• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권7호
• /
• pp.307-314
• /
• 2022

최근 전력수요를 예측하기 위해 통계기반 시계열 분석 기법을 대체하기 위해 딥러닝 기법을 활용한 연구가 활발히 진행되고 있다. 딥러닝 기반 전력수요 예측 연구 결과를 분석한 결과, LSTM 기반 예측 모델의 성능이 우수한 것으로 규명되었으나 장기간의 지역 범위 전력수요 예측에 대해 LSTM 기반 모델의 성능이 충분하지 않음을 확인할 수 있다. 본 연구에서는 기온 데이터를 반영하여 24시간 이전에 전력수요를 예측하는 WaveNet 기반 딥러닝 모델을 개발하여, 실제 사용하고 있는 통계적 시계열 예측 기법의 정확도(MAPE 값 2%)보다 우수한 예측 성능을 달성하는 모델을 개발하고자 한다. 먼저 WaveNet의 핵심 구조인 팽창인과 1차원 합성곱 신경망 구조를 소개하고, 전력수요와 기온 데이터를 입력값으로 모델에 주입하기 위한 데이터 전처리 과정을 제시한다. 다음으로, 개선된 WaveNet 모델을 학습하고 검증하는 방법을 제시한다. 성능 비교 결과, WaveNet 기반 모델에 기온 데이터를 반영한 방법은 전체 검증데이터에 대해 MAPE 값 1.33%를 달성하였고, 동일한 구조의 모델에서 기온 데이터를 반영하지 않는 것(MAPE 값 2.31%)보다 우수한 전력수요 예측 결과를 나타내고 있음을 확인할 수 있다.

• Journal of Biosystems Engineering
• /
• 제24권1호
• /
• pp.31-40
• /
• 1999

The objective of this study were to develop a cooling simulation model for fixed-bed of rough rice and to analyze the factors affecting cooling time of rough rice. A computer simulation model based on equilibrium conditions between grain and air was developed to predict temperature and moisture content changes during cooling of rough rice. the result of t-test showed that there were no significant differences between predicted and measured temperature changes on significance model agreed well with measured values. This cooling simulation model was applied to analyze the effect of some factors, such as air flow rate, cooling air temperature and humidity, initial grain temperature and moisture content, and bed depth, on cooling time of rough rice. Cooling rate increased with increase of air flow rate and bed depth whereas it decreased with increase of cooling air temperature and humidity and initial grain temperature. Among these factors, the most important factor was air flow rate. Specific air flow rate of 0.35㎥/min㎥ was required for cooling rough rice in 24 hours.

• 대한전기학회논문지
• /
• 제45권4호
• /
• pp.511-516
• /
• 1996

In this paper, weekly maximum power demand forecasting method in consideration of temperature estimation using a time series model was presented. The method removing weekly, seasonal variations on the load and irregularities variation due to unknown factor was presented. The forecasting model that represent the relations between load and temperature which get a numeral expected temperature based on the past 30 years(1961~1990) temperature was constructed. Effect of holiday was removed by using a weekday change ratio, and irregularities variation was removed by using an autoregressive model. The results of load forecasting show the ability of the method in forecasting with good accuracy without suffering from the effect of seasons and holidays. Percentage error load forecasting of all seasons except summer was obtained below 2 percentage. (author). refs., figs., tabs.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2014년도 추계 학술논문 발표대회
• /
• pp.26-27
• /
• 2014

Study on high temperature properties of concrete and internal force estimation of structural member subjected to high temperature mainly applied high temperature strength model based on experimental results with concrete under 40MPa. However, it is reported that degradation of internal force at high temperature and spalling of ultra high strength concrete are higher than that of normal strength concrete. Therefore, this study attempts to propose compressive strength degradation model which is suitable to ultra high strength concrete comparing to existing model by evaluating high temperature properties of ultra high strength concrete.

• Journal of Advanced Marine Engineering and Technology
• /
• 제28권7호
• /
• pp.1063-1071
• /
• 2004

Accurate heat release analysis of cylinder pressure data is important for evaluating performance in the development of diesel engine However, traditional single zone first law heat release model(SZM) has significant limitations due to the simplified assumption of uniform charge and neglecting local temperature inside cylinder during combustion process. In this study. heat release rate based on single zone heat release model has been evaluated by comparison with computational analysis results using Fire code which is based on multi-dimensional model(MDM). To overcome limitations due to simplicity of single zone assumption. especially the influence of specific heat ratio on gross heat release has been esteemed and newly suggested were the equation $\gamma$= $\gamma$(${T/T}_{max}$) which describes the variations of gases thermodynamic properties with mean temperature and maximum mean temperature inside cylinder Single zone heat release model applied with this equation is shown to give very good results over whole range of operating conditions when compared with computational analysis results based on multi-dimensional model.

