Artificial Intelligence -Integrated Structural Health Monitoring of Reinforced Concrete Bridges under Multi -Hazard Conditions

Reinforced concrete (RC) bridges are increasingly exposed to multiple concurrent hazards such as earthquakes, floods, and long-term material degradation. To address the growing demand for real-time, data-driven damage detection, this study develops an artificial intelligence-integrated structural health monitoring (AI-SHM) framework tailored for RC bridge systems operating under multi-hazard conditions. The proposed framework combines finite element modeling with supervised machine learning algorithms —namely convolutional neural networks (CNNs) and random forests —for pattern recognition and damage classification. Synthetic datasets were generated from time-history simulations of bridge responses subjected to seismic loads, thermal gradients, and progressive corrosion effects. Key features such as displacement, acceleration, and strain were extracted and used to train and validate the models. Results show that the AI-integrated system achieved over ۹۲% accuracy in identifying damage locations and types, even under overlapping hazard scenarios. Compared to traditional threshold-based methods, the proposed approach significantly improves sensitivity and robustness. This work demonstrates the potential of AI-enhanced SHM to support early warning systems and resilience planning for critical bridge infrastructure in complex environmental contexts.

کلیدواژه ها:

Structural Health Monitoring (SHM) ، Reinforced Concrete Bridges ، Artificial Intelligence ، Multi-Hazard Conditions ، Machine Learning ، Damage Detection ، Resilience Engineering