AI-Powered Structural Health Monitoring for Seismic Resilience in Urban Bridges: A Case Study of Tehran’s Critical Infrastructure

Bridges play a pivotal role in maintaining the operational continuity of urban transportation systems, especially during and after seismic events. In seismically active regions such as Tehran, aging bridge infrastructure combined with increasing traffic loads and inadequate monitoring mechanisms has significantly elevated the risk of structural failure. This study proposes an AI-powered structural health monitoring (SHM) framework tailored to enhance seismic resilience in Tehran's urban bridge network. The framework integrates real-time sensor data acquisition, machine learning-based damage detection, and digital twin simulations to monitor structural responses, predict failure risks, and enable data-driven maintenance planning. A selection of Tehran’s critical vehicular and pedestrian bridges—particularly those located near fault lines or major highways—were evaluated as part of the case study. The results demonstrate that AI-enhanced SHM systems substantially increase detection accuracy, reduce response time, and improve preparedness for seismic hazards. The proposed framework offers a scalable model for seismic risk mitigation in urban infrastructure and provides practical pathways for smart bridge management in earthquake-prone cities.

Keywords:

Artificial Intelligence (AI) , Structural Health Monitoring (SHM) , Seismic Resilience , Urban Bridges , Digital Twin , Earthquake Engineering , Smart Infrastructure , Tehran