• 대한기계학회논문집B
• /
• 제22권1호
• /
• pp.70-78
• /
• 1998

The present study has tested semi-empirical loss models for a reliable performance prediction of mixed-flow pumps with four different specific speeds. In order to improve the predictive capabilities, this paper recommends a new internal loss model and a modified parasitic loss model. The prediction method presented here is also compared with that based on two-dimensional cascade theory. Predicted performance curves by the proposed set of loss models agree fairly well with experimental data for a variety of mixed-flow pumps in the normal operating range, but further studies considering 'droop-like' head performance characteristic due to flow reversal in mixed-flow impellers at low flow range near shut-off head are needed.

• 한국유체기계학회 논문집
• /
• 제2권2호
• /
• pp.46-56
• /
• 1999

This study is on the performance prediction and design of a sirocco fan. Slip coefficient is very important factor for the performance analysis of a centrifugal-type fan. Because generally used slip coefficient equations of backward curved centrifugal fan are not appropriate for forward curved sirocco fan, in this study a proper slip coefficient equation for a sirocco fan is suggested. Using this equation performance prediction program for sirocco fan is composed of and also included the total noise prediction that include the turbulent noise at the fan inlet and boundary layer noise. A comparison between the values obtained from performance prediction program and experimental values shows that the program predicts the sirocco fan performance in a practical rate.

• 유체기계공업학회:학술대회논문집
• /
• 유체기계공업학회 1998년도 강연회 및 연구개발 발표회 논문집
• /
• pp.63-72
• /
• 1998

This study Is on the performance prediction and design of sirocco fan. Slip coefficient is very important factor for the performance analysis of centrifugal-type fan. Because generally used slip coefficient equations of backward curved centrifugal fan are not appropriate for forward curved sirocco fan, in this study a proper slip coefficient equation for sirocco fan is suggested. Using this equation performance prediction program for sirocco fan is composed and also included the total noise prediction that include turbulent noise at the fan Inlet and boundary layer noise. A comparison between the values obtained from performance prediction program and experimental values shows that the program predicts the sirocco fan performance in a practical rate.

• Journal of Advanced Marine Engineering and Technology
• /
• 제23권5호
• /
• pp.637-653
• /
• 1999

In this study well-known burned rate expressions of Weibe function and double Wiebe function have been adopted for the combustion analysis of large two stroke marine diesel engine. A cycle simulation program was also developed to predict the performance and pressure waves in pipes using validated burned rate function,. Levenberg-Marquardt iteration method was applied to cali-brate the shape coefficients included in double Wiebe function for the performance prediction of two-stroke marine diesel engine. As a result the performance prediction using double Wiebe func-tion is well correlated withexperimental dta with the accuracy of 5% and pressure waves in intake and transport pipe are well predicted. From the results of this study it can be confirmed that the shape coefficients of burned rate function should be modified using the numerical method suggested for the accurated prediction and double Wiebe function is more suitable than Wiebe func-tion for combustion analysis of large two stroke marine engine.

• 한국수소및신에너지학회논문집
• /
• 제35권4호
• /
• pp.437-450
• /
• 2024

Sustainable shipping depends on eco-friendly energy solutions. This paper reviews methods for predicting marine fuel cell performance, including empirical approaches, physical modeling, data-driven techniques, and hybrid methods. Accurate prediction models tailored to the marine environment's unique conditions are crucial for operational efficiency. By evaluating the strengths and weaknesses of each method, this study provides a comprehensive analysis of effective strategies for forecasting polymer electrolyte membrane fuel cell and solid oxide fuel cell performance in marine applications. These insights contribute to the advancement of eco-friendly shipping technologies and enhance fuel cell performance in challenging marine environments.

• 정보처리학회 논문지
• /
• 제13권4호
• /
• pp.199-207
• /
• 2024

지역 저수지들은 농업용수 공급의 중요한 수원공으로 가뭄과 같은 극단적 기후 조건을 대비하여 안정적인 저수율 관리가 필수적이다. 저수율 예측은 국지적 강우와 같은 지역적 기후 특성뿐만 아니라 작부시기를 포함하는 계절적 요인 등에 크게 영향을 받기 때문에 적절한 예측 모델을 선정하는 것만큼 입/출력 데이터 간 상관관계 파악이 무엇보다 중요하다. 이에 본 연구에서는 1991년부터 2022년까지의 전라북도 400여 개 저수지의 광범위한 다변량 데이터를 활용하여 각 저수지의 복잡한 수문학·기후학적 환경요인을 포괄적으로 반영한 저수율 예측 모델을 학습 및 검증하고, 각 입력 특성이 저수율 예측 성능에 미치는 영향력을 분석하고자 한다. 신경망 구조에 따른 저수율 예측 성능 개선이 아닌 다변량의 입력 데이터와 예측 성능 간의 상관관계에 초점을 맞추기 위하여 실험에 사용된 예측 모델로 합성곱신경망 또는 순환신경망과 같은 복잡한 형태가 아닌 완전연결계층, 배치정규화, 드롭아웃, 활성화 함수 등의 조합으로 구성된 기본적인 순방향 신경망을 채택하였다. 추가적으로 대부분의 기존 연구에서는 하루 단위의 단기 예측 성능만을 제시하고 있으며 이러한 단기 예측 방식은 10일, 한 달 단위 등 중장기적 예측이 필요한 실무환경에 적합하지 않기 때문에, 본 연구에서는 하루 단위 예측값을 다음 입력으로 사용하는 재귀적 방식을 통해 최대 한 달 뒤 저수율 예측 성능을 측정하였다. 실험을 통해 예측 기간에 따른 성능 변화 양상을 파악하였으며, Ablation study를 바탕으로 예측 모델의 각 입력 특성이 전체 성능에 끼치는 영향을 분석하였다.

