• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.2
• /
• pp.217-230
• /
• 2022

The adequate control of TBM face pressure is of vital importance to maintain face stability by preventing face collapse and surface settlement. An EPB shield TBM excavates the ground by applying face pressure with the excavated soil in the pressure chamber. One of the challenges during the EPB shield TBM operation is the control of face pressure due to difficulty in managing the excavated soil. In this study, the face pressure of an EPB shield TBM was predicted using the geological and operational data acquired from a domestic TBM tunnel site. Four machine learning algorithms: KNN (K-Nearest Neighbors), SVM (Support Vector Machine), RF (Random Forest), and XGB (eXtreme Gradient Boosting) were applied to predict the face pressure. The model comparison results showed that the RF model yielded the lowest RMSE (Root Mean Square Error) value of 7.35 kPa. Therefore, the RF model was selected as the optimal machine learning algorithm. In addition, the feature importance of the RF model was analyzed to evaluate appropriately the influence of each feature on the face pressure. The water pressure indicated the highest influence, and the importance of the geological conditions was higher in general than that of the operation features in the considered site.

• The Journal of Engineering Geology
• /
• v.27 no.3
• /
• pp.217-231
• /
• 2017

The subsidence of ground in urban area can be caused by the occurrence of the cavity and the change in ground volumetric water content. The objective of this study is the detection of abnormal area of ground in urban area where the cavity or the change in ground volumetric water content is occurred by the ground penetrating radar signal. GPR survey is carried out on the test bed with a circular buried object. From the GPR survey, the signals filtered by the bandpass filtering are measured, and the methods consisting of gain function, time zero, background removal, deconvolution and display gain are applied to the filtered signals. As a result of application of the signal processing methods, the polarity of signal corresponds with the relation of electrical impedance of the cavity and the ground in test bed. In addition, the relative permittivity calculated by GPR signal is compared with that of predicted by volumetric water content of the test bed. The relative permittivities obtained from two different methods show similar values. Therefore, the abnormal area where the change in ground volumetric water content is occurred can be detected from the results of the GPR survey in case the depth of underground utilities is known. Signal processing methods and estimation of relative permittivity performed in this study may be effectively used to detect the abnormal area of ground in urban area.

• Journal of the Korean GEO-environmental Society
• /
• v.2 no.3
• /
• pp.47-56
• /
• 2001

In the present study, mainly to determine the embarkation time of equipment in dredged clay fills, an analytical approach is performed to predict a variation of the undrained shear strength in the outermost layer. In this approach, Gibson's non-dimensional linear constant defining the relationship between the void ratio and the effective stress is employed. Also in this approach, void ratios and settlements associated with the volume change due to the self-consolidation and the desiccation shrinkage are evaluated at various elapsed times based on the finite difference solution technique proposed by the authors(1999) and the developed computer program named as DSCON. Predicted results(water content ratio, unit weight and undrained shear strength) are compared with those of laboratory model tests conducted with soil samples obtained from the Koheung site. Based on the predicted undrained shear strengths, possible embarkation time of a equipment is also evaluated. In addition, further analyses are made to indirectly verify the efficiency of the analytical approach proposed in the present study using the PSDDF computer program which can consider the drainage efficiency.

• Journal of the Korean Geotechnical Society
• /
• v.36 no.7
• /
• pp.5-14
• /
• 2020

Kansai International Airport (KIX) was opened in September 1994. Although 26 years have passed since the completion of the first island, long-term settlement is still in progress. This settlement occurs in the Pleistocene layer. For it is not easy to determine the permeability of the Pleistocene sand layer because the thickness and the degree of fine content in the horizontal direction are constantly changing. In addition, it is also a difficult to predict the interactive behavior of the ground due to the construction of the second phase island adjacent to it. In order to solve this problem, a two-dimensional finite element analysis considering elasto-viscoplastic was performed to evaluate the long-term deformation, including the interactive behavior of the alternating Pleistocene foundation due to the construction of two adjacent reclaimed islands. In general, two-dimensional analysis can be used when a section can represent the entire sections. However, Kansai Airport is an artificial reclaimed island so two-dimensional analysis cannot solve the problem such as the stress deformation in the corners of the island. Additionally, the structure of the actual sub-ground through physical exploration is non-homogeneity and its thickness is also not constant. Therefore, there are limitations for the two-dimensional analysis to explain the phenomena. That is, three-dimensional analysis is strongly required. Due to these demands, the author extended the existing two-dimensional program capable of elasto-viscoplastic analysis to three-dimensional and completed the verification of the three-dimensional program developed through one-dimensional consolidation analysis. In order to demonstrate the validity of the developed 3D program that has been verified, an analysis is performed under the same analysis conditions as the existing research using a two-dimensional program. The effectiveness of the developed 3D numerical analysis program was demonstrated by comparing the analysis results with the 2D results and actual measurement data.

