Shear bearing capacity prediction of STRC shear walls using data-augmented fusion model

Machine learning (ML) accurately predicts the shear bearing capacity of steel tube-reinforced concrete (STRC) shear walls, aiding optimization design. However, creating a database for STRC shear walls experimentally is time-consuming and costly. The aim of this study is to propose a method for high-accuracy prediction of STRC shear wall shear bearing capacity using a small-sample dataset. This study employs generative adversarial network (GAN) data augmentation techniques to address the issues of insufficient ML model training and low prediction accuracy in small-sample databases. Based on the stacking framework, a fusion model (Stacking-XRL) combining extreme gradient boosting (XGBoost), random forest (RF), and least absolute shrinkage and selection operator (LASSO) is established to predict the shear bearing capacity of STRC shear walls. Results show that after augmenting the training set with GAN, the prediction performance of K-nearest neighbors (KNN), backpropagation neural network (BPNN), RF, light gradient boosting machine (LightGBM), XGBoost, and stacking-XRL models significantly improve, with average increases of 10% in R-2 and average decreases of 30% and 25% in MAE and RMSE, respectively. The proposed stacking-XRL fusion model outperforms tested models, existing formulas, and Abaqus numerical simulations for the shear bearing capacity of STRC shear walls. Model interpretation reveals that the shear span ratios as the most important factors in predicting shear bearing capacity, followed by axial force ratio and whole section configuration steel tubular index.