Machine learning based predictive model for bond strength of FRP reinforced concrete at high temperature

Fiber-reinforced polymer (FRP) bars have better tensile strength and durability than normal steel bars. The use of FRP bars to replace steel bars in traditional concrete structures has attracted much attention in recent years. Similar to steel bars, the bond strength between FRP bars and concrete is a very important parameter in FRP-reinforced concrete structures, which directly affects the bearing capacity and safety of the structure. At present, the accuracy of calculating the bond strength between FRP bars and concrete under the action of high temperature still needs to be improved. In this study, a prediction model of bond strength between FRP bars and concrete at high temperatures was constructed by collecting 151 sets of experimental data, and six machine learning algorithms were used to construct the prediction model and perform parameter importance and sensitivity analyses. The results show that the XGBoost model can predict the bond strength between FRP bars and concrete more accurately. The conclusions obtained can provide a reference for the design of the specification to a certain extent.