• Nuclear Engineering and Technology
• /
• 제50권4호
• /
• pp.582-588
• /
• 2018

Accident diagnosis is one of the complex tasks for nuclear power plant (NPP) operators. In abnormal or emergency situations, the diagnostic activity of the NPP states is burdensome though necessary. Numerous computer-based methods and operator support systems have been suggested to address this problem. Among them, the recurrent neural network (RNN) has performed well at analyzing time series data. This study proposes an algorithm for accident diagnosis using long short-term memory (LSTM), which is a kind of RNN, which improves the limitation for time reflection. The algorithm consists of preprocessing, the LSTM network, and postprocessing. In the LSTM-based algorithm, preprocessed input variables are calculated to output the accident diagnosis results. The outputs are also postprocessed using softmax to determine the ranking of accident diagnosis results with probabilities. This algorithm was trained using a compact nuclear simulator for several accidents: a loss of coolant accident, a steam generator tube rupture, and a main steam line break. The trained algorithm was also tested to demonstrate the feasibility of diagnosing NPP accidents.

• 한국해양공학회지
• /
• 제25권6호
• /
• pp.110-115
• /
• 2011

Numerouslong-term consolidation and secondary compression settlements may occur in Busan clay, which is astructured soft clay and consists of a thick clay deposit. As a surcharge load is applied to soils, soils experience different stress paths with depth. Therefore, it is necessary to study the long-term consolidation behavior of Busan clay considering stress conditions such as OC or NC states. In this study, a series of long-term consolidation tests were performed to investigate the consolidation characteristics of Busan clay for 20 days. The undisturbed clay samples were taken from 3 sites located in the Nakdong River estuary. The results showed that the creep rate of the Busan clay gradually decreased with time, which indicated that the secondary compression settlement decreased with time. In addition, the experimental results for 3 samples showed that the ratios were about 0.0363 and 0.051, respectively.

• 산업과 과학
• /
• 제3권1호
• /
• pp.17-22
• /
• 2024

인류의 출현과 함께 시작된 역사에는 기록이라는 수단이 있기에 현재에 사는 우리는 데이터를 통해 과거를 확인할 수 있다. 생성되는 데이터는 일정 순간에만 발생하여 저장될 수도 있지만, 과거로부터 현재까지 일정 시간 간격 동안 계속해서 생성될 뿐만 아니라 다가올 미래에도 발생함으로써 이를 활용하여 예측하는 것 또한 중요한 작업이다. 본 논문은 수많은 데이터 중에서 시계열 데이터의 활용 동향을 알아보기 위해서 시계열 데이터의 개념에서부터 머신러닝 분야에서 시계열 데이터 분석에 주로 사용되는 Recurrent Neural Network와 Long-Short Term Memory에 대해 분석하고, 이런 모델들을 활용한 사례의 조사를 통해 의료 진단, 주식 시세 분석, 기후 예측 등 다양한 분야에 활용되어 높은 예측 결과를 보이고 있음을 확인하였고, 이를 바탕으로 향후 활용방안에 대하여 모색해본다.

• 한국환경과학회지
• /
• 제22권10호
• /
• pp.1305-1316
• /
• 2013

A long-term wind resource map was made to provide the key design data for the 2.5 GW Korean West-South Offshore Wind Project, and its reliability was validated. A one-way dynamic downscaling of the MERRA reanalysis meteorological data of the Yeongwang-Gochang offshore was carried out using WindSim, a Computational Fluid Dynamics based wind resource mapping software, to establish a 33-year time series wind resource map of 100 m x 100 m spatial resolution and 1-hour interval temporal resolution from 1979 to 2012. The simulated wind resource map was validated by comparison with wind measurement data from the HeMOSU offshore meteorological tower, the Wangdeungdo Island meteorological tower, and the Gochang transmission tower on the nearby coastline, and the uncertainty due to long-term variability was analyzed. The long-term variability of the wind power was investigated in inter-annual, monthly, and daily units while the short-term variability was examined as the pattern of the coefficient of variation in hourly units. The results showed that the inter-annual variability had a maximum wind index variance of 22.3% while the short-term variability, i.e., the annual standard deviation of the hourly average wind power, was $0.041{\pm}0.001$, indicating steady variability.

• Journal of the korean society of oceanography
• /
• 제39권4호
• /
• pp.207-211
• /
• 2004

We used long time series of hydrographic and biological variables to examine the ecosystem consequences of a rare, anomalous event in the south sea of Korea. The highest zooplankton biomass in 36 years of sampling occurred in April 1997. Zooplankton biomass exceeded 2 times than the long-term mean at 35% of the stations. Copepod abundance was low in April and June and also failed to show a seasonal peak in 1997. Mackerel (Scomber japonicus) catches were very low in spring 1997 and 1999, in spite of a positive correlation between zooplankton biomass and mackerel catches at lags of 0, 12 and 24 months. It was discussed that a high zooplankton biomass with low copepod abundance in April 1997 resulted from unusual high temperature and salps abundance. Water temperatures were ca. $2^{\circ}C$ higher than the long-term mean at the surface. Salps and doliolids (thaliaceans), especially the warm-water species Doliolum nationalis, dominated the zooplankton. An unusual incursion of the Tsushima Warm Current may have transported the thaliaceans into the area and/or produced favorable conditions for a bloom. This study suggested that taxonomic composition of zooplankton was important to decide mackerel catches.

