• Journal of Korean Tunnelling and Underground Space Association
• /
• v.14 no.4
• /
• pp.357-374
• /
• 2012

Considerable uncertainties are included in ground properties used for tunnel designs due to the limited investigation and tests. In this study, a back analysis was performed to find optimal ground properties based on artificial neural network using both face mapping data and convergence measurement data. First of all, the rock class of a study tunnel is determined from face mapping data. Then the possible ranges of ground properties were selected for each rock class through a literature review on the previous studies and utilized to establish more precise learning data. To find an optimal training model, a sensitivity analysis was also conducted by varying the number of hidden layers and the number of nodes more minutely than the previous study. As a result of this study, more accurate ground properties could be obtained. Therefore it was confirmed that the accuracy of the results could be increased by making use of not only convergence measurement data but also face mapping data in tunnel back analyses using artificial neural network. In future, it is expected that the methodology suggested in this study can be used to estimate ground properties more precisely.

• Proceedings of the Korean Society for Rock Mechanics Conference
• /
• 2003.03a
• /
• pp.1-12
• /
• 2003

지반조사 결과에 의거하여 돌리네와 공동이 존재하는 지역을 구분하여 지역에 적합한 카르스트 형식을 적용, 예측하였다. 특히, 터널이 돌리네 발달 가능성이 적은 백운산 지역을 통과하는 경우에 소규모의 KT-1 ∼ KT-5가 존재하는 것으로 예측되었다. 그러나 설계시 지반조사의 한계성을 인식하고 시공 중에 필요하다고 판단되는 구간에는 막장 전방의 지질상태를 파악할 수 있는 조사를 선 시행하여, 그 결과를 토대로 최종 등급을 결정하여 안전한 시공에 대처할 수 있도록 해야 한다.

• Economic and Environmental Geology
• /
• v.42 no.4
• /
• pp.357-366
• /
• 2009

Since weathering weakens the rock fabric and exaggerates any structural weakness, it affects mechanical properties as well as physical and chemical properties of rock. Weathering leads to a decrease in density, strength, friction angle and cohesion, and subsequently it affects negatively on the stability of rock slope. The purpose of the study is to investigate the changes of the rock slope stability caused by discontinuities which have different weathering grades. For that, the discontinuity samples which are divided into two different weathering grades are obtained from the field and tested their mechanical properties such as JCS, JRC and residual friction angle. In order to evaluate the effects on the stability of slope due to weathering, the deterministic analysis is carried out. That is, the factors of safety for planar failure are calculated for rock masses which have two different weathering grades, such as fresh and weathered rock mass. However, since the JRC and friction angle values are widely scattered and the deterministic analysis cannot consider the variation, the factors of safety cannot represent properly the stability of the rock slope. Therefore, the probabilistic analysis has been used to consider the scattered values. In the deterministic analysis, the factors of safety for the fresh discontinuity and weathered discontinuity are 1.25 and 1.0, respectively. The results indicate the fresh discontinuities are stable for planar failure and the weathered discontinuities are marginally stable. However, the probabilities of failure for the fresh discontinuity and weathered discontinuity are 25.6% and 45.9%, respectively. This shows that both discontinuities are analyzed as unstable in the probabilistic analysis.

• Tunnel and Underground Space
• /
• v.10 no.3
• /
• pp.403-409
• /
• 2000

It is very important to control the final load that acts on a support system, in tunnel engineering. A reliable analysis is needed to carry out technically reasonable design and safe construction. Also, a series of procedures of construction and the rock-support interaction behavior must be considered. Most existing studies have been performed as the limited analysis based on the simplified assumption. In this study, through the analysis of a circular tunnel using a 2-D finite differential code, the rock-support interaction behaviors in the variation of rock and stress conditions are analyzed and compared with the results from the closed form solutions. Consequently, more realistic rock-support interaction curves are obtained by including the effects of initial stresses and rock condition. These curves are very useful to predict the required support pressure in the initial design stage.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.10 no.2
• /
• pp.167-175
• /
• 2008

The construction cost for the single shell tunnel is cheaper than that of the double shell tunnel according to the case studies performed in several domestic and foreign tunnels. However, the economic advantage of single shell tunnel drops drastically as the condition of the rock mass deteriorates. Therefore, the single shell tunnelling method should be applied to the good rock mass conditions. The application of the single shell tunnelling method to tunnels in Korea should be determined considering the ratio between the good rock and poor rock masses along the tunnel section. The use of the single shell tunnel is expected to offend depending on the cheap supply of high quality shotcrets and rock bolts developed for single shell tunnels.