• 한국주조공학회지
• /
• 제22권1호
• /
• pp.11-16
• /
• 2002

Hot deformation behavior of GCD-50 cast iron has been investigated by employing the compressive test. Phenomenological deformation behaviors, which were modeled based on the dynamic materials model and the kinetic model, have been correlated with the microstructural change taken place during compression. Microstructural investigation revealed that the adiabatic shear band caused by the locallized deformation was taken place in low temperature and high strain rate. On the other hand, the wavy and curved grain boundaries, which repersent the occurrence of dynamic microstructure change such as dynamic recovery and dynamic recrystallization, were observed in high temperature and low strain rate. Deformation model based on hyperbolic sine law has also been suggested.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 하계학술대회 논문집 B
• /
• pp.673-675
• /
• 1995

A nonlinear process-model based control for main steam temperature control of a 100MW oil-fired drum-type fossil power plant is delveloped and its performances are compared to those of the conventional PID control. The process model for simulation is derived based "first priciple approach" and is validated in steady and transient conditions. The model is in good agreements with the field test data. Performances of the nonlinear PMBC for main steam temperature control are far superior to those of PID in all aspects for the disturbances of ramp increase in load and step change in fuel Btu value.

• 환경위생공학
• /
• 제15권2호
• /
• pp.65-74
• /
• 2000

The purpose of this study is to develop the stochastic stream water quality model for the intake station of Chung-Ju city waterworks in the Han river system. This model was based on the theory of Box-Jenkins Multiplicative ARIMA(SARIMA) and the state space model to simulate changes of water qualities. Variable of water qualities included in the model are temperature and dissolved oxygen(DO). The models development were based on the data obtained from Jan. 1990 to Dec. 1997 and followed the typical procedures of the Box-Jenkins method including identification and estimation. The seasonality of DO and temperature data to formulate for the SARIMA model are conspicuous and the period of revolution was twelve months. Both models had seasonality of twelve months and were formulates as SARIMA {TEX}$(2,1,1)(1,1,1)_{12}${/TEX} for DO and temperature. The models were validated by testing normality and independency of the residuals. The prediction ability of SARIMA model and state space model were tested using the data collected from Jan. 1998 to Oct. 1999. There were good agreements between the model predictions and the field measurements. The performance of the SARIMA model and state space model were examined through comparisons between the historical and generated monthly dissolved oxygen series. The result reveal that the state space model lead to the improved accuracy.

• 콘크리트학회논문집
• /
• 제12권6호
• /
• pp.35-42
• /
• 2000

In paper I, the relationships between compressive strength and splitting tensile strength or modulus of elasticity were proposed. In this paper, new prediction model is investigated from estimating splitting tensile strength and modulus of elasticity with curing temperature and aging without compressive strength. New prediction model is based on the model which was proposed to predict compressive strength, and splitting tensile strength and modulus of elasticity calculated by this model are compared with experimental values of paper I. To evaluate in-situ applicability of the model, strength and modulus of elasticity tested with variable temperatures are estimated by the prediction model. The prediction model reasonably estimates the strength and the modulus of elasticity of type I and V cement concretes tested in paper I and experimental results with variable temperature tested in this paper.

• 한국토양비료학회지
• /
• 제46권5호
• /
• pp.359-364
• /
• 2013

This study was conducted to develop a model to estimate crop leaf surface temperature. The results were as following; A definition for the daily time based on elapsed time from the midnight (00:00) as "E&E time" with the unit of Kmin. was suggested. The model to estimate the scaled temperature ($T^*e$) of crop leaf surface temperature by scale factor ($T^*$) according to the "E&E time : Kmin."(X) was developed as eq. (1) $T^*e=0.5{\cdot}sin(X+780)+0.5$ (2) $T^*=(Tx-Tn)/(Tm-Tn)$, Tx : Daily leaf temperature, Tm : Daily maximum leaf temperature, Tn : Daily minimum leaf temperature. Relative sensitivity of the measured temperature compared to the estimated temperature of red pepper, soybean and persimmon was 1.078, 1.033 and 0.973, respectively.