• 설비공학논문집
• /
• 제21권2호
• /
• pp.71-78
• /
• 2009

Up until recently, the energy and the economic analysis of a cogeneration system have been implemented by a manual calculation that is based on monthly thermal loads of buildings. In this study, a cogeneration system modeling validation with a detail building energy simulation, eQUEST, for a building energy and cost prediction has been implemented. By analyzing the hourly building electricity and thermal loads, it enables users to decide proper cogeneration system capacity and to estimate more accurate building energy consumption. eQUEST also verified the energy analysis when the heat pump system is integrated with the cogeneration system. The mechanical system configuration benefits from the high efficiency heat pump system while avoiding the building electricity demand increase. Economic analysis such as LCC (Life Cycle Cost) method is carried out to verify economical benefits of the system by applying actual utility rates of KEPCO(Korea Electricity Power COmpany) and KOGAS(KOrea GAS company).

• 사물인터넷융복합논문지
• /
• 제8권3호
• /
• pp.55-61
• /
• 2022

지구 온난화의 주범인 온실가스 감축을 위해 UN은 1992년 기후변화협약을 체결하였다. 우리나라도 온실가스 감축을 위해 재생에너지 보급 확대 정책을 펼치고 있다. 태양에너지를 이용한 재생에너지 개발의 확대는 풍력과 태양광 발전의 확대로 이어졌다. 기상 상황에 영향을 많이 받는 재생에너지 개발의 확대는 전력계통의 수요공급관리에 어려움이 발생하고 있다. 이러한 문제를 해결하기 위해 전력중개시장을 도입하게 되었다. 따라서 전력중개시장 참여를 위해서는 발전량 예측이 필요하다. 본 논문에서는 자체 개발한 예측 시스템을 활용하여 연축태양광발전소에 대하여 분석하였다. 현장 일사량(모델 1)과 기상청 일사량(모델 2)을 적용한 결과 모델 2가 3% 정도 높은 것을 확인하였다. 또한, DNN과 RNN 모델을 비교 분석한 결과 DNN 모델이 예측 정확도가 1.72% 정도 향상되는 것을 확인하였다.

• 한국자동차공학회논문집
• /
• 제20권6호
• /
• pp.100-106
• /
• 2012

Recently, the demand to acquire and improve durability performance has steadily risen in rubber components design. In design process of a rubber component, an analytical prediction is the most effective way to improve fatigue life. Existing methods of analytical estimation have mainly used an equation for fatigue life obtained from fatigue test data. However, such formula is rarely used due to costs and time required for fatigue testing, as well as randomness of rubber materials. In this paper, we describe fatigue life estimation of rubber component using only the results from a relatively simple tearing test. We estimated fatigue life of the Janggu type fatigue specimen and the automotive motor mount, and evaluated reliability of the proposed method by comparing the estimated values with actual test results.

• 한국기계가공학회지
• /
• 제19권12호
• /
• pp.21-27
• /
• 2020

Lithium-ion batteries are the heart of energy-storing devices and electric vehicles. Owing to their superior qualities, such as high capacity and energy efficiency, they have become quite popular, resulting in an increased demand for failure/damage prevention and useable life maximization. To prevent failure in Lithium-ion batteries, improve their reliability, and ensure productivity, prognosticative measures such as condition monitoring through sensors, condition assessment for failure detection, and remaining useful life prediction through data-driven prognostics and health management approaches have become important topics for research. In this study, the residual useful life of Lithium-ion batteries was predicted using two efficient artificial recurrent neural networks-ong short-term memory (LSTM) and gated recurrent unit (GRU). The proposed approaches were compared for prognostics accuracy and cost-efficiency. It was determined that LSTM showed slightly higher accuracy, whereas GRUs have a computational advantage.

• 전기전자학회논문지
• /
• 제23권1호
• /
• pp.120-126
• /
• 2019

최근 에너지 인터넷에서 지능형 원격검침 인프라를 이용하여 확보된 대량의 전력사용데이터를 기반으로 효과적인 전력수요 예측을 위해 다양한 기계학습기법에 관한 연구가 활발히 진행되고 있다. 본 연구에서는 전력량 데이터와 같은 시계열 데이터에 대해 효율적으로 패턴인식을 수행하는 인공지능 네트워크인 Gated Recurrent Unit(GRU)을 기반으로 딥 러닝 모델을 제안하고, 실제 가정의 전력사용량 데이터를 토대로 예측 성능을 분석한다. 제안한 학습 모델의 예측 성능과 기존의 Long Short Term Memory (LSTM) 인공지능 네트워크 기반의 전력량 예측 성능을 비교하며, 성능평가 지표로써 Mean Squared Error (MSE), Mean Absolute Error (MAE), Forecast Skill Score, Normalized Root Mean Squared Error (RMSE), Normalized Mean Bias Error (NMBE)를 이용한다. 실험 결과에서 GRU기반의 제안한 시계열 데이터 예측 모델의 전력량 수요 예측 성능이 개선되는 것을 확인한다.

