Enhancing Industrial Reliability through Predictive Maintenance using Hybrid ML-DL Models
DOI:
https://doi.org/10.64882/ijrt.v13.i2.480Keywords:
Predictive Maintenance, Convolutional Neural Network (Conv1D), Machine Learning and Deep Learning,, Industrial IoT (IIoT) and Rotating Machinery Fault DetectionAbstract
This study Predictive maintenance seeks to anticipate equipment breakdowns and reduce unplanned downtime through the utilization of sensor data and sophisticated modeling techniques. This study introduces a detailed pipeline utilizing the AI4I 2020 Predictive Maintenance Dataset, a high-caliber synthetic industrial dataset that includes air and process temperatures, rotational speed, torque, tool wear, and failure labels from the UCI Machine Learning Repository. Our methodology includes thorough preprocessing, which involves the elimination of inaccurate measurements, the generation of engineering characteristics such as temperature difference and mechanical power, feature standardization, and stratified train-test division. Class imbalance is mitigated using SMOTE, which equalizes the proportion of failure and non-failure cases. We develop and enhance various machine learning models (Random Forest, XGBoost, SVM, Logistic Regression) and a Conv1D deep learning model specifically designed for sequential sensor data. Model performance is assessed using metrics like accuracy, precision, recall, F1-score, ROC-AUC, and log loss. Results indicate that Random Forest and XGBoost achieve good accuracy and balanced detection, whereas SMOTE markedly improves recall. The Conv1D network demonstrates significant vulnerability to failures, especially when class balancing is implemented. The innovation consists of combining domain-specific feature engineering with sophisticated oversampling methods and evaluating machine learning and deep learning algorithms on a practical maintenance dataset. Future endeavors will concentrate on implementing the model in real-time industrial settings, investigating hybrid architectures that integrate interpretability with sequential pattern learning, and assessing model robustness using live maintenance data.
References
R. Ganasan et al., “Moment-Rotation Characteristics Prediction Models for Unique Boltless Steel Connections Using Machine Learning,” J. Des. Built Environ., vol. 2025, no. Special Issue V, pp. 69–86, 2025, doi: 10.22452/jdbe.spv.6.
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. March, pp. 57266–57286, 2025, doi: 10.1109/ACCESS.2025.3553155.
R. Soleimani-Babakamali, M. H. Soleimani-Babakamali, M. Ali Heravi, M. Askari, O. Avci, and E. Taciroglu, “Transferring damage detection knowledge across rotating machines and framed structures: Harnessing domain adaptation and contrastive learning,” Mech. Syst. Signal Process., vol. 221, no. January, p. 111743, 2024, doi: 10.1016/j.ymssp.2024.111743.
Z. Aboulhosn, A. Musamih, K. Salah, R. Jayaraman, M. Omar, and Z. Aung, “Detection of Manufacturing Defects in Steel Using Deep Learning With Explainable Artificial Intelligence,” IEEE Access, vol. 12, no. June, pp. 99240–99257, 2024, doi 10.1109/ACCESS.2024.3430113.
A. F. Khalil and S. Rostam, “Machine Learning-based Predictive Maintenance for Fault Detection in Rotating Machinery: A Case Study,” Eng. Technol. Appl. Sci. Res., vol. 14, no. 2, pp. 13181–13189, 2024, doi: 10.48084/etasr.6813.
Z. Zhang, P. Mativenga, W. Zhang, and S. Q. Huang, “Deep Learning-Driven Prediction of Mechanical Properties of 316L Stainless Steel Metallographic by Laser Powder Bed Fusion,” Micromachines, vol. 15, no. 9, 2024, doi: 10.3390/mi15091167.
S. F. Chevtchenko et al., “Anomaly Detection in Industrial Machinery Using IoT Devices and Machine Learning: A Systematic Mapping,” IEEE Access, vol. 11, no. November, pp. 128288–128305, 2023, doi: 10.1109/ACCESS.2023.3333242.
