Federated Learning for Secure AI-Driven Predictive Maintenance in Smart Manufacturing

  • Authors

    • Kishore Kunal Professor of Business Analytics, Loyola Institute of Business Administration, Chennai, TamilNadu, India https://orcid.org/0000-0003-4154-690X
    • Vairavel Madeshwaren Department of Agriculture engineering, Dhanalakshmi Srinivasan College of Engineering, Coimbatore, TamilNadu, India
    • S. Leena Nesaman Department of Computer Applications, Faculty of Science and Humanities, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India. https://orcid.org/0009-0008-3299-6961
    • Banushri. A Associate Professor, Department of Computer Science and Engineering,Vistas (Vels Institute of Science, Technology and Advanced Studies) Pallavaram, Chennai, India https://orcid.org/0000-0003-4555-5387
    • Veeramani Ganesan Professor, Department of Management and Business Administration, Jeppiaar institute of technology, Sunguvarchatram, Sriperumbudur, TamilNadu, India https://orcid.org/0009-0003-2242-2167
    • Sheifali Gupta Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India https://orcid.org/0000-0001-5692-418X
    https://doi.org/10.14419/snsw1b47

    Received date: May 15, 2025

    Accepted date: June 19, 2025

    Published date: June 25, 2025

  • Deep Learning, Edge Computing, Federated Learning, Fault Detection, Smart Manufacturing, Signal Processing

  • Abstract

    Background: In the Industry 4.0 landscape, integrating artificial intelligence (AI) with smart manufacturing is essential for enhancing automated monitoring, predictive maintenance, and system optimization. However, traditional centralized AI model training poses critical risks to data privacy, security, and scalability, especially when sensitive operational data from factory machines is shared across platforms.

    Methods: This study proposes a decentralized, intelligent framework designed for real-time machine monitoring that enhances fault detection accuracy while safeguarding data privacy. The approach begins with real-time sensor data acquisition—capturing vibration, temperature, and acoustic signals from distributed factory units via edge devices. These signals undergo preprocessing and advanced feature extraction using Wavelet Transform and Empirical Mode Decomposition (EMD) to reveal critical fault characteristics.

    Results: A hybrid deep learning model that combines Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks is used for classification. CNNs are responsible for extracting spatial features, whereas LSTMs identify temporal dependencies in time-series. With the federated learning (FL) framework, model training can be done collaboratively across edge devices without the need to transfer sensitive raw data.

    Conclusion: This ensures security and enhances model generalization. Results from experiments indicate that the suggested FL-based hybrid model exceeds centralized architectures regarding detection accuracy, computational efficiency, and adaptability. This research provides a scalable and secure solution that enhances intelligent monitoring for Industry 4.0 systems.

