Dynamic bond stress-slip relationship of steel reinforcing bars in concrete based on XGBoost algorithm

Abstract

The bond stress-slip relationship between a deformed steel bar and concrete under various loading rates is required to appropriately simulate the ultimate conditions of concrete structures under dynamic loading. Furthermore, the corresponding key bond parameters are crucial to ensure the accuracy of the bond-slip model. This study analyzed the effect of concrete strength, geometric profile of steel bar, concrete cover, and stress state around the bond region on the dynamic bond parameters and bond-slip curves. For this purpose, a database containing 1056 pullout specimens was established, which was used to train three ensemble learning models, including Extreme Gradient Boosting Decision Tree (XGBoost), Gradient Boosting Regression Tree, and Random Forest, thereby predicting the bond parameters. The ensemble learning models exhibited higher accuracy than existing empirical models, with the XGBoost algorithm attaining the highest accuracy. Furthermore, the predicted bond parameters were found to express the bond response of the steel bar under different loading rates and lateral confinements with good accuracy. The model proposed in this study provides a new approach for determining the bond parameters and improves the accuracy of bond stress-slip model.