Introduction: This paper evaluates the robustness and generalization ability of five recently developed Convolutional Neural Networks (CNNs), Visual Geometry Group 16 (VGG16), Google Inception Net (GoogLeNet), Mobile Network version 3 Large (MobileNetV3-Large), Efficient Network B0 (EfficientNetB0) and Efficient Network version 2 Small (EfficientNetV2-S), on crack recognition and classification. Methods: This study proposes a semantic segmentation based on VGG16- U-Net to address the issue of background noise in the images automatically and the transfer learning with fine-tuning is used to improve the performance of the CNNs in the bridge crack image dataset and building crack image dataset (transverse cracks, vertical cracks, oblique cracks and irregular cracks). Results: The results indicate that the MobileNetV3-Large has the best performance. For the low-resolution building crack image dataset, the accuracy of the crack recognition reaches 99.58% and the F1-score reaches 99.60%. The accuracy of the classification reaches 94.70% and the Macro-F1 reaches 94.71%. For the higher resolution bridge crack image dataset, the accuracy of the classification reaches 95.70% and the Macro-F1 reaches 95.67%. Discussion: The results show that the MobileNetV3-Large has the best robustness and generalization ability with a small CNN size and the shortest training time.

Under varying humidity and temperature conditions, with the constraint of metal fasteners to wood shrinkage, cracks along the bolt lines are generally observed in bolted glulam joints. A three‐dimensional (3D) numerical model was established in software package ANSYS to investigate the cyclic behavior of bolted glulam joints with local cracks. A reversed cyclic loading was applied in the parallel‐to‐grain direction. The accuracy of numerical simulation was proved by comparison with full‐scale experimental results. Typical failure modes were reproduced in the numerical analysis with the application of wood foundation zone material model and cohesive zone material model. The effect of crack number and length on the hysteretic behavior of bolted glulam joints was quantified by a parametric study. It was found that initial cracks impair the peak capacity and elastic stiffness of bolted glulam joints significantly. More decrease in capacity was observed in joints with more cracks, and longer cracks affect elastic stiffness more dramatically. Moreover, with the existence of initial cracks, the energy dissipated and equivalent viscous damping ratio of bolted joints are reduced by 24% and 13.3%, respectively.