With the increasing number of aging buildings across Korea, emerging maintenance technologies have surged. One such technology is the non-contact detection of concrete cracks via thermal images. This study aims to develop a technique that can accurately predict the depth of a crack by analyzing the temperature difference between the crack part and the normal part in the thermal image of the concrete. The research obtained temperature data through thermal imaging experiments and constructed a big data set including outdoor variables such as air temperature, illumination, and humidity that can influence temperature differences. Based on the collected data, the team designed an algorithm for learning and predicting the crack depth using machine learning. Initially, standardized crack specimens were used in experiments, and the big data was updated by specimens similar to actual cracks. Finally, a crack depth prediction technology was implemented using five regression analysis algorithms for approximately 24,000 data points. To confirm the practicality of the development technique, crack simulators with various shapes were added to the study.

In this study, a full-scale test was conducted to analyze the behavior characteristics which are related to roadbed according to steel pipe press-in excavation during construction of underground railway crossing. the value of depth of soil cover that is the most sensitive element gets to increase gradually by 1.0, 1.5, and 2.0(H/D). Then we performed press-in excavation and measured the displacements of roadbed with LVDT. When the depth of soil cover level is 1.0(H/D), the maximum value of 5.2mm were seen at the point of 2mm for pipe press. Also, when depth of soil cover had increased, Uplift decreased more than 3 times in comparison with the one.