Headed shear studs are an essential interfacial connection for precast steel–concrete structures to ensure composite action; hence, the accurate prediction of the shear capacity of headed studs is of pivotal significance. This study first established a worldwide dataset with 428 push-out tests of headed shear studs embedded in concrete with varied strengths from 26 MPa to 200 MPa. Five advanced machine learning (ML) models and three widely used equations from design codes were comparatively employed to predict the shear resistance of the headed studs. Considering the inevitable data variation caused by material properties and load testing, the isolated forest algorithm was first used to detect the anomaly of data in the dataset. Then, the five ML models were established and trained, which exhibited higher prediction accuracy than three existing design codes that were widely used in the world. Compared with the equations from AASHTO (the one that has the best prediction accuracy among design specifications), the gradient boosting decision tree (GBDT) model showed an 80% lower root mean square error, 308% higher coefficient of determination, and 86% lower mean absolute percent error. Lastly, individual conditional expectation plots and partial dependence plots showed the relationship between the individual parameters and the predicted target based on the GBDT model. The results showed that the elastic modulus of concrete, the tensile strength of the studs, and the length–diameter ratio of the studs influenced most of the shear capacity of shear studs. Additionally, the effect of the length–diameter ratio has an upper limit which depends on the strength of the studs and concrete.

The durability and safety of modern concrete architecture and infrastructure are critically impacted by early-stage surface cracks. Timely and appropriate identification and management of these cracks are therefore essential to enhance structural longevity and stability. This study utilizes computer vision technology to construct a large-scale database, comprising 106,998 concrete surface crack images from various research sources. Through data augmentation, the database is extended to 140,000 images to fully leverage the advantages of deep learning models. For concrete surface crack detection, this study proposed a lightweight convolutional neural network (CNN) model, achieving 92.27% accuracy, 94.98% recall, and a 92.39% F1 score. Notably, the model runs smoothly on lightweight office notebooks without GPUs. Additionally, an image stitching algorithm that seamlessly stitches multiple images was proposed to generate high-quality panoramic views of bridges. The image stitching algorithm demonstrates robustness when applied to multiple images, successfully achieving stitching without visible seams or errors, providing efficient and reliable technical support for bridge panorama generation. The research outcomes demonstrate significant practical value in bridge inspection, providing robust technical support for safe and efficient bridge inspection. Moreover, our findings offer valuable references for future research and applications in related fields.