Concrete-to-concrete interface shear strength prediction based on explainable extreme gradient boosting approach

Accurate prediction of the shear strength of the interface between old and new concrete (cold joints) is essential for the design or assessment of precast and retrofitted concrete structures. However, the shear mechanism of the interface under shear loading is complicated and many factors can affect the shear strength. The conventional empirical models developed based on specific and limited dataset cannot well predict the interface shear strength. This study adopts the machine learning-based approaches and Shapley Additive exPlanations technique to develop an explainable ML-model for interface shear strength prediction of the cold joints. A comprehensive interface shear strength database consisting of 217 cold joints with variant design attributes and two types of interfaces (rough and smooth) were developed. The eXtreme Gradient Boosting (XGBoost) algorithm was selected to develop the predictive model. The model performance of the XGBoost model was thoroughly compared with three additional ML-models (DT, RF, ANN) and six empirical models (ACI, AASHTO, CSA, Kahn and Mitchell, Patnaik, Mattock). Four quantitative measures (R2, RMSE, MAE, and MAPE) were utilized to evaluate the prediction accuracy and the results show that the XGBoost model has the best model performance among the four ML-models. Meanwhile the XGBoost model is superior to the empirical models. The most significant parameter affecting the predictions of the XGBoost model is the reinforcement ratio. The surface type, section width of the interface and concrete strength can significantly affect the shear strength.

Automated summary

Accurate prediction of the shear strength of old and new concrete interfaces is crucial for the design and assessment of precast and retrofitted concrete structures. This study developed an explainable machine learning model for predicting interface shear strength, with the XGBoost model showing the best performance among the ML-models and outperforming empirical models. Key factors affecting predictions include reinforcement ratio, surface type, interface section width, and concrete strength.