• Geophysics and Geophysical Exploration
• /
• v.25 no.3
• /
• pp.140-161
• /
• 2022

Seismic data with missing traces are often obtained regularly or irregularly due to environmental and economic constraints in their acquisition. Accordingly, seismic data interpolation is an essential step in seismic data processing. Recently, research activity on machine learning-based seismic data interpolation has been flourishing. In particular, convolutional neural network (CNN) and generative adversarial network (GAN), which are widely used algorithms for super-resolution problem solving in the image processing field, are also used for seismic data interpolation. In this study, CNN-based algorithm, U-Net and GAN-based algorithm, and conditional Wasserstein GAN (cWGAN) were used as seismic data interpolation methods. The results and performances of the methods were evaluated thoroughly to find an optimal interpolation method, which reconstructs with high accuracy missing seismic data. The work process for model training and performance evaluation was divided into two cases (i.e., Cases I and II). In Case I, we trained the model using only the regularly sampled data with 50% missing traces. We evaluated the model performance by applying the trained model to a total of six different test datasets, which consisted of a combination of regular, irregular, and sampling ratios. In Case II, six different models were generated using the training datasets sampled in the same way as the six test datasets. The models were applied to the same test datasets used in Case I to compare the results. We found that cWGAN showed better prediction performance than U-Net with higher PSNR and SSIM. However, cWGAN generated additional noise to the prediction results; thus, an ensemble technique was performed to remove the noise and improve the accuracy. The cWGAN ensemble model removed successfully the noise and showed improved PSNR and SSIM compared with existing individual models.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.3
• /
• pp.188-193
• /
• 2000

This paper presents an approach to obtain a reduced neuro-fuzzy model for a plant. The Neuro-Fuzzy Network are compose of the Radial Basis Function Networks with Gausis membership and learned by using temporal back propagation. The dependency in rough set theory is used to eliminate rules. Dependency between the condition membership value of each rule in a model and the output of the plant can allow us to see how much contribution the rule is to identify the plant. While the reduced model maintains the same performance as the original one, the selection algorithm can minimize its complexity and redundancy of the structure.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.310-316
• /
• 1998

본 논문에서는 기존의 퍼지 제어규칙에비해 좋은 성능을 갖는 T-S(Takagi-Sugeno)퍼지 모델을 자기조직화 지도와 역전파 신경망을 이용하여 표현하고 제어기 구현을 위한 규칙의 자동 생성 방법을 제안한다. 제안된 방법은 신경망에 기초하여 T-S 퍼지 제어 규칙을 포현하므로써 학습 기능을 이용하여 지식 획득을 용이하게 하고, 입력 변수간의 퍼지 관계에 기반 하여 추론이 이루어지므로 각 퍼지 변수에 대한 소속 함수의 정의 과정이 불필요하게 된다. 또한 제어기로 구현되었을 때 규칙의 수나 퍼지화 및 비퍼지화 등이 구성된 추론망을 통하여 자동으로 수행될 수 있다. 때문에 퍼지 시스템의 구현이 쉽게 이루어 질 수 있게 한다. 제안된 방법을 자동차 궤도 안정화 모의 실험에 적용해 봄으로써 추론망이 규칙을 생성하여 타당한 추론을 하게 됨을 확인한다.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.10 no.2
• /
• pp.64-72
• /
• 1998

Dynamic response analysis is carried out for slender marine structures such as tensioned risers and tethers of tension leg platform, which are subjected to floating vessel motions as well as environmental forces arising from ocean waves. A mumerical analysis procedure is developed by using finite element model of the structural member. Dynamic analses are performed in the time domain for regular waves. Parameter studies are carried out to highlight the effects of surface vessel motions on the lateral dynamics of the structures. Example results of displacements, bending stresses are compared for various in water depth, environmental condition and vessel motion. Some instability conditions of the structures due to time-varying tension by vessel heave motion are discussed through the example analyses. As the results, the interaction between vessel surge and heave motions amplifies the total structural response of a riser. In the case of a tether, the effect of vessel heave motion during heavy storm is seemed to be quite significant to lateral response of the structure.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.36 no.1
• /
• pp.1-10
• /
• 2024

As increasing demands for a floating structure expanded from offshore industry facilities to living facilities, it has emerged that necessity of techniques to reduce motions of a floating structure. This study present a floating structure with porosity on the outer surface of the floater. Under each regular and irregular wave, responses of the floater was investigated in frequency domain. The proposed structure is composed of inner and outer floaters, which are connected to each other and the outer wall is perforated, and the heave and the pitch of floaters with different perforation rates (0~30%) were compared with at both the center and the edge. The results showed that pitch responses can be decreased by increasing of perforation rate of the floater. Comparing with responses of the non-perforated floater, those of the proposed floating structure were reduced to above 10% and 2%, respectively for regular and irregular wave conditions.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.21 no.1
• /
• pp.30-38
• /
• 2009

