An AI-driven LiDAR-based framework for structural health monitoring and crack detection in bridges and structures

In response to these limitations, this thesis presents a comprehensive, AI-powered, and digitally integrated methodology for the Structural Health Monitoring (SHM) of bridges and civil infrastructure. It combines the power of LiDAR-based point cloud data, unsupervised and deep learning techniques, digital twin modelling, simulation analytics, and real-time dashboards to establish a predictive, autonomous, and highly scalable SHM framework. The research highlights significant technological advancements and engineering practices that align with modern infrastructure safety, longevity, and cost-effectiveness [1, 5].