Machine learning model helps ensure safe structural design

A newly developed machine learning model makes reliable strength predictions in carbon fiber-reinforced steel columns, according to a news release by Seoul National University of Science & Technology.

Concrete-filled steel tube columns (CFST) strengthened with carbon fiber-reinforced polymer (CFRP) combine the robust load-bearing capabilities and strength of CFST columns with the lightweight, corrosion-resistant properties of CFRP. The research team “presented and verified a novel hybrid machine learning model capable of accurately predicting the ultimate axial strength of CFRP-strengthened CFST columns—a critical structural parameter in construction projects,” the release says.

Available data on these columns are limited, leading to questionable prediction performance even when using the best available machine learning-powered models. “To overcome the scarce availability of data on CFRP-strengthened CFST columns, the researchers employed a form of generative AI to create a synthetic database,” the researchers say.

“The hybrid model exhibited better accuracy than even the best alternatives available, achieving lower error rates across several key metrics. The results were further solidified via a reliability analysis, which indicated that the model can consistently deliver accurate predictions under various conditions.”

To make the proposed model more easily accessible and widely applicable, the research team also created a web browser-based tool that can be used to make ultimate axial strength predictions in CFRP-strengthened CFST columns for free.