• Journal of the Society of Disaster Information
• /
• v.3 no.1
• /
• pp.37-53
• /
• 2007

Various difficult problems occur due to insufficient bearing capacity or excessive settlements when constructing roads or large complexes. Accurate predictions on the final settlement and consolidation time can help in choosing the ground improvement method and thus enables to save time and expense of the whole project. Asaoka's method is probably the most frequently used for settlement prediction which are based on Terzaghi's one dimensional consolidation theory. Empirical formulae such as Hyperbolic method and Hoshino's method are also often used. However, it is known that the settlement predicted by these methods do not match with the actual settlements. Furthermore these methods cannot be used at design stage when there is no measured data. To find an elaborate method in predicting settlement in embankments using various test results and actual settlement data from domestic sites, Back-Propagation Neural Network(BPNN) and Recurrent Neural Network(RNN) were employed and the most suitable model structures were obtained. Predicted settlement values by the developed models were compared with the measured values as well as numerical analysis results. Analysis of the results showed that RNN yielded more compatible predictions with actual data than BPNN and predictions using cone penetration resistance were closer to actual data than predictions using SPT results. Also, it was found that the developed method were very competitive with the numerical analysis considering the number of input data, complexity and effort in modelling. It is believed that RNN using cone penetration test results can make a highly efficient tool in predicting settlements if enough field data can be obtained.

• Journal of the Korea Concrete Institute
• /
• v.18 no.4 s.94
• /
• pp.469-477
• /
• 2006

Models to predict the ultimate strength of simply supported or continuous deep beams with web openings are proposed. The derived equations are based on upper-bound theorem. The concrete is assumed as a perfectly plastic material obeying the modified Coulomb failure criteria with zero tension cutoff. Reinforcing bar is considered as elastic-perfectly plastic material and its stress is calculated from the limiting principal compressive strain of concrete. The governing failure mechanisms based on test results are idealized as rigid moving blocks separated by a hyperbolic yield line. The effective compressive strength of concrete is calculated from the formula proposed by Vecchio and Collins. Comparisons with existing test results are performed, and they show good agreement.

• Journal of the Korea Convergence Society
• /
• v.9 no.5
• /
• pp.33-41
• /
• 2018

The purpose of this study is to develop more accurate and robust emotion prediction neural network (EPNN) model by combining heart rate variability (HRV) and neural network. For the sake of improving the prediction performance more reliably, the proposed EPNN model is based on various types of activation functions like hyperbolic tangent, linear, and Gaussian functions, all of which are embedded in hidden nodes to improve its performance. In order to verify the validity of the proposed EPNN model, a number of HRV metrics were calculated from 20 valid and qualified participants whose emotions were induced by using money game. To add more rigor to the experiment, the participants' valence and arousal were checked and used as output node of the EPNN. The experiment results reveal that the F-Measure for Valence and Arousal is 80% and 95%, respectively, proving that the EPNN yields very robust and well-balanced performance. The EPNN performance was compared with competing models like neural network, logistic regression, support vector machine, and random forest. The EPNN was more accurate and reliable than those of the competing models. The results of this study can be effectively applied to many types of wearable computing devices when ubiquitous digital health environment becomes feasible and permeating into our everyday lives.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.2C
• /
• pp.71-79
• /
• 2009

This study is to develope the resilient modulus prediction model, which is the function of mean effective principal stress and axial strain, for three types of railroad trackbed materials such as crushed stone, weathered granite soil, and crushed-rock soil mixture. The model consists of the maximum Young's modulus and nonlinear values for higher strain, analogous to dynamic shear modulus. The maximum value is modeled by model parameters, $A_E$ and the power of mean effective principal stress, $n_E$. The nonlinear portion is represented by modified hyperbolic model, with the model parameters of reference strain, ${\varepsilon}_r$ and curvature coefficient, a. To assess the performance of the prediction models proposed herein, the elastic response of a test trackbed near PyeongTaek, Korea, was evaluated using a 3-D elastic multilayer computer program (GEOTRACK). The results were compared with measured elastic vertical displacement during the passages of freight and passenger trains at two locations, whose sub-ballasts were crushed stone and weathered granite soil, respectively. The calculated vertical displacements of the sub-ballasts are within the order of 0.6mm, and agree well with measured values. The prediction models are thus concluded to work properly in the preliminary investigation.