  • References

    1. da Silveira Dib, M. A., Ribeiro, B., & Prates, P. (2021). Federated learning as a privacy-providing machine learning for defect predictions in smart manufacturing. Smart and Sustainable Manufacturing Systems, 5(1), 1–17.
    2. Verma, P., Breslin, J. G., & O’Shea, D. (2022). FLDID: Federated learning enabled deep intrusion detection in smart manufacturing industries. Sensors, 22(22), 8974. https://doi.org/10.3390/s22228974
    3. Nasri, S. A. E. M., Ullah, I., & Madden, M. G. (2023). Compression scenarios for federated learning in smart manufacturing. Procedia Computer Science, 217, 436–445. https://doi.org/10.1016/j.procs.2022.12.239
    4. Liu, H., Li, S., Li, W., & Sun, W. (2024). Efficient decentralized optimization for edge-enabled smart manufacturing: A federated learning-based framework. Future Generation Computer Systems, 157, 422–435. https://doi.org/10.1016/j.future.2024.03.043
    5. Kevin, I., Wang, K., Zhou, X., Liang, W., Yan, Z., & She, J. (2021). Federated transfer learning based cross-domain prediction for smart manufac-turing. IEEE Transactions on Industrial Informatics, 18(6), 4088–4096. https://doi.org/10.1109/TII.2021.3088057
    6. Yang, C., & Zhao, X. (2023). Study on the selection method of federated learning clients for smart manufacturing. Electronics, 12(11), 2532. https://doi.org/10.3390/electronics12112532
    7. Ullah, I., Hassan, U. U., & Ali, M. I. (2023). Multi-level federated learning for Industry 4.0—A crowdsourcing approach. Procedia Computer Sci-ence, 217, 423–435. https://doi.org/10.1016/j.procs.2022.12.238
    8. Savazzi, S., Nicoli, M., Bennis, M., Kianoush, S., & Barbieri, L. (2021). Opportunities of federated learning in connected, cooperative, and auto-mated industrial systems. IEEE Communications Magazine, 59(2), 16–21. https://doi.org/10.1109/MCOM.001.2000200
    9. Zhang, J., Cooper, C., & Gao, R. X. (2022). Federated learning for privacy-preserving collaboration in smart manufacturing. In Global Conference on Sustainable Manufacturing (pp. 845–853). Springer. https://doi.org/10.1007/978-3-031-28839-5_94
    10. Leng, J., Li, R., Xie, J., Zhou, X., Li, X., Liu, Q., ... & Wang, L. (2025). Federated learning-empowered smart manufacturing and product lifecycle management: A review. Advanced Engineering Informatics, 65, 103179.
    11. Shubyn, B., Maksymyuk, T., Gazda, J., Rusyn, B., & Mrozek, D. (2024). Federated learning: A solution for improving anomaly detection accuracy of autonomous guided vehicles in smart manufacturing. In IEEE International Conference on Advanced Trends in Radioelectronics, Telecommuni-cations and Computer Engineering (pp. 746–761). Springer.
    12. Zhuang, C., Zhang, L., Liu, S., Leng, J., Liu, J., & Pei, F. (2025). Digital twin-based smart shop-floor management and control: A review. Ad-vanced Engineering Informatics, 65, 103102. CoLab+1Peeref+1
    13. Leng, J., Zhou, M., Zhao, J. L., Huang, Y., & Bian, Y. (2022). Blockchain Security: A Survey of Techniques and Research Directions. IEEE Trans-actions on Services Computing, 15(4), 2490–2510
    14. Bemani, A. (2024). Collaborative predictive maintenance for smart manufacturing: From wireless control to federated learning (Doctoral disserta-tion, Gävle University Press).
    15. Khan, L. U., Alsenwi, M., Yaqoob, I., Imran, M., Han, Z., & Hong, C. S. (2020). Resource optimized federated learning-enabled cognitive internet of things for smart industries. IEEE Access, 8, 168854–168864. https://doi.org/10.1109/ACCESS.2020.3023940
    16. So, J., Lee, I. B., & Kim, S. (2025). Federated learning-based framework to improve the operational efficiency of an articulated robot manufactur-ing environment. Applied Sciences, 15(8), 4108.
    17. Li, S., Cui, Q., Li, X., Liao, Y., Zhao, X., & Tao, X. (2024). A novel federated transfer learning framework based on collaborative GAN for smart manufacturing. In 2024 IEEE Wireless Communications and Networking Conference (WCNC) (pp. 1–6). IEEE.
    18. Llasag Rosero, R., Silva, C., Ribeiro, B., & Santos, B. F. (2024). Label synchronization for hybrid federated learning in manufacturing and predic-tive maintenance. Journal of Intelligent Manufacturing, 35(8), 4015–4034.
    19. Mehta, M., & Shao, C. (2022). Federated learning-based semantic segmentation for pixel-wise defect detection in additive manufacturing. Journal of Manufacturing Systems, 64, 197–210.
    20. Thakur, A., & Sindhwani, N. (2025). Intelligent load migration using federated learning in intelligent manufacturing. In Intelligent Manufacturing and Industry 4.0 (pp. 81–124). CRC Press.
    21. Yang, W., Xiang, W., Yang, Y., & Cheng, P. (2022). Optimizing federated learning with deep reinforcement learning for digital twin empowered industrial IoT. IEEE Transactions on Industrial Informatics, 19(2), 1884–1893. https://doi.org/10.1109/TII.2022.3152412
    22. Dib, M. A. D. S. (2024). SecFL: Secure federated learning framework for collaborative defect prediction in manufacturing (Doctoral dissertation, Universidade de Coimbra).
    23. Islam, F., Raihan, A. S., & Ahmed, I. (2023). Applications of federated learning in manufacturing: Identifying the challenges and exploring the fu-ture directions with Industry 4.0 and 5.0 visions. arXiv preprint, arXiv:2302.13514. https://doi.org/10.48550/arXiv.2302.13514
    24. Zhang, Y., Li, X., & Zhang, P. (2020). Real-time automatic configuration tuning for smart manufacturing with federated deep learning. In Interna-tional Conference on Service-Oriented Computing (pp. 304–318). Springer. https://doi.org/10.1007/978-3-030-62067-1_23
    25. Bharathi, M., Srinivas, T. A. S., & Bhuvaneswari, M. (n.d.). Decentralized intelligence in smart industry: Federated learning for enhanced manufac-turing.
    26. Murugadoss, R., Nesamani, S. L., Banushri, A., Rajini, S. N. S., & Gopi, P. (2024). A review of using deep learning from an ecology perspective to address climate change and air pollution. Global Nest Journal, 26(2).
    27. Vairavel, M., Rajpradeesh, T., Bathrinath, S., Kanagasabai, T., & Jaichandru, K. (2024). Analysing safety measures and environmental impact in the fireworks industry using machine learning. Journal of Environmental Protection and Ecology, 25(5), 1424–1432.
    28. Madeshwaren, V., Veerabathran, S., & Kunal, K. (2025). Ecowaste framework leveraging PSO-CNN for precise and sustainable biomedical waste management in cities. Global Nest Journal, 27(1).

  • Downloads

  • How to Cite

    Kunal, K. ., Madeshwaren, V., Nesaman, S. L. ., A, B., Ganesan, . V. ., & Gupta, S. . (2025). Federated Learning for Secure AI-Driven Predictive Maintenance in Smart Manufacturing. International Journal of Basic and Applied Sciences, 14(2), 361-370. https://doi.org/10.14419/snsw1b47