About our Sessions

Advancements in sensor and information fusion technologies have brought new perspectives to assessing the health state and safety of bridges across Texas. In particular, emerging artificial intelligence (AI) technologies have shown significant advancements in enhancing damage detection, condition assessment, maintenance strategies, and decision-making. These are driving automation within traditional structural health monitoring (SHM) practices, pushing the frontier toward a new digital era for the bridge engineering community.

This study provides an overview of AI-driven automation in SHM for bridges, focusing on advancements in signal processing and damage detection. It traces the evolution from traditional machine learning techniques, such as shallow learning, to the breakthroughs achieved through deep learning, and the recent emergence of generative AI. These developments are transforming data-driven SHM by enabling more efficient, accurate, and interpretable methods for detecting structural damage and conducting condition assessments of bridges.