• 한국해양공학회지
• /
• 제34권6호
• /
• pp.454-460
• /
• 2020

In 2019, the Korean government announced the 3rd Basic Plan for Energy, which included expanding the rate of renewable energy generation by 30-40% by 2040. Hence, offshore wind power generation, which is relatively easy to construct in large areas, should be considered. The East Sea coast of Korea is a sea area where the depth reaches 50 m, which is deeper than the west coast, even though it is only 2.5 km away from the coastline. Therefore, for offshore wind power projects on the East Sea coast, a floating offshore wind power should be considered instead of a fixed one. In this study, a response analysis was performed by applying the analytical conditions of IEC61400-3-2 for the design of floating offshore wind power generation systems. In the newly revised IEC61400-3-2 international standard, design load cases to be considered in floating offshore wind power systems are specified. The upper structure applied to the numerical analysis was a 5-MW-class wind generator developed by the National Renewable Energy Laboratory (NREL), and the marine environment conditions required for the analysis were based on the Ulsan Meteorological Buoy data from the Korea Meteorological Administration. The FAST v8 developed by NREL was used in the coupled analysis. From the simulation, the maximum response of the six degrees-of-freedom motion and the maximum load response of the joint part were compared. Additionally, redundancy was verified under abnormal conditions. The results indicate that the platform has a maximum displacement radius of approximately 40 m under an extreme sea state, and when one mooring line is broken, this distance increased to approximately 565 m. In conclusion, redundancy should be verified to determine the design of floating offshore wind farms or the arrangement of mooring systems.

• 한국측량학회지
• /
• 제38권6호
• /
• pp.499-509
• /
• 2020

본 연구에서는 최근 영상판독 분야에서 활발히 연구되고, 활용성이 발전하고 있는 인공지능 기반 객체분류 학습 데이터 구축에 관한 내용을 다룬다. 영상판독분야에서 인공지능을 활용하여 정확도 높은 객체를 인식, 추출하기 위해서는 알고리즘에 적용할 많은 양의 학습데이터가 필수적으로 요구된다. 하지만, 현재 공동활용 가능한 데이터 셋이 부족할 뿐만 아니라 데이터 생성을 위해서는 많은 시간과 인력 및 고비용을 필요로 하는 것이 현실이다. 따라서 본 연구에서는 소량의 초기 항공영상 학습데이터를 GAN (Generative Adversarial Network) 기반의 생성기 신경망을 활용하여 오버샘플 영상 학습데이터를 구축하고, 품질을 평가함으로써 추가적 학습 데이터 셋으로 활용하기 위한 실험을 진행하였다. GAN을 이용하여 오버샘플 학습데이터를 생성하는 기법은 딥러닝 성능에 매우 중요한 영향을 미치는 학습데이터의 양을 획기적으로 보완할 수 있으므로 초기 데이터가 부족한 경우에 효과적으로 활용될 수 있을 것으로 기대한다.

• Nutrition Research and Practice
• /
• 제15권1호
• /
• pp.95-105
• /
• 2021

BACKGROUND/OBJECTIVES: The measurement of body composition, including muscle and fat mass, remains challenging in large epidemiological studies due to time constraint and cost when using accurate modalities. Therefore, this study aimed to develop and validate prediction equations according to sex to measure lean body mass (LBM), appendicular skeletal muscle mass (ASM), and body fat mass (BFM) using anthropometric measurement, serum creatinine level, and lifestyle factors as independent variables and dual-energy X-ray absorptiometry as the reference method. SUBJECTS/METHODS: A sample of the Korean general adult population (men: 7,599; women: 10,009) from the Korean National Health and Nutrition Examination Survey 2008-2011 was included in this study. The participants were divided into the derivation and validation groups via a random number generator (with a ratio of 70:30). The prediction equations were developed using a series of multivariable linear regressions and validated using the Bland-Altman plot and intraclass correlation coefficient (ICC). RESULTS: The initial and practical equations that included age, height, weight, and waist circumference had a different predictive ability for LBM (men: R2 = 0.85, standard error of estimate [SEE] = 2.7 kg; women: R2 = 0.78, SEE = 2.2 kg), ASM (men: R2 = 0.81, SEE = 1.6 kg; women: R2 = 0.71, SEE = 1.2 kg), and BFM (men: R2 = 0.74, SEE = 2.7 kg; women: R2 = 0.83, SEE = 2.2 kg) according to sex. Compared with the first prediction equation, the addition of other factors, including serum creatinine level, physical activity, smoking status, and alcohol use, resulted in an R2 that is higher by 0.01 and SEE that is lower by 0.1. CONCLUSIONS: All equations had low bias, moderate agreement based on the Bland-Altman plot, and high ICC, and this result showed that these equations can be further applied to other epidemiologic studies.

