In recent years, artificial intelligence (AI) has been adopted in various fields, not only in the industrial scene. In this study, a deep neural network (DNN) was applied to evaluate a mountain tunnel’s rock mass. The input was a photo of the excavation surface (face) of the mountain tunnel, and the output was the rock mass properties such as degree of weathering, alteration, and fracture. Based on past excavation records, the DNN was tested using supervised learning, and the results showed that the AI judgments were consistent with the engineers’ judgments, having a 73%-97% accurate answer rate. Therefore, practically applying the method of rock mass evaluation using AI was determined as being feasible. Furthermore, to allow ease in its field-based application, a cloud computer system using a tablet computer device was used to enable evaluations, creating a system that contributed to increased productivity.

View full abstract

The loosened zone around the tunnel and underground caverns comprises the physical damaged and stress concentrated zones. Therefore, Young's modulus and stress should be measured to determine the loosened zone. However, the values of Young's moduli of rock mass measured in situ vary widely owing to the anisotropy of the rock mass. In addition, the measurement of rock stress using current domestic methods is expensive owing to the use of special techniques and equipment. Thus, this paper presents a simple technique to measure and analyze anisotropic Young's moduli and rock stress simultaneously using a borehole jack test.

View full abstract

This article is a summary of the paper already published in the “Rock Mechanics and Rock Engineering” (Goto et al., 2021). Superhot geothermal environments exceeding 400 ºC at depths of ~2-4 km are seen as a geothermal frontier. However, there are concerns that the network of permeable fracture is possibly absent in a continental granitic crust because thermally relevant factors which can be impair the formation of the permeable fracture network. Hydraulic fracturing is a hopeful technique to exploit the geothermal energy from such environments via establishing a superhot enhanced geothermal system. Our previous study already revealed that a dense network of permeable fractures, referred to as a cloud-fracture networks, possibly formed by superhot hydraulic fracturing. Although the formation cloud-fracture network is seemed to be caused by the infiltration of low-viscosity water into preexisting microfractures according to our previous study. However, the detailed formation process of cloud-fracture network and the plausible criterion for cloud-fracture network formation is yet to be clarified. The applicability of the Griffith failure criterion is supported by hydraulic fracturing experiments with acoustic emission measurements of granite at 400 ºC under true triaxial stress and at 450 ºC under conventional triaxial stress. The present study provides, for the first time, a theoretical basis required to establish the procedure for hydraulic fracturing in the superhot EGS.

View full abstract

Large groundwater flow into the tunnel during construction of a tunnel can cause crucial problems. It is therefore important to investigate the location, flowrate, and hydraulic pressure of the flow paths ahead of the tunnel face in advance to tunnel excavations. One of the effective ways to characterize the flow paths is measurement of flowrate and pressure in the advanced horizontal boreholes using a packer system. However, with the conventional method, it is often difficult to carry out the installation of packer systems due to the risks of borehole collapse and delay in the construction schedule caused by pulling out the drilling string before packer installation. Therefore, the authors have developed a new measurement system that can be installed packer without pulling out the drilling tools. This paper describes the concept of this system, and a result of its successful application to a tunnel construction site.

View full abstract