R. R. Shubita, A. S. Alsadeh, and I. M. Khater, “Fault Detection in Rotating Machinery Based on Sound Signal Using Edge Machine Learning,” IEEE Access, vol. 11, no. January, pp. 6665–6672, 2023, doi: 10.1109/ACCESS.2023.3237074.
K. M. Almutairi and J. K. Sinha, “Experimental Vibration Data in Fault Diagnosis: A Machine Learning Approach to Robust Classification of Rotor and Bearing Defects in Rotating Machines,” Machines, vol. 11, no. 10, 2023, doi: 10.3390/machines11100943.
A. Jaramillo-Alcazar, J. Govea, and W. Villegas-Ch, “Anomaly Detection in a Smart Industrial Machinery Plant Using IoT and Machine Learning,” Sensors, vol. 23, no. 19, 2023, doi: 10.3390/s23198286.
S. Takesue et al., “Investigation of factors influencing rotating bending fatigue properties of carburized steel using large data source,” Int. J. Fatigue, vol. 198, no. February, p. 109041, 2025, doi: 10.1016/j.ijfatigue.2025.109041.
N. Espinoza-Sepulveda and J. Sinha, “Two-step vibration-based machine learning model for the fault detection and diagnosis in rotating machine and its blind application,” Struct. Heal. Monit., vol. 24, no. 2, pp. 1029–1042, 2025, doi: 10.1177/14759217241249055.
S. Sarfarazi, R. Shamass, F. Guarracino, I. Mascolo, and M. Modano, “Exploring the stainless-steel beam-to-column connections response: A hybrid explainable machine learning framework for characterization,” Front. Struct. Civ. Eng., vol. 19, no. 1, pp. 34–59, 2025, doi: 10.1007/s11709-025-1162-y.
R. Das, G. Sivaswamy, H. Lalvani, and A. P. Singh, “Fracture toughness and microstructural analysis of rotary friction welded S355J2 and SS316L steels for critical applications,” J. Adv. Join. Process., vol. 10, no. August, p. 100244, 2024, doi: 10.1016/j.jajp.2024.100244.
S. O. Ooko and S. M. Karume, “Application of Tiny Machine Learning in Predicative Maintenance in Industries,” J. Comput. Theor. Appl., vol. 2, no. 1, pp. 131–150, 2024, doi: 10.62411/jcta.10929.
D. Kolar, D. Lisjak, M. Curman, and M. Pająk, “Condition Monitoring of Rotary Machinery Using Industrial IOT Framework: Step to Smart Maintenance,” Teh. Glas., vol. 16, no. 3, pp. 343–352, 2022, doi: 10.31803/tg-20220517173151.
X. Chen, J. Van Hillegersberg, E. Topan, S. Smith, and M. Roberts, “Application of data- driven models to predictive maintenance: Bearing wear prediction at TATA steel,” Expert Syst. Appl., vol. 186, no. August 2021, p. 115699, 2021, doi: 10.1016/j.eswa.2021.115699.
K. Sarda et al., “A Multi-Step Anomaly Detection Strategy Based on Robust Distances for the Steel Industry,” IEEE Access, vol. 9, pp. 53827–53837, 2021, doi: 10.1109/ACCESS.2021.3070659.
I. Niyonambaza, M. Zennaro, and A. Uwitonze, “Predictive maintenance (Pdm) structure using internet of things (iot) for mechanical equipment used into hospitals in Rwanda,” Futur. Internet, vol. 12, no. 12, pp. 1–23, 2020, doi: 10.3390/fi12120224.
S. W. Choi, B. G. Seo, and E. B. Lee, “Machine Learning-Based Tap Temperature Prediction and Control for Optimized Power Consumption in Stainless Electric Arc Furnaces (EAF) of Steel Plants,” Sustain., vol. 15, no. 8, 2023, doi: 10.3390/su15086393.
M. A. Shaheen, R. Presswood, and S. Afshan, “Application of Machine Learning to predict the mechanical properties of high strength steel at elevated temperatures based on the chemical composition,” Structures, vol. 52, no. January, pp. 17–29, 2023, doi: 10.1016/j.istruc.2023.03.085.
