Abstract
Structural integrity monitoring (SIM) is essential for the safe and efficient maintenance of civil infrastructure. With the rise of sensor-based monitoring systems, mathematical models play a central role in interpreting real-time data and predicting structural health. This article discusses deterministic, probabilistic, and data-driven modeling techniques used in SIM, focusing on their application in damage detection, fatigue analysis, and lifespan forecasting of critical infrastructures such as bridges and high-rise buildings. By integrating finite element methods (FEM), Bayesian inference, and machine learning models, engineers can ensure early detection of structural faults and reduce maintenance costs. A framework combining these models enhances decision-making for preventive and corrective interventions.

This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2023 Alexei Petrov (Author)