• Geomechanics and Engineering
• /
• v.37 no.4
• /
• pp.307-321
• /
• 2024

This paper delves into the critical assessment of predicting sidewall displacement in underground caverns through the application of nine distinct machine learning techniques. The accurate prediction of sidewall displacement is essential for ensuring the structural safety and stability of underground caverns, which are prone to various geological challenges. The dataset utilized in this study comprises a total of 310 data points, each containing 13 relevant parameters extracted from 10 underground cavern projects located in Iran and other regions. To facilitate a comprehensive evaluation, the dataset is evenly divided into training and testing subset. The study employs a diverse array of machine learning models, including recurrent neural network, back-propagation neural network, K-nearest neighbors, normalized and ordinary radial basis function, support vector machine, weight estimation, feed-forward stepwise regression, and fuzzy inference system. These models are leveraged to develop predictive models that can accurately forecast sidewall displacement in underground caverns. The training phase involves utilizing 80% of the dataset (248 data points) to train the models, while the remaining 20% (62 data points) are used for testing and validation purposes. The findings of the study highlight the back-propagation neural network (BPNN) model as the most effective in providing accurate predictions. The BPNN model demonstrates a remarkably high correlation coefficient (R2 = 0.99) and a low error rate (RMSE = 4.27E-05), indicating its superior performance in predicting sidewall displacement in underground caverns. This research contributes valuable insights into the application of machine learning techniques for enhancing the safety and stability of underground structures.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2005.03a
• /
• pp.1361-1368
• /
• 2005

In this paper, the theoretical method of measuring the tunnel convergence and underground displacement, the objective indices of assessing safety for tunnel construction, using the fiber optic sensor is studied by developing the program to automatically measure them. The model test of Con'c beam is conducted to evaluate reliability of the fiber optic sensor. Furthermore, using the RS232 communication protocol as well as Visual C# and Visual C++, the programming tools, the program was developed to detect automatically the measured value of the fiber optic sensor, calculate the tunnel convergence and underground displacement, predict the deformed shape of the tunnel, and evaluate loosening zone due to the tunnel excavation.

• The Journal of Engineering Geology
• /
• v.33 no.4
• /
• pp.689-699
• /
• 2023

Assessing ground stability is critical to the construction of underground transportation infrastructure. Surface displacement is a key indicator of ground stability, and can be measured using interferometric synthetic aperture radar (InSAR). This study measured time-series surface displacement using permanent scatterer InSAR applied to Sentinel-1 SAR images acquired from January 2017 to June 2023 for the area around a deep underground expressway under construction to connect Mandeok-dong and Centum City in Busan, South Korea. Regions of seasonal subsidence and uplift were identified, as were regions with severe subsidence after summer 2022. To evaluate stability of the ground in the construction area, the mean displacement velocity, final surface displacement, cumulative surface displacement, and difference between minimum and maximum surface displacement were analyzed. Considering the time-series surface displacement characteristics of the study area, the difference between minimum and maximum surface displacement since June 2022 was found to be the most suitable parameter for evaluating ground stability. The results identified highly unstable ground in the construction area as being to the north of the mid-lower reaches of the Oncheon-cheon River and to the west of the Suyeong River at the point where both rivers meet, with the difference between minimum and maximum surface displacement of 40~60 mm.

• Journal of the Korean Geotechnical Society
• /
• v.19 no.4
• /
• pp.211-221
• /
• 2003

The response displacement method is the most frequently used method for seismic design of underground structures. This method is pseudo-static method, and the evaluations of velocity response spectrum of seismic base and response displacement of surrounding soil are the most important steps. In this study, the evaluation of velocity response spectrum of seismic base according to the Korean seismic design guide and the simple method of calculating the response displacement were studied. It was found that velocity response spectrum of seismic base can be estimated by directly integrating the ground-surface acceleration response spectrum of soil type S$_A$, and the evaluation of the response displacement using double cosine method assuming two layers of soil profile shows the advantages in the seismic design.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2009.03a
• /
• pp.634-639
• /
• 2009

The response displacement method is the most frequently used method for the seismic design of underground structures. Underground structures under seismic loading will tend to deform with the surrounding ground, and thus the structure is designed to accommodate the free-field deformation without loss of its structural integrity. This method is pseudo-static method, and response displacement of surrounding ground are most important steps. In this study, the single cosine method and the equivalent linear analysis are applied to estimate the response displacement of the real sites, and the results of the each method are compared. Response analysis was also performed with respect to bedrock depth. As a results, Equivalent linear analysis result was larger than single cosine method. And, the relative displacement becomes lager according to depth of the bedrock.

