Improving Structural Safety with AI

In a paper published by the Structural Health Monitoring journal, researchers give details on how they created an AI system to analyze and assess the damage of bolt connections in metallic structures.

The AI system, named SHMnet, was trained using four repeated datasets and showed a 100% success rate when identifying damage in test structures. SHMnet could be incredibly useful to structural engineers, civil engineers, and government organizations who are responsible for and consistently monitor the structural integrity of metal structures like bridges, towers, dams, and other metal structures. With more fine-tuning, this machine learning algorithm would make engineers’ jobs easier and more accurate while making large structures safer to the public.

Researcher Dr. Ying Wang, one of the paper’s authors and Assistant Professor at the University of Surrey, writes, “While there is more to do, such as testing SHMnet under different vibration conditions and obtaining more training data, the real test is for this system to be used in the field where a reliable, accurate, and affordable way of monitoring infrastructure is sorely needed.”

We love hearing about ongoing developments in the field and hope you do, too! To read more about this study, see the full article here on the University of Surrey’s website.