• 전기학회논문지P
• /
• 제67권2호
• /
• pp.112-118
• /
• 2018

In recent years, decentralized power have been increasing due to environmental problems, liberalization of electricity markets and technological developments. These changes have led to the evolution of power generation, transmission, and distribution into discrete sectors and the division of integrated power systems. Therefore, studies are underway to efficiently supply power and reduce losses to each sector's demand. This is a major concern for system planners and operators, as it accounts for a relatively high proportion of total power, with a transmission and distribution loss of 4-6%. Therefore, this paper analyzes the status of loss management based on the current transmission and distribution loss rate of each country and transmission loss management cases of each national power company, and proposes a loss rate prediction algorithm according to the long-term transmission system plan. The proposed algorithm predicts the demand-based long-term evolution and the loss rate of the grid to which the transmission plan is applied.

• 환경영향평가
• /
• 제23권3호
• /
• pp.177-186
• /
• 2014

Depending on the change of lifestyle and the improvement of people's living standards and rapid industrialization, urbanization of recent, demand for water is increasing rapidly. So emissions of domestic wastewater and various industrial waste water has increased, and water quality is worsening day by day. Therefore, in order to provide a measure against the occurrence of water pollution accident, this study was tried to simulate water pollution accident. This study simulated 2008 Gimcheon phenol accident using 1,2-D model, and analyze scenario for prevent of water pollution accident. Consequently the developed 1-D model presents high reappearance when compared with 2-D model, and has been able to obtain results in a short simulation run time. This study will contribute to the water pollution incident response prediction system and water quality analysis in the future.

• Journal of Advanced Marine Engineering and Technology
• /
• 제31권5호
• /
• pp.514-521
• /
• 2007

There has been considerable interest recently in the topic of renewable energy. This is primarily due to concerns about environmental impacts. Moreover, fluctuating and rising oil prices, increases in demand, supply uncertainties and other factors have led to increased calls for alternative energy sources. Small hydropower, especially using water supply system, attracts high attentions because of relatively lower cost and smaller space requirements to construct the plant. Moreover. newly developed positive displacement turbine has high acceptability for the system. Therefore, the purpose of this study is focused on the examination of the performance characteristics and proposition of a optimum design method of the turbine for the improvement of the performance. The results show that newly proposed optimum design method for the turbine has high accuracy of performance prediction and good applicability for the performance improvement of the turbine.

• Structural Engineering and Mechanics
• /
• 제52권6호
• /
• pp.1157-1176
• /
• 2014

The objective of this research is to develop a practical design and assessment approach of steel frames with steel slit walls (SSWs) that focuses on the damage-control behavior to enhance the structural resilience. The yielding sequence of SSWs and frame components is found to be a critical issue for the damage-control behavior and the design of systems. The design concept is validated by the full-scale experiments presented in this paper. Based on a modified energy-balance model, a procedure for designing and assessing the system motivated by the framework regarding the equilibrium of the energy demand and the energy capacity is proposed. The damage-control spectra constructed by strength reduction factors calculated from single-degree-of-freedom systems considering the post stiffness are addressed. A quantitative damage-control index to evaluate the system is also derived. The applicability of the proposed approach is validated by the evaluation of example structures with nonlinear dynamic analyses. The observations regarding the structural response and the prediction during selected ground motions demonstrate that the proposed approach can be applied to damage-control design and assessment of systems with satisfactory accuracy.

• 한국인터넷방송통신학회논문지
• /
• 제21권6호
• /
• pp.163-171
• /
• 2021

본 논문은 분산형 전력 시스템에서 심층강화학습 기반의 전력 생산 환경 및 수요와 공급을 예측하며 자원 할당 알고리즘을 적용해 전력거래 시스템 연구의 최적화된 결과를 보여준다. 전력 거래시스템에 있어서 기존의 중앙집중식 전력 시스템에서 분산형 전력 시스템으로의 패러다임 변화에 맞추어 전력거래에 있어서 공동의 이익을 추구하며 장기적인 거래의 효율을 증가시키는 전력 거래시스템의 구축을 목표로 한다. 심층강화학습의 현실적인 에너지 모델과 환경을 만들고 학습을 시키기 위해 날씨와 매달의 패턴을 분석하여 데이터를 생성하며 시뮬레이션을 진행하는 데 있어서 가우시안 잡음을 추가해 에너지 시장 모델을 구축하였다. 모의실험 결과 제안된 전력 거래시스템은 서로 협조적이며 공동의 이익을 추구하며 장기적으로 이익을 증가시킨 것을 확인하였다.