M. Radonjić, S. Vujnović, A. Krstić, and Ž. Zečević, “IoT System for Detecting the Condition of Rotating Machines Based on Acoustic Signals,” Appl. Sci., vol. 12, no. 9, 2022, doi: 10.3390/app12094385.
A. Redchuk and F. W. Mateo, “New Business Models on Artificial Intelligence—The Case of the Optimization of a Blast Furnace in the Steel Industry by a Machine Learning Solution,” Appl. Syst. Innov., vol. 5, no. 1, pp. 1–8, 2022, doi: 10.3390/asi5010006.
O. Khalaj, M. B. Jamshidi, E. Saebnoori, B. Masek, C. Stadler, and J. Svoboda, “Hybrid Machine Learning Techniques and Computational Mechanics: Estimating the Dynamic Behavior of Oxide Precipitation Hardened Steel,” IEEE Access, vol. 9, pp. 156930–156946, 2021, doi: 10.1109/ACCESS.2021.3129454.
O. Mey, W. Neudeck, A. Schneider, and O. Enge-Rosenblatt, “Machine Learning-Based Unbalance Detection of a Rotating Shaft Using Vibration Data,” IEEE Int. Conf. Emerg. Technol. Fact. Autom. ETFA, vol. 2020-September, pp. 1610–1617, 2020, doi: 10.1109/ETFA46521.2020.9212000.
R. K. Sheu, Y. C. Lin, C. Y. Huang, L. C. Chen, M. S. Pardeshi, and H. H. Tseng, “IDS-DLA: Sheet Metal Part Identification System for Process Automation Using Deep Learning Algorithms,” IEEE Access, vol. 8, pp. 127329–127342, 2020, doi: 10.1109/ACCESS.2020.3007257.
N. E. Sepulveda and J. Sinha, “Parameter optimisation in the vibration-based machine learning model for accurate and reliable faults diagnosis in rotating machines,” Machines, vol. 8, no. 4, pp. 1–21, 2020, doi: 10.3390/machines8040066.
X. Huang, Z. Liu, X. Zhang, J. Kang, M. Zhang, and Y. Guo, “Surface damage detection for steel wire ropes using deep learning and computer vision techniques,” Meas. J. Int. Meas. Confed., vol. 161, p. 107843, 2020, doi: 10.1016/j.measurement.2020.107843.
K. I. Masani, P. Oza, and S. Agrawal, “Predictive maintenance and monitoring of industrial machine using machine learning,” Scalable Comput., vol. 20, no. 4, pp. 663–668, 2019, doi: 10.12694/scpe.v20i4.1585.
F. Li et al., “Ensemble Machine Learning Systems for the Estimation of Steel Quality Control,” Proc. - 2018 IEEE Int. Conf. Big Data, Big Data 2018, pp. 2245–2252, 2018, doi: 10.1109/BigData.2018.8622583.
S. Guo, T. Yang, W. Gao, and C. Zhang, “A novel fault diagnosis method for rotating machinery based on a convolutional neural network,” Sensors (Switzerland), vol. 18, no. 5, 2018, doi: 10.3390/s18051429.
S. Sarkar, V. Pateshwari, and J. Maiti, “Predictive model for incident occurrences in steel plant in India,” 8th Int. Conf. Comput. Commun. Netw. Technol. ICCCNT 2017, no. December, pp. 6–11, 2017, doi: 10.1109/ICCCNT.2017.8204077.
M. Layouni, M. S. Hamdi, and S. Tahar, “Detection and sizing of metal-loss defects in oil and gas pipelines using pattern-adapted wavelets and machine learning,” Appl. Soft Comput. J., vol. 52, pp. 247–261, 2017, doi: 10.1016/j.asoc.2016.10.040.
M. Kande, A. J. Isaksson, R. Thottappillil, and N. Taylor, “Rotating electrical machine condition monitoring automation-A review,” Machines, vol. 5, no. 4, pp. 1–15, 2017, doi: 10.3390/machines5040024.
Downloads
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