• Earthquakes and Structures
• /
• v.22 no.3
• /
• pp.277-287
• /
• 2022

The ancient underground cities are a collection of self-supporting spaces that have been manually excavated in the soil or rock in the past. Because these structures have a very high cultural value due to their age, the study of their stability under the influence of natural hazards, such as earthquakes, is very important. In this research, while introducing the underground city of Ouyi Nushabad located in the center of Iran as one of the largest man-made underground cities of the old world, the analysis of dynamic stability is performed. For this purpose, the dynamic stress-displacement analysis has been performed through numerical modeling using the finite element software PLAXIS. At this stage, by simulating the Khorgo earthquake as one of the large-scale earthquakes that occurred in Iran, with a magnitude of 6.9 on the Richter scale, dynamic analysis by time history method has been performed on three selected sections of underground spaces. This study shows that the maximum amount of horizontal and vertical dynamic displacement is 12.9 cm and 17.7 cm, respectively, which was obtained in section 2. The comparison of the results shows that by increasing the cross-sectional area of the excavation, especially the distance between the roof and the floor, in addition to increasing the amount of horizontal and vertical dynamic displacement, the obtained maximum acceleration is intensified compared to the mapping acceleration applied to the model floor. Therefore, preventive actions should be taken to stabilize the excavations in order to prevent damage caused by a possible earthquake.

• Journal of the Korean Geotechnical Society
• /
• v.37 no.12
• /
• pp.7-23
• /
• 2021

Underground utility tunnels, which contribute to supply of electricity, communication, water and heat, are critical lifelines of an urban area. In case service is discontinued or functional disruption happens, there will be a huge socio-economic impact. For the improved seismic design and evaluation of underground structures, this study proposes a ground displacement measure when the site is subjected to a scenario earthquake based on hazard-consistent source spectra and site amplification/attenuation. This measure provides a rational estimation of ground displacement and can be an alternative to existing response displacement methods.

• Geomechanics and Engineering
• /
• v.14 no.6
• /
• pp.589-600
• /
• 2018

For foundations in permafrost regions, the displacement characteristics are uncertain because of the randomness of temperature characteristics and mechanical parameters, which make the structural system have an unexpected deviation and unpredictability. It will affect the safety of design and construction. In this paper, we consider the randomness of temperature characteristics and mechanical parameters. A stochastic analysis model for the uncertain displacement characteristic of foundations is presented, and the stochastic coupling program is compiled by Matrix Laboratory (MATLAB) software. The stochastic displacement fields of an embankment in a permafrost region are obtained and analyzed by Neumann stochastic finite element method (NSFEM). The results provide a new way to predict the deformation characteristics of foundations in permafrost regions, and it shows that the stochastic temperature has a different influence on the stochastic lateral displacement and vertical displacement. Construction disturbance and climate warming lead to three different stages for the mean settlement of characteristic points. For the stochastic settlement characteristic, the standard deviation increases with time, which imply that the results of conventional deterministic analysis may be far from the true value. These results can improve our understanding of the stochastic deformation fields of embankments and provide a theoretical basis for engineering reliability analysis and design in permafrost regions.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.6 no.3
• /
• pp.91-96
• /
• 2002

There are many methods for analyzing underground box structures. One is the method of Iterative removal of tensional spring. The other is the method of modeling of ground to 8-node elastic-plastic planar element. In this study, We use inelastic soil spring element for analyzing underground box structures. First, if N-value is over 50, the results of inelastic soil spring method is the same as the method of 8-node planar element in last stage. Second, as N is increasing, element forces in two methods are generally decreasing. Third, as N-value is increasing, element forces in two method are generally decreasing and displacement has decreasing incline. This is the same as the force-displacement curve of general underground structures.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2002.10a
• /
• pp.65-84
• /
• 2002

The Observational Method proposed by Terzaghi can be applied for the safe and economic construction projects where the exact prediction of the behavior of the structures is difficult as in the underground excavation. The method consists of measuring lateral displacement, ground settlement and axial force of supports in the earlier stage of the construction and back analysis technique to find the best fit design parameters such as earth pressure coefficient, subgrade reaction etc, which will minimize the gap between calculated displacement and measured displacement. With the results, more reliable prediction of the later stage can be obtained. In this study, back analysis programs using the Direct Method, based on the Hill Climbing Method were made and evaluated, and to overcome the limits of the method, Genetic Algorithm(GA) was applied and tested for the actual construction cases.