• 한국안전학회지
• /
• 제36권3호
• /
• pp.74-80
• /
• 2021

Korea Atomic Energy Research Institute (KAERI) has been operating an integral effects test facility, the Advanced Thermal-Hydraulic Test Loop for Accident Simulation (ATLAS), according to APR1400 for transient experimental and design basis accident simulation. Moreover, based on the experimental data, the domestic standard problem (DSP) program has been conducted in Korea to validate system codes. Recently, through DSP-05, the performance of the passive auxiliary feedwater system (PAFS) in the event of multiple steam generator tube rupture (MSGTR) has been analyzed. However, some errors exist in the reference input model distributed for DSP-05. Furthermore, the calculation results of the heat loss correlation for the secondary system presented in the technical report of the reference indicate that a large difference is present in heat loss from the target value. Thus, in this study, the reference model is corrected using the geometric information from the design report and drawings of ATLAS. Additionally, a new heat loss correlation is suggested by fitting the results of the heat loss tests. Herein, MSGTR-PAFS accident analysis is performed using MARS-KS 1.5 with the improved model. The steady-state calculation results do not significantly differ from the experimental values, and the overall physical behavior of the transient state is properly predicted. Particularly, the predicted operating time of PAFS is similar to the experimental results obtained by the modified model. Furthermore, the operating time of PAFS varies according to the heat loss of the secondary system, and the sensitivity analysis results for the heat loss of the secondary system are presented.

• 한국정보통신학회논문지
• /
• 제26권6호
• /
• pp.881-889
• /
• 2022

전 세계적으로 선박의 배출물에 의한 환경 오염에 관심이 증가하여, 에너지 효율을 높여 선박 배출물 감소와 연료 소비 효율을 높이는 시스템 개발에 많은 연구가 진행되고 있다. 각 시스템은 소형 선박에서는 실증될 수 있으나, 대형 선박의 경우에는 실증에 대한 여건이 마땅치 않다. 현실적으로 대형 선박에 real time으로 구동되는 에너지 관리 시스템 제어기를 테스트하기 위해서는 시뮬레이터를 통한 테스트를 수행해야 한다. 본 연구에서는 각 제어 시스템과 에너지 관리 시스템을 연동할 수 있도록 각 신호를 Modbus TCP/IP에 맞게 주소를 설정하였으며, 신호의 흐름에 따라 알고리즘을 구성하였다. 또한, 각 제어기가 선박에서 수집하는 신호를 인위적으로 발생시킬 수 있도록 신호 발생기를 설계 및 제작하였다. 시뮬레이터 제작 및 연동 결과 real time으로 운용되는 각 제어기는 역할을 알맞게 수행하였으며, 선박용 에너지 관리 시스템의 알고리즘의 적용이 적절히 수행됨을 확인하였다.

• 시스템엔지니어링학술지
• /
• 제18권2호
• /
• pp.94-107
• /
• 2022

Accidents prevention and mitigation is the highest priority of nuclear power plant (NPP) operation, particularly in the aftermath of the Fukushima Daiichi accident, which has reignited public anxieties and skepticism regarding nuclear energy usage. To deal with accident scenarios more effectively, operators must have ample and precise information about key safety parameters as well as their future trajectories. This work investigates the potential of machine learning in forecasting NPP response in real-time to provide an additional validation method and help reduce human error, especially in accident situations where operators are under a lot of stress. First, a base-case SGTR simulation is carried out by the best-estimate code RELAP5/MOD3.4 to confirm the validity of the model against results reported in the APR1400 Design Control Document (DCD). Then, uncertainty quantification is performed by coupling RELAP5/MOD3.4 and the statistical tool DAKOTA to generate a large enough dataset for the construction and training of neural-based machine learning (ML) models, namely LSTM, GRU, and hybrid CNN-LSTM. Finally, the accuracy and reliability of these models in forecasting system response are tested by their performance on fresh data. To facilitate and oversee the process of developing the ML models, a Systems Engineering (SE) methodology is used to ensure that the work is consistently in line with the originating mission statement and that the findings obtained at each subsequent phase are valid.

• 한국정보전자통신기술학회논문지
• /
• 제15권6호
• /
• pp.440-448
• /
• 2022

최근 분산 에너지 자원들의 도입으로 전력망의 최적 자원 할당 문제의 중요성이 강조되고 있고, 대규모 전력망의 방대한 양의 데이터를 처리하기 위해 분산 자원 할당 기법이 요구되고 있다. 최적 자원 할당 문제에서 각 발전기의 발전 용량의 한계로 인하여 수급의 균형이 만족하는 경우를 고려한 연구는 많이 진행되고 있지만, 총 요구량이 최대 발전 용량을 초과하는 경우인 수급 불균형을 고려한 연구는 아직 미미한 실정이다. 본 논문에서는 수급 균형인 상황뿐만 아니라 수급 불균형 상황을 고려하여 전력망의 최적 자원 할당을 위한 일치 기반의 분산 알고리즘을 제안한다. 제안하는 분산 알고리즘은 수급 균형을 만족하는 경우에는 최적의 자원을 할당하고, 수급이 불균형한 경우에는 부족한 자원의 양을 계측할 수 있도록 설계하였다. 마지막으로 모의실험을 통하여 제안된 알고리즘의 성능을 검증하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권6호
• /
• pp.1530-1544
• /
• 2023