• Wind and Structures
• /
• v.27 no.1
• /
• pp.11-27
• /
• 2018

The straight-cone steel cooling tower is a novel type of structure, which has a distinct aerodynamic distribution on the internal surface of the tower cylinder compared with conventional hyperbolic concrete cooling towers. Especially in the extreme weather conditions of strong wind and heavy rain, heavy rain also has a direct impact on aerodynamic force on the internal surface and changes the turbulence effect of pulsating wind, but existing studies mainly focus on the impact effect brought by wind-driven rain to structure surface. In addition, for the indirect air cooled cooling tower, different additional ventilation rate of shutters produces a considerable interference to air movement inside the tower and also to the action mechanism of loads. To solve the problem, a straight-cone steel cooling towerstanding 189 m high and currently being constructed is taken as the research object in this study. The algorithm for two-way coupling between wind and rain is adopted. Simulation of wind field and raindrops is performed with continuous phase and discrete phase models, respectively, under the general principles of computational fluid dynamics (CFD). Firstly, the rule of influence of 9 combinations of wind sped and rainfall intensity on flow field mechanism, the volume of wind-driven rain, additional action force of raindrops and equivalent internal pressure coefficient of the tower cylinder is analyzed. On this basis, the internal pressures of the cooling tower under the most unfavorable working condition are compared between four ventilation rates of shutters (0%, 15%, 30% and 100%). The results show that the 3D effect of equivalent internal pressure coefficient is the most significant when considering two-way coupling between wind and rain. Additional load imposed by raindrops on the internal surface of the tower accounts for an extremely small proportion of total wind load, the maximum being only 0.245%. This occurs under the combination of 20 m/s wind velocity and 200 mm/h rainfall intensity. Ventilation rate of shutters not only changes the air movement inside the tower, but also affects the accumulated amount and distribution of raindrops on the internal surface.

• Journal of the Korean Geotechnical Society
• /
• v.23 no.7
• /
• pp.17-25
• /
• 2007

Various geotechnical problems due to insufficient bearing capacity or excessive settlement are likely to occur when constructing roads or large complexes on soft ground. Accurate predictions of the magnitude of settlement and the consolidation time provide numerous options of ground improvement methods and, thus, enable to save time and expense of the whole project. Asaoka's method is probably the most frequently used one for settlement prediction and the empirical formulae such as Hyperbolic method and Hoshino's method are also often used. To find an elaborate method of predicting the embankment settlement, two recurrent type neural network models, such as Jordan model and Elman-Jordan model, are adopted. The data sets of settlement measured at several domestic sites are analyzed to obtain the most suitable model structures. It was shown from the comparison between predicted and measured settlements that Jordan model provides better predictions than Elman-Jordan model does and that the predictions using CPT results are more accurate than those using SPT results. It is believed that RNN using cone penetration test results can be a highly efficient tool in predicting settlements if enough field data can be obtained.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1143-1154
• /
• 2021

The selection of activation function has a great influence on the groundwater level prediction performance of artificial neural network (ANN) model. In this study, five activation functions were applied to ANN model for two groundwater level observation wells in the middle mountainous area of the Pyoseon watershed in Jeju Island. The results of the prediction of the groundwater level were compared and analyzed, and the optimal activation function was derived. In addition, the results of LSTM model, which is a widely used recurrent neural network model, were compared and analyzed with the results of the ANN models with each activation function. As a result, ELU and Leaky ReLU functions were derived as the optimal activation functions for the prediction of the groundwater level for observation well with relatively large fluctuations in groundwater level and for observation well with relatively small fluctuations, respectively. On the other hand, sigmoid function had the lowest predictive performance among the five activation functions for training period, and produced inappropriate results in peak and lowest groundwater level prediction. The ANN-ELU and ANN-Leaky ReLU models showed groundwater level prediction performance comparable to that of the LSTM model, and thus had sufficient potential for application. The methods and results of this study can be usefully used in other studies.

• Journal of the Korean Geotechnical Society
• /
• v.39 no.5
• /
• pp.51-63
• /
• 2023

Numerical analysis was conducted to determine the effect of soil behavior by thawing and freezing of seasonal frozen soil on pile foundations. The analysis was performed using the finite element method (FEM) to simulate soil-pile interaction based on the atmosphere temperature change. Thermomechanical coupled modeling using FEM was applied with the temperature-dependent nonlinear properties of the frozen soil. The analysis model cases were applied to the MCR and HDP models to simulate the elastoplastic behavior of soil. The numerical analysis results were analyzed and compared with various conditions having different length and width sizes of the pile. The results of the numerical analysis showed t hat t he HDP model was relat ively passive, and t he aspect and magnit ude of t he bearing capacit y and displacement of the pile head were similar depending on the length and width of the pile conditions. The vertical displacement of the pile head by thawing and freezing of the ground showed a large variation in displacement for shorter length conditions. In the MCR model, the vertical displacement appeared in the maximum thaw settlement and frost heaving of 0.0387 and 0.0277 m, respectively. In the HDP model, the vertical displacement appeared in the maximum thaw settlement and frost heaving of 0.0367 and 0.0264 m, respectively. The results of the pile bearing capacity for the two elastoplastic models showed a larger difference in the width condition than the length condition of the pile, with a maximum of about 14.7% for the width L condition, a maximum of about 5.4% for M condition, and a maximum of about 5.3% for S condition. The significance of the effect on the displacement of the pile head and the bearing capacity depended on the pile-soil contact area, and the difference depended on the presence or absence of an active layer in the soil and its thickness.