Abstract :

The Rapid Digital Transformation Of Industrial Systems Has Accelerated The Adoption Of Advanced Maintenance Strategies Aimed At Improving Equipment Reliability, Operational Efficiency, And Sustainability. Reliability-Centered Maintenance (RCM), Traditionally Based On Predefined Failure Modes And Historical Maintenance Records, Faces Significant Limitations In Modern Industrial Environments Characterized By Complex Cyber-physical Systems, Dynamic Operating Conditions, And Vast Streams Of Heterogeneous Sensor Data. Artificial Intelligence (AI) Has Emerged As A Transformative Technology Capable Of Enhancing RCM Through Dynamic Risk Modeling, Real-time Condition Assessment, Predictive Analytics, And Autonomous Decision Support. This Study Presents A Comprehensive Review And Conceptual Framework For Artificial Intelligence-Driven Dynamic Risk Modeling (AI-DDRM) Within The Context Of ReliabilityCentered Maintenance. The Paper Systematically Examines Recent Developments In Machine Learning, Deep Learning, Digital Twins, Edge Computing, Industrial Internet Of Things (IIoT), Reinforcement Learning, And Explainable Artificial Intelligence (XAI) For Maintenance Optimization. A Thematic Review Of Significant Studies Published Between 2018 And 2026 Reveals That AI-enabled Maintenance Systems Can Reduce Unplanned Downtime By 20–50%, Lower Maintenance Costs By 15–40%, And Improve Asset Utilization By Up To 30%. Despite These Advancements, Challenges Remain Regarding Data Quality, Model Interpretability, Cybersecurity, Integration Complexity, And Autonomous Decision Reliability. To Address These Issues, A Novel Conceptual Framework Integrating Multi-modal Condition Monitoring, Dynamic Risk Assessment, Digital Twin Technology, And Autonomous Maintenance Decision Support Is Proposed. The Framework Enables Continuous Risk Adaptation Based On Evolving Equipment Conditions And Operational Contexts. The Study Further Identifies Critical Research Gaps And Proposes A Future Research Roadmap Emphasizing Explainable AI, Federated Learning, Self-healing Systems, And Autonomous Industrial Ecosystems. The Findings Contribute To Both Academic Research And Industrial Practice By Providing A Structured Foundation For The Next Generation Of Intelligent Maintenance Systems Capable Of Supporting Industry 5.0 Objectives.

Published:

22-12-2025

Issue:

Vol. 25 No. 12 (2025)

Page Nos:

566-595

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite