Smart Predictive Maintenance for Energy System performed by Artificial Intelligence

Abstract

In the era of digital transformation, artificial intelligence (AI) is emerging as a foundational technology that is driving efficiency and innovation across many industries. One area where AI has had a significant impact is Smart predictive maintenance (SPM). Industries are gradually moving away from old models of reactive maintenance to proactive methods using AI. This shift helps minimize downtime, reduce costs, and improve operational efficiency. This article explores the many benefits, real-world applications, and techniques through which AI is enabling the implementation of SPM. Multi-agent system-based SPM employing machine learning classifiers has been used combined with deep learning proposed algorithms LSTM for optimizing SPM for energy systems at SONELGAZ Algeria. Using the forecast model and analyzing time-series data, LSTM model has obtained good accuracy with almost 97% accuracy. The experimental results showcase remarkable performance, achieving a Score about of 92% for binary classification and an impressive 97% for multiple classifications. Comparative analysis highlights the superiority of the MAS-LSTM hybrid approach in prediction accuracy. Our solution model, SIPM (Smart energy system, Intelligent, Predictive, and Maintenance), implemented in Python, predicts a device failure probability within 30 days as 0.0046.

Keywords

• Artificial Intelligence (AI)
• Autonomy Robot (AR)
• Smart Predictive Maintenance
• Energy Systems
• LSTM
• Multi-Agent System

References

1. Thyago P Carvalho, Fabrízzio AAMN Soares, Roberto Vita, Roberto da P Francisco, João P Basto, and Symone GS Alcalá. A systematic literature review of machine learning methods applied to predictive maintenance. Computers & Industrial Engineering, 137:106024, 2019.
2. Marwa Assim, Qasem Obeidat, and Mustafa Hammad. Software defects prediction using machine learning algorithms. In 2020 International conference on data analytics for business and industry: way towards a sustainable economy (ICDABI), pages 1–6. IEEE, 2020.
3. Clayton Miller, Pandarasamy Arjunan, Anjukan Kathirgamanathan, Chun Fu, Jonathan Roth, June Young Park, Chris Balbach, Krishnan Gowri, Zoltan Nagy, Anthony D Fontanini, et al. The ASHRAE great energy predictor III competition: Overview and results. Science and Technology for the Built Environment, 26(10):1427–1447, 2020.
4. Jay Lee, Edzel Lapira, Shanhu Yang, and Ann Kao. Predictive manufacturing system-trends of next-generation production systems. IFAC Proceedings Volumes, 46(7):150–156, 2013.
5. Jose-Raul Ruiz-Sarmiento, Javier Monroy, Francisco-Angel Moreno, Cipriano Galindo, Jose-Maria Bonelo, and Javier Gonzalez-Jimenez. A predictive model for the maintenance of industrial machinery in the context of industry 4.0. Engineering Applications of Artificial Intelligence, 87:103289, 2020.
6. Jinjiang Wang, Peilun Fu, Laibin Zhang, Robert X Gao, and Rui Zhao. Multilevel information fusion for induction motor fault diagnosis. IEEE/ASME Transactions on Mechatronics, 24(5):2139–2150, 2019.
7. Maria Drakaki, Yannis L Karnavas, Panagiotis Tzionas, and Ioannis D Chasiotis. Recent developments towards industry 4.0 oriented predictive maintenance in induction motors. Procedia Computer Science, 180:943–949, 2021.
8. Weiting Zhang, Dong Yang, and Hongchao Wang. Data-driven methods for predictive maintenance of industrial equipment: A survey. IEEE Systems Journal, 13(3):2213–2227, 2019.

9. Sam Heim, Jason Clemens, James E Steck, Christopher Basic, David Timmons, and Kourtney Zwiener. Predictive maintenance on aircraft and applications with digital twin. In 2020 IEEE International Conference on Big Data (Big Data), pages 4122–4127. IEEE, 2020.
10. Murat Yildirim, Nagi Z Gebraeel, and Xu Andy Sun. Integrated predictive analytics and optimization for opportunistic maintenance and operations in wind farms. IEEE Transactions on Power Systems, 32(6):4319–4328, 2017.
11. Pooja Malik, Anita Gehlot, Rajesh Singh, Lovi Raj Gupta, and Amit Kumar Thakur. A review on ANN-based model for solar radiation and wind speed prediction with real-time data. Archives of Computational Methods in Engineering, 29(5):3183–3201, 2022.
12. F-y Shen, W Li, D-n Jiang, and H-j Mao. Autonomous predictive maintenance of quadrotor UAV with multi-actuator degradation. The Aeronautical Journal, pages 1–25, 2024.
13. Tran Minh Tuan and Pham Thi Hoa. Emerging technologies in secure data sharing, predictive maintenance, and autonomous systems in 5G networks. Journal of Humanities and Applied Science Research, 7(9):1–15, 2024.
14. Diego Galar and Uday Kumar. Robotics and artificial intelligence (AI) for maintenance. Monitoring and Protection of Critical Infrastructure by Unmanned Systems, pages 206–223, 2023.
15. Kathrin Kirchner, Grzegorz Leszczyński, Marek Zieliński, and Bartosz Jędrzejczak. Predictive maintenance as an artificial intelligence service: A study of value creation. In Handbook of Services and Artificial Intelligence, pages 31–52. Edward Elgar Publishing, 2024.
16. Maria G Ioannides, Anastasios P Stamelos, Stylianos A Papazis, Erofili E Stamataki, and Michael E Stamatakis. Internet of Things-based control of induction machines: Specifics of electric drives and wind energy conversion systems. Energies, 17(3):645, 2024.
17. Madhu Puttegowda and Sharath Ballupete Nagaraju. Artificial intelligence and machine learning in mechanical engineering: Current trends and future prospects. Engineering Applications of Artificial Intelligence, 142:109910, 2025.
18. John Eriksson. Machine learning for predictive maintenance on wind turbines: Using SCADA data and the Apache Hadoop ecosystem, 2020.