• Proceedings of the KSEEG Conference
• /
• 2007.04a
• /
• pp.296-299
• /
• 2007

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.617-628
• /
• 2022

A ground support pattern should be designed by properly integrating various support materials in accordance with the rock mass grade when constructing a tunnel, and a technical decision must be made in this process by professionals with vast construction experiences. However, designing supports at the early stage of tunnel design, such as feasibility study or basic design, may be very challenging due to the short timeline, insufficient budget, and deficiency of field data. Meanwhile, the design of the support pattern can be performed more quickly and reliably by utilizing the machine learning technique and the accumulated design data with the rapid increase in tunnel construction in South Korea. Therefore, in this study, the design data and ground exploration data of 48 road tunnels in South Korea were inspected, and data about 19 items, including eight input items (rock type, resistivity, depth, tunnel length, safety index by tunnel length, safety index by rick index, tunnel type, tunnel area) and 11 output items (rock mass grade, two items for shotcrete, three items for rock bolt, three items for steel support, two items for concrete lining), were collected to automatically determine the rock mass class and the support pattern. Three machine learning models (S1, A1, A2) were developed using two machine learning algorithms (SVR, ANN) and organized data. As a result, the A2 model, which applied different loss functions according to the output data format, showed the best performance. This study confirms the potential of support pattern design using machine learning, and it is expected that it will be able to improve the design model by continuously using the model in the actual design, compensating for its shortcomings, and improving its usability.

• Journal of the Korean GEO-environmental Society
• /
• v.3 no.3
• /
• pp.5-13
• /
• 2002

In tunnel design, geotechnical survey of over 200m tunnel depth is required because of its characteristical topography. For this reason, there are difficulties in collecting information of basic data in tunnel design because of large-scale costs in borehole tests, of limits to a geotechnical analysis by the existing refraction seismic survey and of analytical errors in steep mountainous area. Seismic tomography has many advantages as follows; 1) seismic velocity as absolute value is more reliable than electrical resistivity, 2) geotechnical analysis in deep tunnel depth is available by seismic velocity, 3) analytical errors is reduced in steep mountainous area. In this paper, it was found out a correlation of seismic velocity and Q in tunnel design in the neighborhood of the National Capital region and the reduction effect of tunnel construction cost using reliable rock quality by seismic tomography compared with by borehole data and electricity resistivity data.

• Tunnel and Underground Space
• /
• v.15 no.6 s.59
• /
• pp.441-451
• /
• 2005

It is the unavoidable problem that the RMR rock classification method has the uncertainty resulted from uncertain definition of measured value in RMR grade table, hence in this paper, the estimation of probability density function$(p{\cdot}d{\cdot}f)$ graph with the evaluation of continuos RMR and the Monte Carlo Simulation and statistic reasoning were carried out to evaluate the uncertainty quantitatively. Also, the modified RMR rock classification table was presented in order to apply the uncertainty of RMR to the practice, and then the design process of standard support pattern and the tunnel support material was proposed.

• Tunnel and Underground Space
• /
• v.21 no.6
• /
• pp.439-449
• /
• 2011

The characteristics of rock fractures for engineering rock classification are investigated by analyzing three dimensional point cloud generated from adjusted digital images of a tunnel face during construction and the tunnel is reinforced based on the supporting pattern suggested by the RMR and the Q system using parameters extracted from those images. As results, it is possible saving time required from face mapping to tunnel reinforcing work, enhancing safety during face mapping work in tunnels and reliability of both the mapping information and selecting supporting pattern by storing the files of digital images and related information which can be checked again, if necessary sometime in the future.