IoT-Driven Predictive Maintenance Model for Rotating Machinery Using Machine Learning and Deep Learning Techniques
DOI:
https://doi.org/10.64882/ijrt.v13.i3.484Keywords:
Vibration Signal Processing, Predictive Maintenance, Bearing Fault Diagnosis, Industry 4.0, Condition Monitoring, RobustAbstract
In modern factories, it is very important to make sure that equipment problems are found quickly and accurately so that operations stay efficient and costly downtime is avoided. The H-CBLSTMNet is a novel and better technique to discover problems with bearings for health monitoring. The model learns in order with Bidirectional LSTM layers and finds spatial characteristics with Convolutional Neural Networks. This helps it automatically pick up on both short-term and long-term patterns in raw sensor data. The proposed model outperformed traditional machine learning and independent deep learning models, achieving a test accuracy of 98.73%, with Precision, Recall, and F1-Score metrics of 98.74%, 98.73%, and 98.74%, respectively. These results suggest that the classification is fair, with very few false positives and negatives. A high training accuracy of 97.80% and a high validation accuracy of 96.83%, along with a low test loss of 0.0436, showed that strong generalization was possible. Using Adam optimization, early halting, and dropout regularization made this achievable. The confusion matrix showed that the faults were divided into several groups, which proved that the diagnostic performance was accurate. Models like SVM, KNN, and Random Forest, on the other hand, have a hard difficulty discovering features that are very different from each other. In general, H-CBLSTMNet is a mechanism to find bearing problems in real time that can be scaled and automated. It cuts down on manual feature engineering and promotes Industry 4.0 predictive maintenance by making machines more reliable, letting people make decisions ahead of time, and reducing down on downtime.
References
S. Kontos, A. Bousdekis, K. Lepenioti, and G. Mentzas, “Degradation Modelling and Prognostics of Rotating Equipment with Automated Machine Learning,” Procedia Comput. Sci., vol. 253, no. 2024, pp. 1640–1648, 2025, doi: 10.1016/j.procs.2025.01.226.
I. Ul Hassan, K. Panduru, and J. Walsh, “Predictive Maintenance in Industry 4.0: A Review of Data Processing Methods,” Procedia Comput. Sci., vol. 257, pp. 896–903, 2025, doi: 10.1016/j.procs.2025.03.115.
K. M. A. Alghtus, A. Gannan, K. M. Alhajri, A. L. A. Al Jubouri, and H. A. I. Al-Janahi, “Short-Horizon Predictive Maintenance of Industrial Pumps Using Time-Series Features and Machine Learning,” pp. 1–15, 2025.
A. K. Ovacıklı, M. Yagcioglu, S. Demircioglu, T. Kocatekin, and S. Birtane, “Supervised Learning-Based Fault Classification in Industrial Rotating Equipment Using Multi-Sensor Data,” Appl. Sci., vol. 15, no. 13, 2025, doi: 10.3390/app15137580.
S. D. Brito, G. J. Azinheira, J. F. Semião, N. M. Sousa, and S. P. Litrán, “Non-Intrusive Low-Cost IoT-Based Hardware System for Sustainable Predictive Maintenance of Industrial Pump Systems,” Electron., vol. 14, no. 14, pp. 1–34, 2025, doi: 10.3390/electronics14142913.
V. I. Vlachou et al., “Intelligent Fault Diagnosis of Ball Bearing Induction Motors for Predictive Maintenance Industrial Applications,” pp. 1–30, 2025.
J. Feng and J. Kan, “A Novel Multi-Objective Fuzzy Deep Learning Framework for Predictive Maintenance in Industrial Internet of Things,” IEEE Access, vol. 13, no. February, pp. 41955–41973, 2025, doi: 10.1109/ACCESS.2025.3547863.
T. M. Le, H. M. Tran, K. Wang, H. V. Pham, and S. V. T. Dao, “An Internet-of-Things-Integrated Deep Learning Model for Fault Diagnosis in Industrial Rotating Machines,” IEEE Access, vol. 13, no. April, pp. 57266–57286, 2025, doi: 10.1109/ACCESS.2025.3553155.
J. Garcia, L. Rios-Colque, A. Peña, and L. Rojas, “Condition Monitoring and Predictive Maintenance in Industrial Equipment: An NLP-Assisted Review of Signal Processing, Hybrid Models, and Implementation Challenges,” Appl. Sci., vol. 15, no. 10, pp. 1–35, 2025, doi: 10.3390/app15105465.
A. Moccardi, C. Conte, R. Chandra Ghosh, and F. Moscato, “A Robust Conformal Framework for IoT-Based Predictive Maintenance,” Futur. Internet, vol. 17, no. 6, pp. 1–27, 2025, doi: 10.3390/fi17060244.
C. Tsallis, P. Papageorgas, D. Piromalis, and R. A. Munteanu, “Application-Wise Review of Machine Learning-Based Predictive Maintenance: Trends, Challenges, and Future Directions,” Appl. Sci., vol. 15, no. 9, pp. 1–25, 2025, doi: 10.3390/app15094898.
A. Lycksam, M. O’Nils, and F. Z. Qureshi, “A prognostic framework for rotating machines considering multi-component fault scenarios,” IEEE Access, vol. 13, no. April, pp. 91682–91692, 2025, doi: 10.1109/ACCESS.2025.3572582.
