Machine learning models often face challenges in bridge inspections, especially in handling complex surface features and overlapping defects that make accurate classification difficult. These challenges are common for image-based monitoring, which has become increasingly popular for inspecting and assessing the structural condition of reinforced concrete bridges with automated possibilities. Despite advances in defect detection using convolutional neural networks (CNNs), although challenges such as overlapping defects, complex surface textures, and data imbalance remain difficult, full fine-tuning of deep learning models helps them better adapt to these conditions by updating all the layers for domain-specific learning. The aim of this study is to demonstrate how effective the fine-tuning of several deep learning architectures for bridge damage classification allows for robust performance and the best utilization value of the methods. Six CNN architectures, ResNet-18, ResNet-50, ResNet-101, ResNeXt-50, ResNeXt-101 and EfficientNet-B3, were fine-tuned using the CODEBRIM dataset. Their performance was evaluated using Precision, Recall, F1 Score, Balanced Accuracy and AUC-ROC metrics to ensure a robust evaluation framework. This indicates that the EfficientNet-B3 and ResNeXt-101 models outperformed the other models and achieved the highest classification accuracy in all the error categories. EfficientNet-B3 showed the best-balanced Precision (0.935) and perfect Recall (1.000) in background classification, indicating its ability to distinguish defect-free areas from structural damage. These results highlight the potential of these models to improve automated bridge inspection systems and thus increase accuracy and efficiency in real-world applications, as well as provide guidance for the selection of methods based on whether accuracy or overall consistency is more important for a specific application.

Qualitative and quantitative assessments evaluate the structural vulnerability of liquid storage tanks. Liquid storage tanks are typically constructed and operated in areas with hard soils to minimize confining influences. However, many of these critical structures are in coastal areas with soft soils. The research conducted in this study entails the utilization of the finite element method accurately model the seismic behavior of a semi-buried concrete tank under various conditions, including changing water levels and soil properties. The study examines fluid–structure and soil–structure interactions through dynamic analyses of the rectangular semi-buried tank and comparing its different parameters. It also identifies sensitive areas where there is a probability of liquid leakage in storage tanks. The modeling is compared with the qualitative evaluation in the Japanese vibration capability diagnosis table. The results show that the tensile stress in the wall adjacent to the expansion joint is greater than the corresponding stress in the wall in all cases. In the dynamic analyses of the soil types, the pressure on the surface increases with increasing water height. A comparison of the quantitative and qualitative evaluation results shows the possible leakage of the tank in soft soil in the expansion joint.