Forecasting ultimate bond strength between ribbed stainless steel bar and concrete using explainable machine learning algorithms

Purpose In recent years, there has been growing interest in the use of stainless steel (SS) in reinforced concrete (RC) structures due to its distinctive corrosion resistance and excellent mechanical properties. To ensure effective synergy between SS and concrete, it is necessary to develop a time-saving approach to accurately determine the ultimate bond strength τ u between the two materials in RC structures. Design/methodology/approach Three robust machine learning (ML) models, including support vector regression (SVR), random forest (RF) and extreme gradient boosting (XGBoost), are employed to predict τ u between ribbed SS and concrete. Model hyperparameters are fine-tuned using Bayesian optimization (BO) with 10-fold cross-validation. The interpretable techniques including partial dependence plots (PDPs) and Shapley additive explanation (SHAP) are also utilized to figure out the relationship between input features and output for the best model. Findings Among the three ML models, BO-XGBoost exhibits the strongest generalization and highest accuracy in estimating τ u . According to SHAP value-based feature importance, compressive strength of concrete f c emerges as the most prominent feature, followed by concrete cover thickness c , while the embedment length to diameter ratio l / d , and the diameter d for SS are deemed less important features. Properly increasing c and f c can enhance τ u between ribbed SS and concrete. Originality/value An online graphical user interface (GUI) has been developed based on BO-XGBoost to estimate τ u . This tool can be utilized in structural design of RC structures with ribbed SS as reinforcement.