• 한국지능시스템학회논문지
• /
• 제25권2호
• /
• pp.191-196
• /
• 2015

최근 기업의 실적 및 주가를 예측하기 위해 매출액증가율, 부채비율 등의 다양한 예측변수를 활용하여 정량적인 예측방법을 활용하는 연구가 많이 이루어지고 있다. 기업실적 및 주가를 정량적 예측하기 위해 수많은 예측변수들 중에서 모델구축을 위해 중요한 예측변수를 선정하는 것이 중요하다. 대부분의 기존연구들에서는 다양한 알고리즘을 활용하여 예측변수들을 제거하는 방법을 사용하는 경우가 많았다. 이러한 경우 각 예측변수들이 가지는 많은 정보들이 제거되는 문제점이 존재한다. 이러한 문제점을 해결하기 위해 본 연구에서는 예측모델 구축을 위해 예측변수들을 제거하는 대신 각 변수들이 가지고 있는 정보를 병합하여 새로운 변수를 생성하는 대표적인 차원축소 방법인 주성분분석(PCA)을 활용하였다. 본 연구에서는 제안된 예측모델을 미국의 전자, 전기기업의 재무정보를 활용하여 구축하고 예측성능을 실증적으로 분석해 보았다.

• 대기
• /
• 제31권5호
• /
• pp.511-523
• /
• 2021

This study explores the optimal ensemble size to improve the prediction performance of the Korea Meteorological Administration's operational climate prediction system, global seasonal forecast system version 5 (GloSea5). The GloSea5 produces an ensemble of hindcast data using the stochastic kinetic energy backscattering version2 (SKEB2) and timelagged ensemble. An experiment to increase the hindcast ensemble from 3 to 14 members for four initial dates was performed and the improvement and effect of the prediction performance considering Root Mean Square Error (RMSE), Anomaly Correlation Coefficient (ACC), ensemble spread, and Ratio of Predictable Components (RPC) were evaluated. As the ensemble size increased, the RMSE and ACC prediction performance improved and more significantly in the high variability area. In spread and RPC analysis, the prediction accuracy of the system improved as the ensemble size increased. The closer the initial date, the better the predictive performance. Results show that increasing the ensemble to an appropriate number considering the combination of initial times is efficient.

• ETRI Journal
• /
• 제42권3호
• /
• pp.366-375
• /
• 2020

The network traffic prediction of a smart substation is key in strengthening its system security protection. To improve the performance of its traffic prediction, in this paper, we propose an improved gravitational search algorithm (IGSA), then introduce the IGSA into a wavelet neural network (WNN), iteratively optimize the initial connection weighting, scalability factor, and shift factor, and establish a smart substation network traffic prediction model based on the IGSA-WNN. A comparative analysis of the experimental results shows that the performance of the IGSA-WNN-based prediction model further improves the convergence velocity and prediction accuracy, and that the proposed model solves the deficiency issues of the original WNN, such as slow convergence velocity and ease of falling into a locally optimal solution; thus, it is a better smart substation network traffic prediction model.

• Nuclear Engineering and Technology
• /
• 제56권9호
• /
• pp.3594-3601
• /
• 2024

It is difficult to detect a small-scale leakage in a nuclear power plant (NPP) quickly and take appropriate action. Delaying these procedures can have adverse effects on NPPs. In this paper, we propose leak flow rate prediction using the bidirectional gated recurrent unit (Bi-GRU) method to detect leakage quickly and accurately in small-scale leakage situations because large-scale leak rates are known to be predicted accurately. The data were acquired by simulating small loss-of-coolant accidents (LOCA) or small-scale leakage situations using the modular accident analysis program (MAAP) code. In addition, to improve prediction performance, data were collected by distinguishing the break sizes in more detail. In addition, the prediction accuracy was improved by performing both LOCA diagnosis and leak flow rate prediction in small LOCA situations. The prediction model developed using the Bi-GRU showed a superior prediction performance compared with other artificial intelligence methods. Accordingly, the accurate and effective prediction model for small-scale leakage situations proposed herein is expected to support operators in decision-making and taking actions.