• Journal of the Korean Geotechnical Society
• /
• v.21 no.8
• /
• pp.73-84
• /
• 2005

A three layered neural network model was developed using back propagation algorithm to estimate the UU undrained shear strength of Korean soft soil based on the database of actual undrained shear strengths and piezocone measurements compiled from 8 sites over the Korea. The developed model was validated by comparing model predictions with measured values about new piezocone data, which were not previously employed during development of model. Performance of the neural network model was also compared with conventional empirical methods. It was found that the number of neuron in hidden layer is different for the different combination of transfer functions of neural network models. However, all piezocone neural network models are successful in inferring a complex relationship between piezocone measurements and the undrained shear strength of Korean soft soils, which give relatively high coefficients of determination ranging from 0.69 to 0.72. Since neural network model has been generalized by self-learning from database of piezocone measurements and undrained shear strength over the various sites, the developed neural network models give more precise and generally reliable undrained shear strengths than empirical approaches which still need site specific calibration.

• Journal of the Korean Geotechnical Society
• /
• v.29 no.4
• /
• pp.57-65
• /
• 2013

Assessment of uncertainties of loads and resistances is prerequisite for the development of load and resistance factor design (LRFD). Many previous studies related to resistance factor calculations of piles were conducted for short or medium span bridges (span lengths less than 200m) reflecting the live load uncertainty for ordinary span bridges. In this study, by using a revised live load model and its uncertainty for long span bridges (span lengths longer than 200m and shorter than 1500m), resistance factors are recalibrated. For the estimation of nominal pile capacity (both base and shaft capacities), the Imperial College Pile (ICP) design method is used. For clayey and sandy foundation, uncertainty of resistance is assessed based on the ICP database. As long span bridges are typically considered as more important structures than short or medium span bridges, higher target reliability indices are assigned in the reliability analysis. Finally, resistance factors are calculated and proposed for the use of LRFD of driven piles for ordinary span and long span bridges.

• Journal of the Korean Geotechnical Society
• /
• v.32 no.6
• /
• pp.27-40
• /
• 2016

Conventional warning criteria for landslides due to rainfall in broad regions have limitations, because they did not have proper reflection of topography, forest physiognomy, and unsaturated soil properties, et al. This study suggested a new stability model for unsaturated slope analyses during rainfall, considering rainfall pattern, geomorphological characteristics (slope angle, soil depth), engineering properties of unsaturated soils, and tree surcharge and root reinforcement. Stability analysis not considering root reinforcement and tree surcharge tends to over-predict a factor of safety in unsaturated slopes. Developed slope stability model was used to build database on the factor of safety in unsaturated slopes during rainfall, and it was integrated with GIS to do quantitative risk analysis in landslide risk areas specified in Ulju. Landslide risk areas were located at downstream of the point with sudden drop in safety factor, as well as at regions with low safety factor during rainfall.

• Journal of the Korean Geotechnical Society
• /
• v.30 no.12
• /
• pp.5-14
• /
• 2014

Most of slope failures have taken place between June and September in Korea, which cause a considerable damage to society. Rainfall intensity and duration are very significant triggering factors for landslide. In this paper, landslide-triggering rainfall threshold consisting of rainfall intensity-duration (I-D) was proposed. For this study, total 255 landslides were collected in landslide inventory during 1999 to 2012 from NDMI (National Disaster Management Institute), various reports, newspapers and field survey. And most of the required rainfall data were collected from KMA (Korea Meteorological Administration). The collected landslides were classified into three categories: debris flow, shallow landslide and unconfirmed. A rainfall threshold was proposed based on landslide type using statistical method such as quantile-regression method. Its validation was carried out based on 2013 landslide database. The proposed rainfall threshold was also compared with previous rainfall thresholds. The proposed landslide-triggering rainfall thresholds could be used in landslide early warning system in Korea.

• Geotechnical Engineering
• /
• v.10 no.3
• /
• pp.79-96
• /
• 1994

A tunnel design expert system entitled NESTED is developed using the artificial neural network. The expert system includes three neural network computer models designed for the stability assessment of underground openings and the estimation of correlation between the RMR and Q systems. The expert system consists of the three models and the computerized rock mass classification programs that could be driven under the same user interface. As the structure of the neural network, a multi -layer neural network which adopts an or ror back-propagation learning algorithm is used. To set up its knowledge base from the prior case histories, an engineering database which can control the incomplete and erroneous information by learning process is developed. A series of experiments comparing the results of the neural network with the actual field observations have demonstrated the inferring capabilities of the neural network to identify the possible failure modes and the support timing. The neural network expert system thus complements the incomplete geological data and provides suitable support recommendations for preliminary design of tunnels in rock masses.