A. T. Abdullah, R. S. Sabeeh, H. M. Hussein, and M. J. Hussien, “A Comprehensive Review of Machine Learning Algorithms for Fault Diagnosis and Prediction in Rotating Machinery,” vol. 3, no. 4, pp. 110–127, 2025.
M. Nsor, “Predictive Maintenance Using Machine Learning for Engineering Systems Through Real-Time Sensor Data and Anomaly Detection Models,” Int. J. Res. Publ. Rev., vol. 6, no. 7, pp. 5167–5183, 2025, doi: 10.55248/gengpi.6.0725.2541.
C. Eang and S. Lee, “Predictive Maintenance and Fault Detection for Motor Drive Control Systems in Industrial Robots Using CNN-RNN-Based Observers,” Sensors, vol. 25, no. 1, 2025, doi: 10.3390/s25010025.
R. Aragonés, J. Oliver, and C. Ferrer, “Enhanced Heat-Powered Batteryless IIoT Architecture with NB-IoT for Predictive Maintenance in the Oil and Gas Industry,” Sensors, vol. 25, no. 8, 2025, doi: 10.3390/s25082590.
S. K. Shil, “AI DRIVEN PREDICTIVE MAINTENANCE IN PETROLEUM AND POWER SYSTEMS USING RANDOM FOREST REGRESSION MODEL,” vol. 04, no. 01, pp. 363–391, 2025, doi: 10.63125/477x5t65.
M. M. R. Shamim and R. A. Ruddro, “Smart Diagnostics in Industrial Maintenance: a Systematic Review of Ai-Enabled Predictive Maintenance Tools and Condition Monitoring Techniques,” ASRC Procedia Glob. Perspect. Sci. Scholarsh., vol. 01, no. 01, pp. 63–80, 2025, doi: 10.63125/b4tn2x46.
N. Nayak et al., “Enhancing fault detection and predictive maintenance of rotating machinery with Fiber Bragg Grating sensor and machine learning techniques,” Int. J. Inf. Technol., vol. 17, no. 2, pp. 1225–1234, 2025, doi: 10.1007/s41870-024-02256-4.
S. O. Alhuqay, A. T. Alenazi, H. A. Alabduljabbar, and M. A. Haq, “Improving Predictive Maintenance in Industrial Environments via IIoT and Machine Learning,” Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 4, pp. 627–636, 2024, doi: 10.14569/IJACSA.2024.0150464.
A. Emmanuel, “Artificial Intelligence in Predictive Maintenance for Industry,” Newport Int. J. Sci. Exp. Sci., vol. 6, no. 3, pp. 7–13, 2025, doi: 10.59298/nijses/2025/63.713.
R. Ūselis, A. Serackis, and R. Pomarnacki, “Signal Processing Optimization in Resource-Limited IoT for Fault Prediction in Rotating Machinery,” Electron., vol. 14, no. 18, 2025, doi: 10.3390/electronics14183670.
R. W. Abdalah, O. F. Abdulateef, and A. H. Hamad, “A Predictive Maintenance System Based on Industrial Internet of Things for Multimachine Multiclass Using Deep Neural Network,” J. Eur. des Syst. Autom., vol. 58, no. 2, pp. 373–381, 2025, doi: 10.18280/jesa.580218.
et al., “Predictive Maintenance in Industrial Automation: a Systematic Review of Iot Sensor Technologies and Ai Algorithms,” Am. J. Interdiscip. Stud., vol. 5, no. 1, pp. 01–30, 2024, doi: 10.63125/hd2ac988.
S. Hanifi, B. Alkali, G. Lindsay, M. Waters, and D. McGlinchey, “Advancements in predictive maintenance modelling for industrial electrical motors: Integrating machine learning and sensor technologies,” Meas. Sensors, vol. 38, 2025, doi: 10.1016/j.measen.2024.101473.
T. T. Luu and D. A. Huynh, “A ResNet-based deep reinforcement learning framework using soft actor-critic for remaining useful life prediction of rolling bearings,” Results Eng., vol. 27, no. August, p. 106739, 2025, doi: 10.1016/j.rineng.2025.106739.
M. R and R. R. Mutra, “Fault classification in rotor-bearing system using advanced signal processing and machine learning techniques,” Results Eng., vol. 25, no. December 2024, p. 103892, 2025, doi: 10.1016/j.rineng.2024.103892.
Ovie Vincent Erhueh, Chukwuebuka Nwakile, Oluwaseyi Ayotunde Akano, Adeoye Taofik Aderamo, and Enobong Hanson, “Advanced maintenance strategies for energy infrastructure: Lessons for optimizing rotating machinery,” Glob. J. Res. Sci. Technol., vol. 2, no. 2, pp. 065–093, 2024, doi: 10.58175/gjrst.2024.2.2.0073.
L. Magadan, J. Roldan-Gomez, J. C. Granda, and F. J. Suarez, “Early Fault Classification in Rotating Machinery With Limited Data Using TabPFN,” IEEE Sens. J., vol. 23, no. 24, pp. 30960–30970, 2023, doi: 10.1109/JSEN.2023.3331100.
Downloads
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
