• Geotechnical Engineering
• /
• v.10 no.4
• /
• pp.17-28
• /
• 1994

It is well known that human brain has the advantage of handling disperse and parallel distributed data efficiently. On the basic of this fact, artificial neural networks theory was developed and has been applied to various fields of science successfully. In this study, error back propagation algorithm which is one of the teaching technique of artificial neural networks is applied to predict ultimate bearing capacity of pile foundations. For the verification of applicability of this system, a total of 28 data of model pile test results are used. The 9, 14 and 21 test data respectively out of the total 28 data are used for training the networks, and the others are used for the comparison between the predicted and the measured. The results show that the developed system can provide a good matching with model pile test results by training with data more than 14. These limited results show the possibility of utilizing the neural networks for pile capacity prediction problems.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.629-635
• /
• 2019

In Deep Learning models derivative is implemented by error back-propagation which enables the model to learn the error and update parameters. It can find the global (or local) optimal points of parameters even in the complex models taking advantage of a huge improvement in computing power. However, deliberately generated data points can 'fool' models and degrade the performance such as prediction accuracy. Not only these adversarial examples reduce the performance but also these examples are not easily detectable with human's eyes. In this work, we propose the method to detect adversarial datasets with random noise addition. We exploit the fact that when random noise is added, prediction accuracy of non-adversarial dataset remains almost unchanged, but that of adversarial dataset changes. We set attack methods (FGSM, Saliency Map) and noise level (0-19 with max pixel value 255) as independent variables and difference of prediction accuracy when noise was added as dependent variable in a simulation experiment. We have succeeded in extracting the threshold that separates non-adversarial and adversarial dataset. We detected the adversarial dataset using this threshold.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.6
• /
• pp.839-850
• /
• 2018

The flood damage in urban areas due to torrential rain is increasing with urbanization. For this reason, accurate and rapid flooding forecasting and expected inundation maps are needed. Predicting the extent of flooding for certain rainfalls is a very important issue in preparing flood in advance. Recently, government agencies are trying to provide expected inundation maps to the public. However, there is a lack of quantifying the extent of inundation caused by a particular rainfall scenario and the real-time prediction method for flood extent within a short time. Therefore the real-time prediction of flood extent is needed based on rainfall-runoff-inundation analysis. One/two dimensional model are continued to analyize drainage network, manhole overflow and inundation propagation by rainfall condition. By applying the various rainfall scenarios considering rainfall duration/distribution and return periods, the inundation volume and depth can be estimated and stored on a database. The Rainfall-Duration-Flooding Quantity (RDF) relationship curve based on the hydraulic analysis results and the Self-Organizing Map (SOM) that conducts unsupervised learning are applied to predict flooded area with particular rainfall condition. The validity of the proposed methodology was examined by comparing the results of the expected flood map with the 2-dimensional hydraulic model. Based on the result of the study, it is judged that this methodology will be useful to provide an unknown flood map according to medium-sized rainfall or frequency scenario. Furthermore, it will be used as a fundamental data for flood forecast by establishing the RDF curve which the relationship of rainfall-outflow-flood is considered and the database of expected inundation maps.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.5 no.1 s.9
• /
• pp.1-12
• /
• 2006

In order to estimate a dynamic origin and destination demand between on and off-ramps in the freeways, a traffic flow theory can be used to calculate a link distribution proportion of traffics moving between them. We have developed a dynamic traffic estimation model based on the three-phase traffic theory (Kerner, 2004), which explains the complexity of traffic phenomena based on phase transitions among free-flow, synchronized flow and moving jam phases, and on their complex nonlinear spatiotemporal features. The developed model explains and estimates traffic congestion in terms of speed breakdown, phase transition and queue propagation. We have estimated the link, on and off-ramp volumes at every time interval by using traffic data collected from vehicle detection systems in Korea freeway sections. The analyzed results show that the developed model describes traffic flows adequately.

• Journal of Korea Water Resources Association
• /
• v.51 no.11
• /
• pp.1021-1029
• /
• 2018

A primary objective of this study is to develop a drought forecasting technique based on groundwater which can be exploit for water supply under drought stress. For this purpose, we explored the lagged relationships between regionalized SGI (standardized groundwater level index) and SPI (standardized precipitation index) in view of the drought propagation. A regional prediction model was constructed using a NARX (nonlinear autoregressive exogenous) artificial neural network model which can effectively capture nonlinear relationships with the lagged independent variable. During the training phase, model performance in terms of correlation coefficient was found to be satisfactory with the correlation coefficient over 0.7. Moreover, the model performance was described by root mean squared error (RMSE). It can be concluded that the proposed approach is able to provide a reliable SGI forecasts along with rainfall forecasts provided by the Korea Meteorological Administration.

