Finding Hidden Damage in Cold-Formed Steel with Radar and AI

University of Houston, TX

A new technology uses ground-penetrating radar and artificial intelligence to automatically detect possible damage in materials like studs and joists made of the lightweight steel. (Image: ananaline/ Adobe Stock)

A University of Houston engineer has developed a method to detect possible damage in concealed cold-formed steel construction framing materials hidden behind walls, without having to tear the walls open.

Over the past decade, as advancements in developing cold-formed steel have surged, its use in the construction industry has soared. In comparison to hot rolled steel, cold-formed steel is more affordable and offers environmental benefits. But traditional inspection of concealed cold-steel materials is inefficient, requiring partial or complete removal of cladding and drywall, making the process labor-intensive and costly.

“To address these limitations, we have introduced a new framework that combines a quick radar scan with AI that reads the radar images and points to where the steel is, where damage is likely, and the severity and type of damage,” said Vedhus Hoskere, Kaspar J. Willam Assistant Professor of Civil and Environmental Engineering. “That lets inspectors verify only the flagged spots instead of opening up everything — saving time, money, and disruption, and helping maintenance or post-disaster assessments scale.”

Hoskere published his new method in the Journal of Computing in Civil Engineering. It includes development of his new AI tool — InternImage.

Hoskere’s invention also includes a specialized dataset of radar images of cold-formed steel behind common wall coverings, spanning different layouts and damage types and a new training trick for the AI (GPR-CutMix) that helps the model handle real-world variations, like different stud spacings and messy field conditions.

“The radar sends pulses into the wall and listens for echoes from what’s behind it. Hidden steel creates a recognizable pattern in the radar scan image. If the steel is damaged (for example, buckled), it can create a small gap/void that changes the echo pattern in a consistent way,” said Hoskere. “The AI is trained to recognize these patterns and draw boxes around them, labeling what it thinks it sees.” In other words, radar takes the picture, and AI interprets it.

“These findings highlight the potential of our framework to advance concealed cold-formed steel structural inspection methods by providing a rapid, reliable and scalable approach for damage detection, ultimately improving building maintenance and rehabilitation,” said Muhammad Taseer Ali, first author of the research. Before becoming a graduate student in Hoskere’s lab, Ali had 10 years of industry experience in cold-formed steel structure design.

For more information, contact Vedhus Hoskere at This email address is being protected from spambots. You need JavaScript enabled to view it..