The damage investigation and inspection methods for infrastructures performed in small-scale (type III) facilities usually involve a visual examination by an inspector using surveying tools (e.g., cracking, crack microscope, etc.) in the field. These methods can interfere with the subjectivity of the inspector, which may reduce the objectivity and reliability of the record. Therefore, a new image analysis technique is needed to automatically detect cracks and analyze the characteristics of the cracks objectively. In this study, an image analysis technique using deep learning is developed to detect cracks and analyze characteristics (e.g., length, and width) in images for small-scale facilities. Three stages of image processing pipeline are proposed to obtain crack detection and its characteristics. In the first and second stages, two-dimensional convolutional neural networks are used for crack image detection (e.g., classification and segmentation). Based on convolution neural network for the detection, hierarchical feature learning architecture is applied into our deep learning network. After deep learning-based detection, in the third stage, thinning and tracking algorithms are applied to analyze length and width of crack in the image. The performance of the proposed method was tested using various crack images with label and the results showed good performance of crack detection and its measurement.

Methane hydrate has attracted attention as a next-generation resource, and many researchers have conducted various studies to estimate its productivity. Numerical simulation is the optimal method for estimating methane gas productivity. Meanwhile, using a reasonable input parameter is essential for obtaining accurate numerical modeling results. Permeability is a geotechnical property that exhibits the greatest impact on productivity. The permeability of hydrate-bearing sediment varies based on the sediment pore structure and hydrate saturation. In this study, an empirical permeability model was derived from experimental data using soil specimens from the Ulleung Basin, and the model was applied in numerical analysis to evaluate the sediment gas productivity and ground stability. The gas productivity and stability of hydrate-bearing sediments were compared by applying a widely used permeability model and the proposed model to a numerical model. Additionally, a parametric study was performed to examine the effects of initial hydrate saturation on the sediment gas productivity and stability. There were significant differences in the productivity and stability analysis results according to the proposed permeability model. Therefore, it was found that for accurate numerical analysis, a regional permeability model should be applied.

Gas hydrates have great potential as future energy resources. Several productivity and stability analyses have been conducted for the Ulleung Basin, and the depressurization method is being considered for production. Under depressurization, ground settlement occurs near the wellbore and axial stress develops. For a safe production test, it is essential to perform a stability analysis for the wellbore and hydrate-bearing sediments. In this study, the development of axial stress on the wellbore was investigated considering the coupling stiffness of the interface between the wellbore and sediment. A coupling stiffness model, which can consider both confining stress and slippage phenomena, was suggested and applied in a numerical simulation. Parametric analyses were conducted to investigate the effects of coupling stiffness and slippage on axial stress development. The results show that shear coupling stiffness has a significant effect on wellbore stability, while normal coupling stiffness has a minor effect. In addition, the maximum axial stress of the well bore has an upper limit depending on the magnitude of the confining stress, and the axial stress converges to this upper limit due to slipping at the interface. The results can be used as fundamental data for the design of wellbore under depressurization-based gas production.

The development of underground spaces in urban centers has attracted significant research attention. Typical excavation methods for underground spaces in urban areas include the New Austrian tunneling method (NATM) and the tunnel boring machine (TBM). The NATM is superior in terms of ease of construction and economic efficiency; however, vibration and noise are often cited as major complaints. In addition to their high initial cost, TBMs require intricate analyses of ground conditions during excavation. To overcome the disadvantages of both methods and reduce construction time, a TBM and NATM parallel excavation method has recently been investigated. In this study, the effects of blasting vibrations on the TBM, TBM backup device, and surrounding ground were examined during an NATM application for rear expansion blasting after pilot tunnel excavation using a TBM. Different rock types and powder factors were simulated, and differences in the vibration velocity according to their variations were predicted using 3D numerical analysis.