• 한국지반신소재학회논문집
• /
• 제21권2호
• /
• pp.11-19
• /
• 2022

본 연구에서는 하수관거 내부에서 촬영된 균열 데이터를 활용하여 균열검출에 대한 시계열 예측 성능을 개선하기 위해 GoogleNet의 전이학습과 CNN- LSTM(Long Short-Term Memory) 결합 방법을 제안하였다. LSTM은 합성곱방법(CNN)의 장기의존성 문제를 해결할 수 있으며 공간 및 시간적 특징을 동시에 모델링 할 수 있다. 제안 방법의 성능을 검증하기 위해 하수관거 내부 균열 데이터를 활용하여 학습데이터, 초기학습률 및 최대 Epochs를 변화하면서 RMSE를 비교한 결과 모든 시험 구간에서 제안 방법의 예측 성능이 우수함을 알 수 있다. 또한 데이터가 발생하는 시점에 대한 예측 성능을 살펴본 결과 역시 제안방법이 우수하게 나타나 균열검출의 예측에서 제안 방법이 효율적인 것을 검증하였다. 기존 합성곱방법(CNN) 단독 모델과 비교함으로써 본 연구를 통해 확보된 제안 방법과 실험 결과를 활용할 경우 콘크리트 구조물의 균열데이터뿐만 아니라 시계열 데이터가 많이 발생하는 환경, 인문과학 등 다양한 영역에서 응용이 가능하다.

• Ocean and Polar Research
• /
• 제40권3호
• /
• pp.99-114
• /
• 2018

In the present study, we assess the GloSea5 (Global Seasonal Forecasting System version 5) near-surface ocean current forecasts using globally observed surface drifter dataset. Annual mean surface current fields at 0-day forecast lead time are quite consistent with drifter-derived velocity fields, and low values of root mean square (RMS) errors distributes in global oceans, except for regions of high variability, such as the Antarctic Circumpolar Current, Kuroshio, and Gulf Stream. Moreover a comparison with the global high-resolution forecasting system, HYCOM (Hybrid Coordinate Ocean Model), signifies that GloSea5 performs well in terms of short-range surface-current forecasts. Predictions from 0-day to 4-week lead time are also validated for the global ocean and regions covering the main ocean basins. In general, the Indian Ocean and tropical regions yield relatively high RMS errors against all forecast lead times, whilst the Pacific and Atlantic Oceans show low values. RMS errors against forecast lead time ranging from 0-day to 4-week reveal the largest increase rate between 0-day and 1-week lead time in all regions. Correlation against forecast lead time also reveals similar results. In addition, a strong westward bias of about $0.2m\;s^{-1}$ is found along the Equator in the western Pacific on the initial forecast day, and it extends toward the Equator of the eastern Pacific as the lead time increases.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2004년도 춘계공동학술대회 논문집
• /
• pp.532-535
• /
• 2004

현재 국내 초고속 인터넷 인프라는 세계 최고 수준으로 xDSL 계열의 디지털 가입자 회선과 HFC(Hybrid Fiber Coxial) 망을 활용한 케이블 모뎀이 시장을 거의 차지하고 치열한 경쟁을 보이고 있다. 하지만 서비스 가입자 수준은 거의 포화점에 다다른 것으로 보이며 앞으로 속도를 비롯한 품질 면에서 진보된 차세대 인터넷 접속 서비스 구축을 계획하고 있다. NGN은 유무선 통합을 통한 다양한 서비스를 제공을 목표로 정부나 기업에서 추진 중은 차세대 통합 정보통신 인프라이다. 이 NGN을 실현시킬 수 있는 가입자 망 기술로서는 FTTH가 유력하게 거론되고 있다. 본 연구에서는 초고속 인터넷 서비스 수요에 대한 체계적인 분석을 통하여 NGN 서비스 특성을 반영하는 적절한 예측 모형을 제시하였다. FTTH 가입자 수요를 예측하기 위해 본 논문에서는 Bass 모형의 변형인 변형된 공존 Bass 모형을 이용하였다.

• International journal of advanced smart convergence
• /
• 제12권1호
• /
• pp.199-207
• /
• 2023

Trend Impact Analysis is a prominent hybrid method has been used in future studies with a modified surprise- free forecast. It considers experts' perceptions about how future events may change the surprise-free forecast. It is an advanced forecasting tool used in futures studies for identifying, understanding and analyzing the consequences of unprecedented events on future trends. In this paper, we propose an advanced mechanism to generate more justifiable estimates to the probability of occurrence of an unprecedented event as a function of time with different degrees of severity using adaptive neuro-fuzzy inference system (ANFIS). The key idea of the paper is to enhance the generic process of reasoning with fuzzy logic and neural network by adding the additional step of attributes simulation, as unprecedented events do not occur all of a sudden but rather their occurrence is affected by change in the values of a set of attributes. An ANFIS approach is used to identify the occurrence and severity of an event, depending on the values of its trigger attributes.

• 한국경영과학회지
• /
• 제22권3호
• /
• pp.163-173
• /
• 1997

Although numerous studies demonstrate that one technique outperforms the others for a given data set, it is hard to tell a priori which of these techniques will be the most effective to solve a specific problem. It has been suggested that the better approach to classification problem might be to integrate several different forecasting techniques by combining their results. The issues of interest are how to integrate different modeling techniques to increase the predictive performance. This paper proposes the post-model integration method, which tries to find the best combination of the results provided by individual techniques. To get the optimal or near optimal combination of different prediction techniques, Genetic Algorithms (GAs) are applied, which are particularly suitable for multi-parameter optimization problems with an object function subject to numerous hard and soft constraints. This study applies three individual classification techniques (Discriminant analysis, Logit model and Neural Networks) as base models for the corporate failure prediction. The results of composite predictions are compared with the individual models. Preliminary results suggests that the use of integrated methods improve the performance of business classification.

