• Journal of Ocean Engineering and Technology
• /
• v.18 no.1
• /
• pp.41-46
• /
• 2004

This paper describes a study on the tearing damage of a ship's bottom plating, during a grounding. It is widely known that different scaling laws are applied for bodies undergoing simultaneous plastic flow and crack propagation in the deformation of plate tearing. Specifically, the basic scaling law is not followed for the fracture. In this study, in order to verify the problem, plate cutting experiments for geometrically similar models have been performed. From the experimental results, it has been observed that the cutting forces and energy for the larger models are significantly lower than those of the smaller models. A simplified analytical method for the estimation of tearing is proposed, based on the experiments. It has been observed that the results of the present formula are highly correlated with the experiments.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.22 no.6
• /
• pp.649-658
• /
• 2002

As an attempt to further improve the reliability and effectiveness of ultrasonic testing (UT), a two-dimensional numerical simulator of UT was developed. The simulator models the wave medium (or test object) using the mass-spring lattice model (MSLM) that consists of mass-points and springs. Some previous simulation results, obtained by using MSLM, are briefly reviewed in this paper, for propagation, reflection, and scattering of ultrasonic waves. Next, the models of transmitting and receiving piezoelectric transducers are introduced with some numerical results, which is a main focus of this paper. The UT simulator, established by combining the transducer models with the MSLM, was used to simulate many UT setups. In this paper, two simple setups are considered as examples, and their simulated A-scan signals are discussed. The potential of the MSLM, transducer models, and the UT simulator developed in this study to be used in the actual UT is confirmed.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.5
• /
• pp.225-231
• /
• 2023

With the recent surge in the autonomous driving market, the significance of lane detection technology has escalated. Lane detection plays a pivotal role in autonomous driving systems by identifying lanes to ensure safe vehicle operation. Traditional lane detection models rely on engineers manually extracting lane features from predefined environments. However, real-world road conditions present diverse challenges, hampering the engineers' ability to extract adaptable lane features, resulting in limited performance. Consequently, recent research has focused on developing deep learning based lane detection models to extract lane features directly from data. In this paper, we classify lane detection models into four categories: cluster-based, curve-based, information propagation-based, and anchor-based methods. We conduct an extensive analysis of the strengths and weaknesses of each approach, evaluate the model's performance on an embedded board, and assess their practicality and effectiveness. Based on our findings, we propose future research directions and potential enhancements.

• Journal of Korea Water Resources Association
• /
• v.34 no.6
• /
• pp.701-711
• /
• 2001

Forecasting of water quality variation is not an easy process due to the complicated nature of various water quality factors and their interrelationships. The objective of this study is to test the applicability of neural network models to the forecasting of the water quality at Gongju station in Geum River. This is done by forecasting monthly water qualities such as DO, BOD, and TN, and comparing with those obtained by ARIMA model. The neural network models of this study use BP(Back Propagation) algorithm for training. In order to improve the performance of the training, the models are tested in three different styles ; MANN model which uses the Moment-Adaptive learning rate method, LMNN model which uses the Levenberg-Marquardt method, and MNN model which separates the hidden layers for judgement factors from the hidden layers for water quality data. the results show that the forecasted water qualities are reasonably close to the observed data. And the MNN model shows the best results among the three models tested

• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.4
• /
• pp.49-56
• /
• 1997

In mobile communications, it is very important that we predict the propagation environments of radiation pattern, in order to decide the service area, select the best location of the best station, design the cell etc. Therefore, by analyzing the propagation prediction model that is varied according to the kind of antenna, the beam angle, the terrain and obstacles, we expect that the economic operating of communication networks, the calling quality and the service of subscriber will be enhanced. In this paper, we select the around of Seji base station in Naju-city Chonnam for modern suburban area and measure the field strength to propose the optimal propagation prediction model for suburban areas. We propose the propagation prediction model that, it is not found in the other models until now, consists of the correction coefficient with the relative differences of antenna effective height of the base station and mobile station for minimizing errors. Finally, comparing the results of the field test with the computer simulation(PPGIS : Propagation Prediction Geographic Information System) results for the Hata model, the Egri model, the Carey model and the propose model, we confirm the property of the proposed model.

• Journal for History of Mathematics
• /
• v.15 no.3
• /
• pp.59-64
• /
• 2002

This paper investigates a history of Fourier Series for the heat equation and how deeply it is related to modern famous three equations, Navier-Stokes equations in fluid dynamics, drift-diffusion equations in semiconductor, and Black-Scholes equation in finance. We also propose improved models for the heat equation with finite propagation speeds.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2006.07a
• /
• pp.379-379
• /
• 2006

• Geophysics and Geophysical Exploration
• /
• v.6 no.1
• /
• pp.13-22
• /
• 2003

TSP (Tunnel Seismic Profiling) survey is a technique for imaging and characterizing geological structures ahead of a tunnel face. The seismic modeling algorithm and the synthetic data could be helpful for TSP surveys. However, there is few algorithm to describe the propagation of the elastic waves around the tunnel. In this study, existing 2-dimensional seismic modeling algorithm using finite element method was modified to make a suitable algorithm for TSP modeling. Using this algorithm, TSP modeling was practiced in some models. And the synthetic data was analyzed to examine the propagation characteristics of the elastic waves. First of all, the modeling for the homogeneous tunnel model was practiced to examine the propagation characteristics of the direct waves in the vicinity of the tunnel. And the algorithm was applied to some models having reflector which is perpendicular or parallel to the excavation direction. From these, the propagation characteristics of the reflected waves were examined. Furthermore, two source-receiver arrays were used in respective models to investigate the properties of the two arrays. These modeling algorithm and synthetic data could be helpful in interpreting TSP survey data, developing inversion algorithm and designing new source-receiver arrays.

• Geophysics and Geophysical Exploration
• /
• v.11 no.2
• /
• pp.93-98
• /
• 2008

Abstract: Surface topography has a significant influence on seismic wave propagation in a reflection seismic exploration. Effects of surface topography on two-dimensional elastic wave propagation are investigated through modeling using a weighted-averaging (WA) finite-element method (FEM), which is computationally more efficient than conventional FEM. Effects of air layer on wave propagation are also investigated using flat surface models with and without air. To validate our scheme in modeling including topography, we compare WA FEM results for irregular topographic models against those derived from conventional FEM using one set of rectangular elements. For the irregular surface topography models, elastic wave propagation is simulated to show that breaks in slope act as a new source for diffracted waves, and that Rayleigh waves are more seriously distorted by surface topography than P-waves.