Abstract

Author:
James Avevor, Francis Chukwudi Eze, Onum Friday Okoh, Selasi Agbale Aikins, Lawrence Anebi Enyejo, Ignatius Idoko Adaudu

Doi: 10.26480/egnes.02.2025.56.64

This is an open access article distributed under the Creative Commons Attribution License CC BY 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

As climate-induced hazards such as extreme heatwaves, flooding, and hurricanes increasingly threaten the operational continuity of energy-critical infrastructure, the integration of predictive maintenance into structural and economic resilience strategies has become imperative. This review examines the development and application of real-time predictive maintenance models for combined-cycle turbines (CCTs) deployed in critical load-bearing facilities such as hospitals, data centers, and industrial manufacturing hubs where energy supply reliability and structural integrity are interdependent. Emphasis is placed on the role of machine learning algorithms, including deep neural networks and reinforcement learning frameworks, in processing high-frequency sensor data for anomaly detection, failure prediction, and dynamic scheduling of maintenance actions. The study also explores how these models are embedded within digital twin environments to simulate both turbine performance and its effect on structural systems during climate extremes. From an economic perspective, the review analyzes how predictive maintenance reduces unscheduled downtimes, minimizes structural stress-induced failures, and lowers lifecycle operating and repair costs. Quantitative insights into avoided capital losses, enhanced return on infrastructure investment (ROI), and reduction in economic disruptions due to turbine failure are discussed. Furthermore, the paper evaluates policy and regulatory mechanisms that support the integration of smart maintenance frameworks into infrastructure resilience planning and highlights best practices for implementation in high-risk geographic zones. By aligning real-time maintenance intelligence with structural engineering and economic risk mitigation, this work identifies a transformative paradigm for safeguarding both the functional and financial sustainability of critical energy-structural systems in an era of increasing environmental volatility.