• Journal of Mechanical Science and Technology
• /
• v.20 no.12
• /
• pp.2292-2314
• /
• 2006

Efficient numerical method is developed for the prediction of aerodynamic noise generation and propagation in low Mach number flows such as aeolian tone noise. The proposed numerical method is based on acoustic/viscous splitting techniques of which acoustic solvers use simplified linearised Euler equations, full linearised Euler equations and nonlinear perturbation equations as acoustic governing equations. All of acoustic equations are forced with immersed surface dipole model which is developed for the efficient computation of aerodynamic noise generation and propagation in low Mach number flows in which dipole source, originating from unsteady pressure fluctuation on a solid surface, is known to be more efficient than quadrupole sources. Multi-scale overset grid technique is also utilized to resolve the complex geometries. Initially, aeolian tone from single cylinder is considered to examine the effects that the immersed surface dipole models combined with the different acoustic governing equations have on the overall accuracy of the method. Then, the current numerical method is applied to the simulation of the aeolian tones from twin cylinders aligned perpendicularly to the mean flow and separated 3 diameters between their centers. In this configuration, symmetric vortices are shed from twin cylinders, which leads to the anti-phase of the lift dipoles and the in-phase of the drag dipoles. Due to these phase differences, the directivity of the fluctuating pressure from the lift dipoles shows the comparable magnitude with that from the drag dipoles at 10 diameters apart from the origin. However, the directivity at 100 diameters shows that the lift-dipole originated noise has larger magnitude than, but still comparable to, that of the drag-dipole one. Comparison of the numerical results with and without mean flow effects on the acoustic wave emphasizes the effects of the sheared background flows around the cylinders on the propagating acoustic waves, which is not generally considered by the classic acoustic analogy methods. Through the comparison of the results using the immersed surface dipole models with those using point sources, it is demonstrated that the current methods can allow for the complex interactions between the acoustic wave and the solid wall and the effects of the mean flow on the acoustic waves.

• Korean Chemical Engineering Research
• /
• v.62 no.1
• /
• pp.27-35
• /
• 2024

Fuel gases such as methane and propane are used in explosion hazardous area of domestic plants and can form non-uniform mixtures with the influence of process conditions due to leakage. The fire-explosion risk assessment using literature data measured under uniform mixtures, damage prediction can be obtained the different results from actual explosion accidents by gas leaks. An explosion characteristics such as explosion pressure and flame velocity of non-uniform gas mixtures with concentration change similar to that of facility leak were examined. The experiments were conducted in a closed 0.82 m long stainless steel duct with observation recorded by color high speed camera and piezo pressure sensor. Also we proposed the quantification method of non-uniform mixtures from a regression analysis model on the change of concentration difference with time in explosion duct. For the non-uniform condition of this study, the area of flame surface enlarged with increasing the concentration non-uniform in the flame propagation of methane and was similar to the wrinkled flame structure existing in a turbulent flame. The time to peak pressure of methane decreased as the non-uniform increased and the explosion pressure increased with increasing the non-uniform. The ranges of K_G (Deflagration index) of methane with the concentration non-uniform were 1.30 to 1.58 [MPa·m/s] and the increase rate of K_G was 17.7% in methane with changing from uniform to non-uniform.

• Explosives and Blasting
• /
• v.14 no.4
• /
• pp.13-19
• /
• 1996

Lately, the improtance of smooth blasting is increasing on every construction fields, suchas underground caves, tunnels, and roadconstruction, etc. The main purpose of smooth blasting is to prevent unnecessary cracks from the base rockwhich preserved permanently and is to gain the smooth fracture plane. So, in smooth blashing, explosives with low detonating velocity are generally used. But it is difficult to discuss general theory on the smooth blashing because the mechanical properties of pertienent rocks are difficult regionally. Accordingly basic reserches on the smooth blasting are demended. In this paper, the mechanisms of the smooth blasting on the rocks containing discontinuities were discussd. Firstly, the writer predicted the formation of fracture plane and unevenness using mathematical methodology, the next the model blast tests were conducted in order to simulate the crack propagation modes from the blast holes. Through the research, the following conclusions were obtained l)The blast test results were in reasonally good agreement with the theoretical prediction. 2)The degree of discontinuity has an influence on the fracture morphology.

• Journal of the Korean Geotechnical Society
• /
• v.20 no.5
• /
• pp.17-25
• /
• 2004

The flat dilatometer test (DMT) is a geotechnical tool to estimate in-situ properties of various types of ground materials. The undrained shear strength is known to be the most reliable and useful parameter obtained by DMT. However, the existing relationships which were established for other local deposits depend on the regional geotechnical characteristics. In addition, the flat dilatometer test results have been interpreted using three intermediate indices - material index $(I_D)$, horizontal stress index $(K_D)$, and dilatometer modulus (E$_{D}$) and the undrained shear strength has been estimated merely using the horizontal stress index $(K_D)$. In this paper, the applicability of the flat dilatometer to Korean soft clay deposit has been investigated. Then an artificial neural network was developed to evaluate the undrained shear strength by DMT and the ANN, based on the $p_0, p_1, p_2, {\sigma '}_v$ and porewater pressure. The ANN which adopts the back-propagation algorithm was trained based on the DMT data obtained from Korean soft clay. To investigate the feasibility of ANN model, the prediction results obtained from data which were not used to train the ANN and those obtained from existing relationships were compared.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2004.03b
• /
• pp.154-161
• /
• 2004

The flat dilatometer test(DMT) is a geotechnical tool to estimate in-situ properties of various types of ground materials. The undrained shear strength is known to be the most reliable and useful parameter obtained by DMT. However, the existing relationships which were established for other local deposits depend on the regional geotechnical characteristics. In addition, the flat dilatometer test results have been interpreted using three intermediate indicesmaterial index($I_p$), horizontal stres index($K_p$), and dilatometer modulus($E_p$) and the undrained shear strength is estimated only by using the horizontal stress index($K_D$). In this paper, an artificial neural network was developed to evaluate the undrained shear strength by DMT and the ANN, based on the $p_0,\;p_1,\;p_2,\;{\sigma}'_v_0$, and porewater pressure. The ANN which adopts the back-propagation algorithm was trained based on the DMT data obtained from Korean soft clay. To investigate the feasibility of ANN model, the prediction results obtained from data which were not used to train the ANN and those obtained from existing relationships were compared.