In recent years, there's been strong demand for coastal structures that have a permeability that serves water affinity and disaster prevention from wave attack. The aim of this study is to examine the wave transformation, including wave run-up that propagates over the coastal structures with a steep slope. A numerical model based on the nonlinear shallow water equation, together with the unsteady nonlinear Darcy law for fluid motion in permeable underlayer and laboratory measurements was carried out in terms of the free surface elevations and fluid particle velocities for the cases of regular and irregular waves over 1:5 impermeable and permeable slopes. The numerical results were used to evaluate the application and limitations of the PBREAK numerical model. The numerical model could predict the cross-shore variation of the wave profile reasonably, but showed less accurate results in the breaking zone that the mass and momentum influx is exchanged the most. Except near the wave crest, the computed depth averaged velocities could represent the measured profile below the trough level fairly well.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.18 no.2
• /
• pp.154-165
• /
• 2006

In the present study, a numerical model using Boussinesq equation is set up to predict the interacted equilibrium between waves and their induced currents in the occurrence of breaking waves over an underwater shoal, and the numerical results are compared with results of existing hydraulic experiments. A sensitivity analysis has been done to find out appropriate values of breaking wave parameters with the result (regular wave case) of Vincent and Briggs (1989)’ experiment. Then the numerical model is applied to the irregular wave cases of the experiment and the hydraulic model test of Ieodo which is a natural undersea shoal. The results show that a strong current forms in the wave direction at the downstream side of the shoals, causing the attenuation of wave heights there. The calculated wave heights generally show a similar pattern with the measured data.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.29 no.1
• /
• pp.253-260
• /
• 2005

Recently, the storms which hit Korean Peninsula are getting bigger, and the damages from the storms are wide spreaded. Thus, and approach with disaster prebention to offshore area and/or opened island area is neccessary. The existing wave design parameter was calculated with linear regular wave models inputting deep water design wave or wind sources. so it wasn't able to deal with wind-induced waves, interactions with waves, and redistribution of wave energy simultaneously. In this study, we made numerical simulation with SWAN(Simulation Waves Nearshore) Model which can consider development of waves and winds and their interference. The result from this model shows much different with those from existing model's. so the result from this study, especially in this modeling area, could be used for harbor design and coastal disaster prevention field in the future.

• Journal of Ocean Engineering and Technology
• /
• v.8 no.1
• /
• pp.123-130
• /
• 1994

일반적으로 규칙파 또는 불규칙파중에서의 반잠수식 해양구조물의 응답을 추정할때, 선형계에 적합한 주파수 영역해석법을 사용하고 있다. 대다수의 해양구조물은 Lower Hull과 단면적이 일정한 Column으로 구성되어 있지만, 만약 Column의 단면적이 홀수에 따라 변화한다면 복원력항에 비선형계를 적용해야만 한다. 따라서 본 논문에서는 비선형 복원력을 고려한 반잠수식 해양구조물의 응답을 추정할 수 있는 시간 영역 해석법을 개발하였다. 그리고, Column형상이 다른 5개의 모델을 선정하여, 이들의 시간 영역 해석결과와 주파수 영역 해석 결과를 서로 비교하였다. 또한 파랑외력으로서 불규칙파를 적용할 때, 비선형 복원력이 해양구조물에 응답에 미치는 영향을 조사 하였다.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.6
• /
• pp.315-324
• /
• 2022

The experimental data obtained in a wave flume were analyzed using machine learning techniques to establish a model that predicts the input wave height of the wavemaker based on the waves that have experienced wave shoaling and to verify the performance of the established model. For this purpose, artificial neural network (NN), the most representative machine learning technique, and Gaussian process regression (GPR), one of the non-parametric regression analysis methods, were applied respectively. Then, the predictive performance of the two models was compared. The analysis was performed independently for the case of using all the data at once and for the case by classifying the data with a criterion related to the occurrence of wave breaking. When the data were not classified, the error between the input wave height at the wavemaker and the measured value was relatively large for both the NN and GPR models. On the other hand, if the data were divided into non-breaking and breaking conditions, the accuracy of predicting the input wave height was greatly improved. Among the two models, the overall performance of the GPR model was better than that of the NN model.