This issue shares the paper “Machine learning based prediction of joint sheet strength for fiber reinforced concrete beam column connections” published in the international journal Composite Structures in 2026.
A FRC beam column joint test database containing 220 specimens was constructed, and the predictive performance of 10 machine learning algorithms was systematically compared.
The SHAP method was used to analyze the parameter influence mechanism, and a visual GUI prediction tool was developed, providing a data-driven new method for seismic design of fiber-reinforced concrete structures.
This article is only for academic exchange, and the copyright belongs to the original author and publisher.
.