools to Build Digital Twin Cities. Building Digital Twin Metaverse Cities: Revolutionizing Cities with Emerging Technologies. X. S. Li. Berkeley, CA: Apress. 2024. рр. 173-209.
[29] Fortino G. A review of internet of things platforms through the iot-a reference architecture. G. Fortino, et al. In: International Symposium on Intelligent and Distributed Computing. Cham: Springer International Publishing. 2021. p. 25-34.
[30] Yang Y. Random forest-based machine failure prediction: A performance comparison. Y. Yang, H. Wang. Applied Sciences. 2025. 15(16). 8841.
[31] Miah M. R. Data Preprocessing and Feature Engineering Strategies for Large-Scale Predictive Modeling Applications. M. R. Miah, M. M. Islam. Review of Applied Science and Technology. 2024. 3(01). рр. 263-302.
[32] Hao Y. LSTM and GRU Based Lightweight Temporal Models for Edge Computing on Real-Time Individual Abnormal Behavior Recognition. Y. Hao, A. Ojha, Y. Liu. IEEE Transactions on Consumer Electronics. 2025. Vol. 71. № 3. рр. 8298-8311
[33] Mikayilov K. Modern anomaly detection methods in industry: A comparative analysis of machine learning algorithms and their application to improve the efficiency of manufacturing processes. K. Mikayilov, L. Gardashova. Science. 2025. 14. 100154.
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Journal of Natural Sciences and Technologies

This work is licensed under a Creative Commons Attribution 4.0 International License.

