IRO Journals
Journal of Electrical Engineering and Automation

An Integrated ML Framework for Predictive Maintenance and Energy Optimization

Open Access
Published: 17 October, 2026
Pages: 300-314
  • Aaron S. , Aaron S.
    Student, Department of Artificial Intelligence and Data Science, NPR College of Engineering and Technology, Natham, Dindigul, India
    Student, Department of Artificial Intelligence and Data Science, NPR College of Engineering and Technology, Natham, Dindigul, India
  • Akash S. , Akash S.
    Student, Department of Artificial Intelligence and Data Science, NPR College of Engineering and Technology, Natham, Dindigul, India
    Student, Department of Artificial Intelligence and Data Science, NPR College of Engineering and Technology, Natham, Dindigul, India
  • Balavijay M. , Balavijay M.
    Student, Department of Artificial Intelligence and Data Science, NPR College of Engineering and Technology, Natham, Dindigul, India
    Student, Department of Artificial Intelligence and Data Science, NPR College of Engineering and Technology, Natham, Dindigul, India
  • Prisca Mary J. Prisca Mary J.
    Assistant Professor & Head, Department of Artificial Intelligence and Data Science, NPR College of Engineering and Technology, Natham, Dindigul, India
    Assistant Professor & Head, Department of Artificial Intelligence and Data Science, NPR College of Engineering and Technology, Natham, Dindigul, India
view PDF
view PDF

How to Cite

S., Aaron, Akash S., Balavijay M., and Prisca Mary J. 2026. “An Integrated ML Framework for Predictive Maintenance and Energy Optimization”. Journal of Electrical Engineering and Automation 8 (4): 300-314. https://doi.org/10.36548/jeea.2026.4.004.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Predictive Maintenance
XGBoost
Machine Failure Prediction
AI4I 2020
SMOTE
SHAP
Explainable AI
Energy Optimization
Real-Time Monitoring

Abstract

The industrial machinery provides constant stream of sensor readings, which can be effectively used for failure prediction and maintenance decisions. This research work proposes a novel approach to enable predictive maintenance and energy saving through the use of AI4I 2020 Predictive Maintenance Dataset. In the proposed model, XGBoost algorithm is used for performing machine failure prediction, along with the use of SMOTE to handle the imbalanced classes and feature engineering for revealing the relationship between sensor readings. The SHAP-based method is used for explaining the key features affecting failure prediction and prediction-based alarm system is introduced as well. Experimental evaluation on the held-out test set demonstrated 97.4% accuracy, which is better than that of baseline models. In an experiment evaluating the performance in the 48-hour deployment, the model detected all the heat dissipation failure instances that were observed, alerting about them on average 3.2 cycles before the threshold was breached. The energy-awareness policy provided 18.4% of energy savings in the period when the machine operated with degradation.

References

  1. M. H. Rziki, A. E. Hadbi, M. K. Boutahir, and M. C. Abounaima, “Adaptive Predictive Maintenance and Energy Optimization in Metro Systems Using Deep Reinforcement Learning,” Sustainability, 2025, vol. 17, no. 11, 5096.
  2. S. Sarkar, “AI-enabled Digital Twin Framework for Predictive Maintenance and Energy Optimization in Industrial Systems,” ASRC Procedia: Global Perspectives in Science and Scholarship, 2025, vol. 1, no. 1, 1359–1389.
  3. T. S. Oyetunji, F. L. Erinjogunola, R. O. Ajirotutu, A. B. Adeyemi, T. C. Ohakawa, and S. A. Adio, “Predictive AI Models for Maintenance Forecasting and Energy Optimization in Smart Housing Infrastructure,” International Journal of Advanced Multidisciplinary Research and Studies, 2024, vol. 4, no. 6, 1372–1380.
  4. A. Hamdan, K. I. Ibekwe, V. I. Ilojianya, S. Sonko, and E. A. Etukudoh, “AI in Renewable Energy: A Review of Predictive Maintenance and Energy Optimization,” International Journal of Science and Research Archive, 2024, vol. 11, no. 1, 718–729.
  5. R. Haque, A. Bajwa, N. A. Siddiqui, and I. Ahmed, “Predictive Maintenance in Industrial Automation: A Systematic Review of IoT Sensor Technologies and AI Algorithms,” American Journal of Interdisciplinary Studies, 2024, vol. 5, no. 1, 01–30.
  6. S. M. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” in Proc. Advances in Neural Information Processing Systems (NeurIPS), 2017, vol. 30, 4765–4774.
  7. T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, 785–794.
  8. N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic Minority Over-Sampling Technique,” Journal of Artificial Intelligence Research, 2002, vol. 16, 321–357.
  9. M. Canizo, I. Triguero, A. Conde, and E. Onieva, “Multi-head CNN-RNN for Multi-Time Series Anomaly Detection: An Industrial Case Study,” Neurocomputing, 2019, vol. 363, 246–260.
  10. Predictive Maintenance Dataset (AI4I 2020) – [Available] https://www.kaggle.com/datasets/stephanmatzka/predictive-maintenance-dataset-ai4i-2020