Data monitoring is an important foundation of modern science. In most cases, the monitoring data is time-series data, which has high application value. The deep learning algorithm has a strong nonlinear fitting capability, which enables the recognition of time series by capturing anomalous information in time series. At present, the research of time series recognition based on deep learning is especially important for data monitoring. Deep learning algorithms require a large amount of data for training. However, abnormal sample is a small sample in time series, which means the number of abnormal time series can seriously affect the accuracy of recognition algorithm because of class imbalance. In order to increase the number of abnormal sample, a data augmentation method called GANBATS (GAN-based Bi-LSTM and Attention for Time Series) is proposed. In GANBATS, Bi-LSTM is introduced to extract the timing features and then transfer features to the generator network of GANBATS.GANBATS also modifies the discriminator network by adding an attention mechanism to achieve global attention for time series. At the end of discriminator, GANBATS is adding averagepooling layer, which merges temporal features to boost the operational efficiency. In this paper, four time series datasets and five data augmentation algorithms are used for comparison experiments. The generated data are measured by PRD(Percent Root Mean Square Difference) and DTW(Dynamic Time Warping). The experimental results show that GANBATS reduces up to 26.22 in PRD metric and 9.45 in DTW metric. In addition, this paper uses different algorithms to reconstruct the datasets and compare them by classification accuracy. The classification accuracy is improved by 6.44%-12.96% on four time series datasets.

• 풍력에너지저널
• /
• 제14권4호
• /
• pp.50-56
• /
• 2023

With the abnormal weather phenomena caused by global warming, the frequency and intensity of lightning strikes are increasing, and lightning accidents are becoming one of the biggest causes of failures and accidents in offshore wind turbines. In order to secure generator operation reliability, effective and practical measures are needed to reduce lightning damage. Because offshore wind turbines are tall structures installed at sea, the possibility of direct lightning strikes is very high compared to other structures, and the role of surge protection devices to minimize damage to the electrical and electronic circuits inside the wind turbine is very important. In this study, a varistor, which is a key element for a class 1 surge protection device for direct lightning protection, was developed. The current density was improved by changing the varistor composition, and the distance between the electrode located on the varistor surface and the edge of the varistor was optimized through a simulation program to improve the fabrication process. Considering the combined effects of heat distribution, electric field distribution, and current density on the optimized varistor surface, silver electrodes were formed with a gap of 0.5 mm. The varistor developed in this study was confirmed to have an energy tolerance of 10/350 ㎲, 50kA, which is a representative direct lightning current waveform, and good protection characteristics with a limiting voltage of 2 kV or less.

• Radiation Oncology Journal
• /
• 제5권1호
• /
• pp.49-58
• /
• 1987

환부에 열을 가하여 종양을 치료할 수 있는 온열요법의 생물학적 효과는 상당히 고무적이며 새로운 암 치료 수단으로 등장되었다. 그러나 체내 깊숙히 위치하고 있는 종양에 일정한 열을 계속 부여하면서 온도와 열의 분포를 정확히 측정하기가 어려웠다. 연세 암센터는 연세대학교 공과대학과 녹십자 의료 공업주식회사와 산학협동으로 라디오파 유전가열형 온열장치(가칭 Greenytherm-GY8)를 개발 제작하고 임상응용을 위해 기초 연구를 실시하였다. 개발된 온열장치는 $8{\sim}10MHz$ 라디오파 발생기와 유전가열 전극, 온도계측용 열정대, 냉각장치 및 제어용 개인 컴퓨터로 구성되었다. 온열장치의 성능을 시험하기 위하여 인체크기의 한천팬텀과 동물 및 인체의 악성종양에 대한 치료온도와 온열분포를 측정하였다. 라디오파 발생전력을 $200{\sim}1,500W$까지 조절할 수 있으며 유전가열을 위한 라디오파의 주파수는 $8{\sim}10MHz$ 범위를 얻을 수 있었다. 피부에 근접된 종양의 가열온도는 $200{\sim}500W$의 RF 전력으로 10분이 내 치료가능온도$(42.5^{\circ}C)$ 이상으로 가열할 수 있었으며 정상조직 쪽의 전극은 $5{\sim}10^{\circ}C$로 냉각시키므로서 피부손상을 방지할 수 있었다. $5{\sim}10cm$ 깊이에 존재하는 종양의 가열온도는 치료 가능한 $40{\sim}43^{\circ}C$까지 가열이 가능하였으며 냉각보러스와 정합회로에 의해 피부의 자극을 줄일 수 있었다. 이상과 같은 실험결과로 유전가열형 온열장치는 임상응용에 적합하다고 판단되며 임상경험을 통하여 더 예민한 정합장치와 전기적 자극을 완전히 줄일 수 있는 방법 및 편리한 전극 등의 개발이 가능한 기본자료가 될 수 있다.