Prediction of Failure Modes of Steel Tube-Reinforced Concrete Shear Walls Using Blending Fusion Model Based on Generative Adversarial Networks Data Augmentation

The steel tube-reinforced concrete (STRC) shear wall plays an important role in the seismic design of high-rise building structures. Due to the synergistic collaboration between steel tubes and concrete, they effectively enhance the ductility and energy dissipation capacity of conventional shear walls. To identify vulnerable areas prone to brittle failure and optimize the design, it is essential to develop a rapid method for identifying the failure mode of STRC shear walls. In this study, a fast identification method of STCR shear wall failure modes based on a Blending fusion model with Generative Adversarial Network (GAN) augmented data is proposed. The GAN is employed to address the issue of inadequate experimental data by generating new samples. This method combines classification boosting (Catboost), Random Forest (RF), K-Nearest Neighbors (KNN), and Least Absolute Shrinkage and Selection Operator (LASSO) to establish the Blending-CRKL fusion model to improve the prediction accuracy of the failure mode of STRC shear walls. The results reveal a significant improvement in the prediction performance of KNN, Backpropagation Neural Network (BPNN), RF, Light Gradient Boosting Machine (LightGBM), Catboost, and Blending-CRKL models after augmenting the training set with GAN. On average, the accuracy increased by 13%, precision increased by 81%, recall increased by 48%, and F1 score increased by 67%. The proposed Blending-CRKL fusion model outperforms the tested KNN, BPNN, RF, LightGBM, and Catboost models, achieving an accuracy rate of 97% in predicting the failure mode of STRC shear walls. Additionally, the stability and robustness of the Blending-CRKL model were validated, while the important features and value ranges of different failure modes were analyzed. This study provides a reference for the rapid identification of the failure mode of STRC shear walls.