• Journal of the Korean Geotechnical Society
• /
• v.19 no.2
• /
• pp.267-278
• /
• 2003

Artificial neural networks are efficient computing techniques that are widely used to solve complex problems in many fields. In this study, in order to predict tunnel-induced ground movements, Tunnel Behavior Prediction System (TBPS) was developed by using these artificial neural networks model, based on a Held instrumentation database (i.e. crown settlement, convergence, axial force of rock bolt, compressive and shear stress of shotcrete, stress of concrete lining etc.) obtained from 193 location data of 31 different tunnel sites where works are completed. The study and test of the network were performed by Back Propagation Algorithm which is known as a systematic technique for studying the multi-layer artificial neural network. The tunnel behaviors predicted by TBPS were compared with monitored data in the tunnel sites and numerical analysis results. This study showed that the values obtained from TBPS were within allowable limits. It is concluded that this system can effectively estimate the tunnel ground movements and can also be used f3r tunneling feasibility study, and basic and detailed design and construction of tunnel.

• Economic and Environmental Geology
• /
• v.43 no.6
• /
• pp.649-659
• /
• 2010

In this study, a tunnel information database system was developed to optimize the process of assessing and analyzing geological information from the life cycle of tunnel construction. All data from every stage in tunnel construction can be put into the system and be utilized for the decision making. In the system, tunnel face mapping information can be managed by digital format which can be easily transformed into 3D visualization module and thus help analyzing geological discontinuities. The system was applied to waterway and road tunnel in domestic area to verify its effectiveness.

• Journal of the Korean Geotechnical Society
• /
• v.39 no.4
• /
• pp.5-17
• /
• 2023

The advancement in large-scale underground excavation in urban areas necessitates monitoring and predicting technologies that can pre-emptively mitigate risk factors at construction sites. Traditionally, two methods predict the deformation of retaining walls induced by excavation: empirical and numerical analysis. Recent progress in artificial intelligence technology has led to the development of a predictive model using machine learning techniques. This study developed a model for predicting the deformation of a retaining wall under construction using a boosting-based algorithm and an ensemble model with outstanding predictive power and efficiency. A database was established using the data from the design-construction-maintenance process of the underground retaining wall project in a manifold manner. Based on these data, a learning model was created, and the performance was evaluated. The boosting and ensemble models demonstrated that wall deformation could be accurately predicted. In addition, it was confirmed that prediction results with the characteristics of the actual construction process can be presented using data collected from ground measurements. The predictive model developed in this study is expected to be used to evaluate and monitor the stability of retaining walls under construction.

• Journal of the Korean Geotechnical Society
• /
• v.25 no.11
• /
• pp.5-15
• /
• 2009

Dynamic shear properties of Nak-Dong river sand were investigated to build a soil property database for Nak-Dong delta region. Samples were taken from the estuary and the midstream of the river. Laboratory specimens were prepared by air pluviation method, and were tested by using RC/TS apparatus at various confining stresses, relative densities and numbers of cycles. Shear modulus reduction and damping curves were developed using Ramberg-Osgood and Modified Hyperbolic Models. The developed curves, compared to those reported by other investigators, show only a slight difference. The outcome of this RC/TS experiments can be very important resources when accessing the dynamic response of sandy soils in Nak-Dong delta region in the future.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2006.03a
• /
• pp.1046-1053
• /
• 2006

In the large scale recent reclaiming works performed within the wide spatial boundary, evaluation of long-term consolidation settlement and residual settlement of the whole construction area is sometimes made with the results of the limited ground investigation and measurement. Then the reliability of evaluation has limitations due to the spatial uncertainty. Additionally, in case of large scale deep excavation works such as urban subway construction, there are a lot of hazardous elements to threaten the safety of underground pipes or adjacent structures. Therefore it is necessary to introduce a damage prediction system of adjacent structures and others. For the more accurate analysis of monitoring information in the wide spatial boundary works and large scale urban deep excavations, it is necessary to perform statistical and spatial analysis considering the geographical spatial effect of ground and monitoring information in stead of using diagrammatization method based on a time-series data expression that is traditionally used. And also it is necessary that enormous ground information and measurement data, digital maps are accumulated in a database, and they are controlled in a integrating system. On the abovementioned point of view, we developed Geomonitor 2.0, an Internet based real time monitoring program with a new concept by adding GIS and geo-statistical analysis method to the existing real time integrated measurement system that is already developed and under useful use. The new program enables the spatial analysis and database of monitoring data and ground information, and helps the construction- related persons make a quick and accurate decision for the economical and safe construction.