International Journal of Emerging Research in Science, Engineering, and Management
Vol. 1, Issue 1, pp. 01-09, July 2025.
This work is licensed under a Creative Commons Attribution 4.0 International License.
AI-based Predictive Maintenance in Mechanical Systems
Sayyed Nagulmeera
G Rajesh
Bandi Rajasekhar
Shaik Hedayath Basha
Assistant Professor, Department of CSE, DVR & Dr. HS MIC College of Technology, Vijayawada, India.
Assistant Professor, Department of CSE, NBKRIST, Vidyanagar, India.
HOD, Department of CSE, Sree Venkateswara College of Engineering, Nellore, India.
Associate Professor, Department of ECE, R.M.K. College of Engineering and Technology, Chennai, India.
Abstract: Predictive maintenance has emerged as a critical solution for minimizing unplanned downtime, extending equipment lifespan, and enhancing operational efficiency in mechanical systems. Recent advancements in artificial intelligence (AI) have enabled the development of intelligent maintenance strategies that leverage machine learning (ML), deep learning (DL), and hybrid algorithms to anticipate equipment failures with high accuracy. While numerous AI-driven predictive maintenance solutions have been proposed, most are application-specific, resulting in fragmented methodologies with limited transferability across domains. This paper proposes a unified conceptual framework for AI-based predictive maintenance tailored to mechanical systems. Drawing insights from diverse sectors—including HVAC, gas turbines, photovoltaic systems, manufacturing, and tunneling infrastructure—the framework integrates essential layers: data acquisition, preprocessing, modeling, decision-making, and action. The proposed model emphasizes modularity, scalability, and adaptability, and supports integration with real-time data sources, including edge computing platforms. This paper aims to consolidate current advancements, address cross-domain limitations, and offer a reusable framework that can guide the implementation of predictive maintenance across a variety of mechanical environments.
Keywords: AI-based prediction, HVAC, Gas Turbines, Mechanical Systems, Tunneling.
References:
- N. H. Amin, A. Etemad, and A. Abdalisousan, “Data-driven performance analysis of an active chilled beam air conditioning system: A machine learning approach for energy efficiency and predictive maintenance,” Results in Engineering, vol. 23, p. 102747, Aug. 2024, doi: 10.1016/j.rineng.2024.102747.
- L. Brahimi, N. Hadroug, A. Iratni, A. Hafaifa, and I. Colak, “Advancing predictive maintenance for gas turbines: An intelligent monitoring approach with ANFIS, LSTM, and reliability analysis,” Computers & Industrial Engineering, vol. 191, p. 110094, Mar. 2024, doi: 10.1016/j.cie.2024.110094.
- A. Syamsuddin, A. C. Adhi, A. Kusumawardhani, T. Prahasto, and A. Widodo, “Predictive maintenance based on anomaly detection in photovoltaic system using SCADA data and machine learning,” Results in Engineering, p. 103589, Dec. 2024, doi: 10.1016/j.rineng.2024.103589.
- P. Marti-Puig, I. A. Touhami, R. C. Perarnau, and M. Serra-Serra, “Industrial AI in condition-based maintenance: A case study in wooden piece manufacturing,” Computers & Industrial Engineering, vol. 188, p. 109907, Jan. 2024, doi: 10.1016/j.cie.2024.109907.
- X. Zou et al., “Advancing tunnel equipment maintenance through data-driven predictive strategies in underground infrastructure,” Computers and Geotechnics, vol. 173, p. 106532, Jun. 2024, doi: 10.1016/j.compgeo.2024.106532.
- V. Artiushenko, S. Lang, C. Lerez, T. Reggelin, and M. Hackert-Oschätzchen, “Resource-efficient Edge AI solution for predictive maintenance,” Procedia Computer Science, vol. 232, pp. 348–357, Jan. 2024, doi: 10.1016/j.procs.2024.01.034.
- Y. Lu, J. Jiang, B. Wang, W. Chen, and J. Ye, “AI-based evaluation method of mechanical performance of shield tunnel structures after fire,” Tunnelling and Underground Space Technology, vol. 150, p. 105858, May 2024, doi: 10.1016/j.tust.2024.105858.
- O. Aeddula, M. Frank, R. Ruvald, C. J. Askling, J. Wall, and T. Larsson, “AI-Driven predictive maintenance for autonomous vehicles for Product-Service system development,” Procedia CIRP, vol. 128, pp. 84–89, Jan. 2024, doi: 10.1016/j.procir.2024.06.008.
- C. Gnekpe, D. Tchuente, S. Nyawa, and P. K. Dey, “Energy performance of building refurbishments: Predictive and prescriptive AI-based machine learning approaches,” Journal of Business Research, vol. 183, p. 114821, Jul. 2024, doi: 10.1016/j.jbusres.2024.114821.
- A. Stohr, P. Ollig, R. Keller, and A. Rieger, “Generative mechanisms of AI implementation: A critical realist perspective on predictive maintenance,” Information and Organization, vol. 34, no. 2, p. 100503, Feb. 2024, doi: 10.1016/j.infoandorg.2024.100503.
- P. D. Paraschos and D. E. Koulouriotis, “Learning-based production, maintenance, and quality optimization in smart manufacturing systems: A literature review and trends,” Computers & Industrial Engineering, p. 110656, Oct. 2024, doi: 10.1016/j.cie.2024.110656.
- Gusnul Mahesa, Ahmad Tajri, Eflan Ananda Pujito, Muhammad Rizal, Dimas Arya Bagaskara, Mohammad Givi Efgivia, “Integration of Artificial Intelligence in Network Technology: A Literature Review,” International Journal of Emerging Research in Engineering, Science, and Management, vol. 4, no. 2, pp. 22-31, 2025. doi: 10.58482/ijeresm.v4i2.4.
- Allu Venkata Satyanarayana, Yerubandi Venkata Ramana Murthy, Chandra Mouli V.S.A, “Evaluation of Mechanical Properties of Al6061 Composite by Stir Casting Method,” International Journal of Emerging Research in Engineering, Science, and Management, vol. 3, no. 3, pp. 51-58, 2024. doi: 10.58482/ijeresm.v3i3.9.