• 한국수산과학회지
• /
• 제46권2호
• /
• pp.186-194
• /
• 2013

We compiled and analyzed long-term time-series data collected in Korea to evaluate changes in oceanographic conditions and marine ecosystems near Jeju Island ($33^{\circ}00^{\prime}-34^{\circ}00^{\prime}\;N$, $125^{\circ}30^{\prime}-127^{\circ}30^{\prime}\;E$) from 1981 to 2010. Environmental data included depth-specific time series of temperature and salinity that have been measured bimonthly since 1961 in water columns at 175 fixed stations along 22 oceanographic lines in Korean waters by the National Fisheries Research & Development Institute, and time series of estimated volume transport of the Tsushima Warm Current (TWC) and Korea Strait Bottom Cold Water (KSBCW) for the period from 1961 to 2008. We analyzed the species composition in terms of biomass of fish species caught by Korean fishing vessels in the waters near Jeju Island (1981-2010). Data were summarized and related to environmental changes using canonical correspondence analysis (CCA). The CCA detected major shifts in fish community structure between 1982 and 1983 and between 1990 and 1992; the dominant species were a filefish during 1981-1992 and chub mackerel from 1992 to 2007. CCA suggested that water temperature and salinity in the mixed layer and the volume transport of the TWC and the KSBCW were significantly related to the long-term changes in the fish community in the waters off Jeju Island. Fish community shifts seemed to be related to the well-established 1989 regime shift in the North Pacific. Further studies are required to elucidate the mechanisms driving climate change effects on the thermal windows and habitat ranges of commercial species to develop fisheries management plans based on reliable projections of long-term changes in the oceanographic conditions in waters off Jeju Island.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2017년도 추계학술대회
• /
• pp.50-53
• /
• 2017

장기 해운불황에 따라 불확실성이 증폭되고 있는 상황에서 경기추세의 이해뿐만 아니라 예측 또한 중요해지고 있는 실정이다. 본 논문에서는 최근 특정 복잡한 문제에 대해서 각광받고 있는 인공신경망을 적용하여 BDI 예측을 연구하였다. 사용된 인공신경망은 순환신경망으로 RNN과 LSTM 그리고 비교의 목적으로 MLP를 통해 2009.04.01.부터 2017.07.31.의 기간을 대상으로 연구를 진행하였다. 또한 전통적 시계열 예측방법론인 ARIMA 분석을 실시해 인공신경망들의 예측성능과 비교하였다. 결과로 순환신경망인 RNN의 성능이 가장 뛰어났으며 LSTM의 특정 시계열(BDI)에의 적용가능성을 확인할 수 있었다.

• 대한원격탐사학회지
• /
• 제36권4호
• /
• pp.515-525
• /
• 2020

This study investigates the potential of bidirectional long short-term memory (Bi-LSTM) for efficient modeling of temporal information in crop classification using multitemporal remote sensing images. Unlike unidirectional LSTM models that consider only either forward or backward states, Bi-LSTM could account for temporal dependency of time-series images in both forward and backward directions. This property of Bi-LSTM can be effectively applied to crop classification when it is difficult to obtain full time-series images covering the entire growth cycle of crops. The classification performance of the Bi-LSTM is compared with that of two unidirectional LSTM architectures (forward and backward) with respect to different input image combinations via a case study of crop classification in Anbadegi, Korea. When full time-series images were used as inputs for classification, the Bi-LSTM outperformed the other unidirectional LSTM architectures; however, the difference in classification accuracy from unidirectional LSTM was not substantial. On the contrary, when using multitemporal images that did not include useful information for the discrimination of crops, the Bi-LSTM could compensate for the information deficiency by including temporal information from both forward and backward states, thereby achieving the best classification accuracy, compared with the unidirectional LSTM. These case study results indicate the efficiency of the Bi-LSTM for crop classification, particularly when limited input images are available.

• 대한원격탐사학회지
• /
• 제36권4호
• /
• pp.527-534
• /
• 2020

This study aims to monitor the displacement of the bridges using Stanford Method for Persistent Scatterers (StaMPS) time-series Persistent Scatterer Interferometric Synthetic Aperture Radar analysis. For case study bridges: Kimdaejung bridge and Deokyang bridge, we acquired 60 and 33 Cosmo-Skymed Synthetic Aperture Radar (SAR) data over the Mokpo region and Yeosu region, respectively from 2013 to 2019. With single-look interferograms, we estimated the long-term time-series displacements over the bridges. The time-series displacements were estimated as -8.8 mm/year and -1.34 mm/year at the mid-span over the selected bridges: Kimdaejung and Deokyang bridge, respectively. This time-series displacement provides reliable and high spatial resolution information to monitor the structural behavior of the bridge for preventing structural behaviors.

• Geomechanics and Engineering
• /
• 제11권4호
• /
• pp.531-552
• /
• 2016

The greenschist in the Jinping II Hydropower Station in southwest China exhibits continuous creep behaviour because of the geological conditions in the region. This phenomenon illustrates the time-dependent deformation and progressive damage that occurs after excavation. In this study, the responses of greenschist to stress over time were determined in a series of laboratory tests on samples collected from the access tunnel walls at the construction site. The results showed that the greenschist presented time-dependent behaviour under long-term loading. The samples generally experienced two stages: transient creep and steady creep, but no accelerating creep. The periods of transient creep and steady creep increased with increasing stress levels. The long-term strength of the greenschist was identified based on the variation of creep strain and creep rate. The ratio of long-term strength to conventional strength was around 80% and did not vary much with confining pressures. A quantitative method for predicting the failure period of greenschist, based on analysis of the stress-strain curve, is presented and implemented. At a confining pressure of 40 MPa, greenschist was predicted to fail in 5000 days under a stress of 290 MPa and to fail in 85 days under the stress of 320 MPa, indicating that the long-term strength identified by the creep rate and creep strain is a reliable estimate.