• 대기
• /
• 제34권2호
• /
• pp.217-231
• /
• 2024

The Korea Integrated Model (KIM)-based real-time volcanic ash dispersion prediction system, which employs the Hybrid Single Particle Lagrangian Integrated Trajectory (HYSPLIT) model, has been developed to quantitatively predict volcanic ash dispersion in East Asia and the Northwest Pacific airspace. This system, known as KIM-HYSPLIT, automatically generates forecasts for the vertical and horizontal spread of volcanic ash up to 72 hours. These forecasts are initiated upon the receipt of a Volcanic Ash Advisory (VAA) from the Tokyo Volcanic Ash Advisory Center by the server at the Korea Meteorological Administration (KMA). This system equips KMA forecasters with diverse volcanic ash prediction information, complemented by the Unified Model (UM)-based HYSPLIT (UM-HYSPLIT) system. Extensive experiments have been conducted using KIM-HYSPLIT across 128 different volcanic scenarios, along with qualitative comparisons with UM-HYSPLIT. The results indicate that the ash direction predictions from KIM-HYSPLIT are consistent with those from UM-HYSPLIT. However, there are slight differences in the horizontal extent and movement speed of the volcanic ash. Additionally, quantitative verifications of the KIM-HYSPLIT forecasts have been performed, including threat score evaluations, based on recent eruption cases. On average, the KIMHYSPLIT forecasts for 6 and 12 hours show better quantitative alignment with the VAA forecasts compared to UM-HYSPLIT. Nevertheless, both models tend to predict a broader horizontal spread of the ash cloud than indicated in the VAA forecasts, particularly noticeable in the 6-hour forecast period.

• 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.

• Journal of Power Electronics
• /
• 제17권2호
• /
• pp.476-489
• /
• 2017

Under partial shading conditions (PSCs), multiple maximums may be exhibited on the P-U curve of string inverter photovoltaic (PV) systems. Under such conditions, heuristic methods are invalid for extracting a global maximum power point (GMPP); intelligent algorithms are time-consuming; and model-based methods are complex and costly. To overcome these shortcomings, a novel hybrid MPPT (MPF-IP&O) based on a model-based peak forecasting (MPF) method and an improved perturbation and observation (IP&O) method is proposed. The MPF considers the influence of temperature and does not require solar radiation measurements. In addition, it can forecast all of the peak values of the PV string without complex computation under PSCs, and it can determine the candidate GMPP after a comparison. Hence, the MPF narrows the searching range tremendously and accelerates the convergence to the GMPP. Additionally, the IP&O with a successive approximation strategy searches for the real GMPP in the neighborhood of the candidate one, which can significantly enhance the tracking efficiency. Finally, simulation and experiment results show that the proposed method has a higher tracking speed and accuracy than the perturbation and observation (P&O) and particle swarm optimization (PSO) methods under PSCs.

• 한국인터넷방송통신학회논문지
• /
• 제19권2호
• /
• pp.187-192
• /
• 2019

수요관리와 정전에 대한 비상전원 기능을 갖춘 하이브리드 전력저장시스템으로 비상발전설비가 필요한 빌딩 및 공장건축 시에 투자비를 최소화하고, 상시 전력비를 절감함으로서 경제성을 확보할 수 있 기술을 개발함으로써 새로운 비즈니스 모델을 제시한다. 평상시에 STS(Static Transfer Switch)를 통해 부하에 계통 전력을 공급하고 PCS는 계통에 병렬로 연계되어 수요관리를 수행한다. EMS는 수요예측을 통한 전력의 효율적 운용을 위해 ESS에 충방전 지령을 PMS(Power Management System)로 하달하고 PMS는 다시 PCS 제어기로 지령을 전달하여 시스템을 운용한다. 정전시에는 STS가 계통으로부터 빠르게 이탈되면서 PCS는 독립 전원이 되어 부하 측에 정전압/정주파수의 전력을 공급할수 있는 구조이다. 따라서 하이브리드 ESS에 대한 실 계통 연계 및 독립 운전 성능 검증을 통한 신뢰성을 확보할수 있고, 저탄소 녹색성장 기술의 효율적 전력망과 연계 운영이 가능하게 함으로써 ESS 연계를 통한 신재생에너지 발전에 의한 불규칙한 전력 품질개선, 피크부하 기여도 제고가 가능하다. 또한 현재 석탄 화력이 담당하고 있는 주파수추종 예비력을 ESS로 대체함에 따라 연료비가 높은 LNG 발전기 가동비용을 절감할 수 있는 기대효과가 있다.

• 한국지하수토양환경학회지:지하수토양환경
• /
• 제20권3호
• /
• pp.74-82
• /
• 2015

A method to filter out the effect of river stage fluctuations on groundwater level was designed using an artificial neural network-based time series model of groundwater level prediction. The designed method was applied to daily groundwater level data near the Gangjeong-Koryeong Barrage in the Nakdong river. Direct prediction time series models were successfully developed for both cases of before and after the barrage construction using past measurement data of rainfall, river stage, and groundwater level as inputs. The correlation coefficient values between observed and predicted data were over 0.97. Using the time series models the effect of river stage on groundwater level data was filtered out by setting a constant value for river stage inputs. The filtered data were applied to the hybrid water table fluctuation method in order to estimate the groundwater recharge. The calculated ratios of groundwater recharge to precipitation before and after the barrage construction were 11.0% and 4.3%, respectively. It is expected that the proposed method can be a useful tool for groundwater level prediction and recharge estimation in the riverside area.