HYBRID FRAMEWORK FOR PREDICTIVE MAINTENANCE IN SMART MANUFACTURING SYSTEMS
Article Sidebar
Main Article Content
Abstract
Predictive maintenance (PdM) is one of the key components of smart manufacturing systems. It employs data-driven
solutions to reduce maintenance expenses, minimize downtime, and optimize system efficiency. The most widely used machine
learning techniques for PdM come with many challenges, especially on the transparency and explainability front. In this research, a new smart predictive maintenance system using deep learning (DL) and the CWRU bearing data set is presented for defect
classification of industrial equipment. The cleaned, normalized, labeled, and standardized data are then split into a training set and a test set to assess the model. Various models have been developed and tested, including RF, MLP, KNN and the proposed
GRU+BiLSTM model. Among the models tested, the proposed hybrid model achieved the best results with a 99.8% F1 score (F1),
99.1% recall (REC), 99.5% precision (PRE) and 99.8% accuracy (ACC). The results indicate that the temporal relationships of
vibration signals can be effectively captured by using the combination of GRU and BiLSTM, which can achieve more accurate and
reliable defect identification. This proposed approach can be used to provide smart maintenance capabilities with a predictive
approach in the context of Smart Manufacturing Systems.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Download CopyrightReferences
[1] A. Chakroun, Y. Hani, A. Elmhamedi, and F. Masmoudi, “A predictive maintenance model for health assessment of an assembly robot based on machine learning in the context of smart plant,” J. Intell. Manuf., vol. 35, no. 8, pp. 3995–4013, Dec. 2024, doi: 10.1007/s10845-023-02281-3.
[2] L. P. Maguluri, D. Suganthi, G. M. Dhote, D. Kapila, M. M. Jadhav, and S. Neelima, “AI-enhanced predictive maintenance in hybrid roll-to-roll manufacturing integrating multi-sensor data and self-supervised learning,” Int. J. Adv. Manuf. Technol., Aug. 2024, doi: 10.1007/s00170-024-14263-7.
[3] S. T. S. Tarakampet, “Transforming Asset Management with Predictive Enterprise Applications: A Case Study Approach,” Int. J. Comput. Trends Technol., vol. 74, no. 2, pp. 30–37, 2026, doi: 10.14445/22312803/IJCTT-V74I2P105.
[4] I. T. Christou, N. Kefalakis, A. Zalonis, J. Soldatos, and R. Bröchler, “End-to-End Industrial IoT Platform for Actionable Predictive Maintenance,” IFAC-PapersOnLine, vol. 53, no. 3, pp. 173–178, 2020, doi: 10.1016/j.ifacol.2020.11.028.
[5] S. Dodda, N. Kamuni, P. Nutalapati, and J. R. Vummadi, “Intelligent Data Processing for IoT Real-Time Analytics and Predictive Modeling,” in 2025 International Conference on Data Science and Its Applications (ICoDSA), IEEE, Jul. 2025, pp. 649–654. doi: 10.1109/ICoDSA67155.2025.11157424.
[6] N. R. Barot, “Transparency-Driven Operational Intelligence: A New Data Governance Model for High-Risk Industrial Automation,” J. Inf. Syst. Eng. Manag., vol. 10, no. 63s, pp. 1019–1028, Dec. 2025, doi: 10.52783/jisem.v10i63s.13975.
[7] W. Liu, W.-A. Yang, and Y. You, “Three-Stage Wiener-Process-Based Model for Remaining Useful Life Prediction of a Cutting Tool in High-Speed Milling,” Sensors, vol. 22, no. 13, p. 4763, Jun. 2022, doi: 10.3390/s22134763.
[8] S. Das, V. Challagulla, P.Balaramesh, and A. Mohan, “Deep Learning for Corrosion Monitoring Virtual Sensor and Predictive Modeling Approaches in Industrial Water Pipeline,” The Bioscan, vol. 21, no. 1, pp. 35–45, Jan. 2026, doi: 10.63001/tbs.2026.v21.i01.pp35-45.
[9] G. A. Susto, A. Schirru, S. Pampuri, S. McLoone, and A. Beghi, “Machine Learning for Predictive Maintenance: A Multiple Classifier Approach,” IEEE Trans. Ind. Informatics, vol. 11, no. 3, pp. 812–820, Jun. 2015, doi: 10.1109/TII.2014.2349359.
[10] M. Ibtihazzaman, Z. Al Sadat, S. Sakib, S. I. Oni, and M. Khatun, “Enhancing Predictive Maintenance in Smart Textile Manufacturing Using Machine Learning Models,” in 2025 IEEE 2nd International Conference on Computing, Applications and Systems (COMPAS), IEEE, Oct. 2025, pp. 1–5. doi: 10.1109/COMPAS67506.2025.11381799.
[11] L. N, R. Jayashri, and R. M, “Intelligent Maintenance Scheduling by ANFIS-Based Soft Actor-Critic RL Model in Smart Production Lines,” in 2025 2nd International Conference on Electronic Circuits and Signaling Technologies (ICECST), IEEE, Oct. 2025, pp. 63–68. doi: 10.1109/ICECST66106.2025.11307611.
[12] J. Y. Jo, T. Heo, and S. H. Kim, “Explainable AI for Predictive Maintenance in Manufacturing Process Using RTDB Sensor Data,” in 2025 5th International Conference on Robotics, Automation, and Artificial Intelligence (RAAI), IEEE, Dec. 2025, pp. 589–593. doi: 10.1109/RAAI67517.2025.11423337.
[13] L. N and R. Maranan, “Decentralized Smart Manufacturing System using Cross-Modal Data Fusion Approach,” in 2025 10th International Conference on Research in Intelligent Computing in Engineering (RICE), IEEE, Dec. 2025, pp. 1–6. doi: 10.1109/RICE67503.2025.11439983.
[14] A. Lazzaro, D. M. D’Addona, and M. Merenda, “A Detailed Study on Algorithms for Predictive Maintenance in Smart Manufacturing: Chip Form Classification Using Edge Machine Learning,” IEEE Open J. Ind. Electron. Soc., vol. 5, pp. 1190–1205, 2024, doi: 10.1109/OJIES.2024.3484006.
[15] G. A. Sampedro, M. A. P. Putra, J.-M. Lee, and D.-S. Kim, “Industrial Internet of Things-Based Fault Mitigation for Smart Additive Manufacturing Using Multi-Flow BiLSTM,” IEEE Access, vol. 11, pp. 99130–99142, 2023, doi: 10.1109/ACCESS.2023.3312724.
[16] Y. K. Teoh, S. S. Gill, and A. K. Parlikad, “IoT and Fog-Computing-Based Predictive Maintenance Model for Effective Asset Management in Industry 4.0 Using Machine Learning,” IEEE Internet Things J., vol. 10, no. 3, pp. 2087–2094, Feb. 2023, doi: 10.1109/JIOT.2021.3050441.