A Deep Learning-Based Watershed Feature Fusion Approach for Tunnel Crack Segmentation in Complex Backgrounds.

As highway tunnel operations continue over time, structural defects, particularly cracks, have been observed to increase annually. Coupled with the rapid expansion of tunnel networks, traditional manual inspection methods have proven inadequate to meet current demands. In recent years, machine vision and deep learning technologies have gained significant attention in civil engineering for the detection and analysis of structural defects.

Multi-arch dam safety evaluation based on statistical analysis and numerical simulation.

The Foziling multi-arch dam, one of the few multi-arch dams in the world, was built on the bedrock with complicated geological conditions. It has undergone several reinforcements since it was put into service in the 1950s. In this study, the dam safety is evaluated by analyzing the measured displacements and simulating stresses in the concrete.