• Journal of the Korean Geotechnical Society
• /
• v.24 no.10
• /
• pp.45-55
• /
• 2008

In this study, the in-situ model test has been conducted to estimate and analyze consolidation behavior of the ground by using the miniature test that reconstructs economically geotechnical behavior of in-situ full scale structure. To analyze the relation of effective stress, void ratio and coefficient of permeability at the self-weight consolidation stage, the low stress seepage consolidation test has been conducted and the involution function of constitutive equation had been obtained from the result of the curve fitted seepage consolidation test. As a result of the numerical analysis that had been conducted on the representative section using a constitute equation, final settlement was similar to those of self-weight consolidation of the centrifugal model test. But it was more or less smaller. It seems that these trends are caused by the difference between estimated values.

• Geotechnical Engineering
• /
• v.14 no.3
• /
• pp.73-94
• /
• 1998

In the present study, a method of the three-dimensional limit equilibrium stability analysis of shape of the potential failure wedge for the concave-shaped excavation corner is assumed on the basis of the results of the FLACSU program analysis. Estimation of the three-dimensional seepage forces expected to act on the failure wedge is made by solving the three-dimensional continuity equation of flow with appropriate boundary conditions. By using the proposed method of three-dimensional stability analysis of the concave-shaped excavation corner, a parametric study is performed to examine the reinforcement effect of skew soil nailing system, range of the efficient skew angles and seepage effect on the overall stability. Also examined is the effect of an existence of the right-angled excavation corner on three-dimensional deflection behaviors of the convex-shaped skew soil nailing walls. The results of analyses of the convexshaped excavation corner with skew soil nailing system is further included to illustrate the effects of various design parameters for typical patterns of skew nails reinforcement system.

• Journal of the Korean Geotechnical Society
• /
• v.20 no.7
• /
• pp.69-78
• /
• 2004

In this study, the back analysis program was developed by applying the genetic algorithm, one of artificial intelligence fields, to the direct method. The optimization process which has influence on the efficiency of the direct method was modulated with genetic algorithm. On conditions that the displacement computed by forward analysis for a certain rock mass model was the same as the displacement measured at the tunnel section, back analysis was executed to verify the validity of the program. Usefulness of the program was confirmed by comparing relative errors calculated by back analysis, which is carried out under the same rock mass conditions as analysis model of Gens et at (1987), one of back analysis case in the past. We estimated the total displacement occurring by tunnelling with the crown settlement and convergence measured at the working faces in three tunnel sites of Kyungbu Express railway. Those data measured at the working face are used for back analysis as the input data after confidence test. As the results of the back analysis, we comprehended the tendency of tunnel behaviors with comparing the respective deformation characteristics obtained by the measurement at the working face and by back analysis. Also the usefulness and applicability of the back analysis program developed in this study were verified.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.1C
• /
• pp.63-72
• /
• 2006

Due to rapid development of many cities in Korea, many public facilities are required to be built as well as complementary civil structures. Consequently, a number of tunnel constructions are currently carried out throughout the country, and many more tunnels are planned to be constructed in the near future. Tunnel excavation in a city often causes serious damage to above-ground structures and sewer system because of unexpected settlement. In order to prevent the destruction, the tunnel, which bypasses the center of a city, must be specially evaluated for its influence to other structure. In addition, since a slight disturbance of above-ground structure causes numerous public complaints and civil appeals, it must be approached with different method than the mountain tunnels. In this paper, the evaluation method using the Artificial Neural Network (ANN) has been studied. The method begins with an analysis of the minimal sectional area. If its result can be used to approximate the general influence of the whole section, the actual evaluation using ANN will take off. In addition, it also studies the construction management method which reflects the real time soil behavior and environment influence during construction using Geographic Information System (GIS).

• Journal of the Korean Geotechnical Society
• /
• v.23 no.7
• /
• pp.37-46
• /
• 2007

In the practice of preloading method for soft ground improvement, field engineers need information of ground properties, construction works and field monitoring on ground behaviors of the site. So, integrating all these informations into one database can provide more efficient way for managing and utilizing the data for construction management. In this study, integrated system for construction management of ground improvement sites under preloading is developed. The developed system consists of database (DB) and application program. The database contains all collected data in a construction site and processed data in the system with their geographic information. All informations in the database are standardized from the result of data characterization. Application program performs various functions on managing and utilizing information in the database; pre- and post- data processing with graphic visualization of output, spatial data interpolation, and prediction of ground behavior using field measuring data. And by providing integrating informations and predictions over entire project area with comprehensible visual displays, the applicability and effectiveness of the developed system for construction management were confirmed.