• Journal of Electrical Engineering and Technology
• /
• 제9권3호
• /
• pp.970-977
• /
• 2014

In this paper, the artificial neural network is used to predict the junction temperature of the IGBT power module, by measuring the temperature sensitive electrical parameters (TSEP) of the module. An experiment circuit is built to measure saturation voltage drop and collector current under different temperature. In order to solve the nonlinear problem of TSEP approach as a junction temperature evaluation method, a Back Propagation (BP) neural network prediction model is established by using the Matlab. With the advantages of non-contact, high sensitivity, and without package open, the proposed method is also potentially promising for on-line junction temperature measurement. The Matlab simulation results show that BP neural network gives a more accuracy results, compared with the method of polynomial fitting.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2005년도 창립60주년 기념 추계 학술대회
• /
• pp.27.1-27.1
• /
• 2005

• 태양에너지
• /
• 제7권2호
• /
• pp.37-53
• /
• 1987

This study has been prepared for the purpose of developing the system performance prediction method of natural circulation solar hot water system. The storage tank of the natural circulation solar hot water system equipped with flat-plate solar collector is located at higher elevation than the solar collectors. Therefor, the storage tank temperature distribution formed accordance with configuration of storage tank by flow rate of circulating fluid affect system collection efficiency. In this study measure the storage tank temperature distribution with various experimental system under real sun condition and present the theoretical prediction method of the storage tank temperature. Moreover measure the flow rate not only day-time but also night-time reverse flow rate with die injection visual flow meter. Main conclusion obtain from the present study is as follows; 1) The storage tank temperature distribution above the connecting pipe connection position is the same as that of the fully mixed tank and below the connection position is the same as that of stratified tank. 2) The system performance sensitive to the storage tank temperature distribution. Therefore detailed tank model is necessary. Average storage tank temperature can be calculate 3% and storage tank temperature profile can get less than 10% difference with this model system.

• KIEAE Journal
• /
• 제17권5호
• /
• pp.69-76
• /
• 2017

Purpose: This study aimed at developing an Artificial Neural Network (ANN) model for predicting the amount of cooling energy consumption of the variable refrigerant flow (VRF) cooling system by the different set-points of the control variables, such as supply air temperature of air handling unit (AHU), condenser fluid temperature, condenser fluid pressure, and refrigerant evaporation temperature. Applying the predicted results for the different set-points, the control algorithm, which embedded the ANN model, will determine the most energy efficient control strategy. Method: The ANN model was developed and tested its prediction accuracy by using matrix laboratory (MATLAB) and its neural network toolbox. The field data sets were collected for the model training and performance evaluation. For completing the prediction model, three major steps were conducted - i) initial model development including input variable selection, ii) model optimization, and iii) performance evaluation. Result: Eight meaningful input variables were selected in the initial model development such as outdoor temperature, outdoor humidity, indoor temperature, cooling load of the previous cycle, supply air temperature of AHU, condenser fluid temperature, condenser fluid pressure, and refrigerant evaporation temperature. The initial model was optimized to have 2 hidden layers with 15 hidden neurons each, 0.3 learning rate, and 0.3 momentum. The optimized model proved its prediction accuracy with stable prediction results.

• 한국컴퓨터정보학회논문지
• /
• 제28권11호
• /
• pp.13-20
• /
• 2023

본 논문에서는 LSTM-Autoencoder 기반 특징추출과 재구성 데이터를 이용한 수온 예측 방법을 제안한다. 냉수대 현상이 발생한 동해 낙산 지역의 해수면 수온과 수온에 영향을 미치는 풍향, 풍속 등 다변량 시계열 데이터를 이용하고, LSTM-Autoencoder 모델을 이용하여, 원본 데이터의 차원 축소를 통해 추출된 특징 데이터를 원본 데이터의 다변수 데이터로 결합한 데이터, 복원 데이터, 원본 데이터 총 3가지를 사용한다. 수온 예측을 위해 LSTM 모델에 3가지 데이터를 학습하고, 정확도를 평가한 결과 MAE 0.3652, RMSE 0.5604, MAPE 3.309%으로 LSTM-Autoencoder의 특징추출을 이용한 수온 예측 정확도가 가장 우수한 성능을 보이는 것을 확인하였다. 본 연구의 결과는 냉수대와 같이 해수면 수온 변화가 급변하는 구간의 예측 정확도를 높여, 자연재해의 피해를 예방할 수 있을 것으로 기대한다.

• 한국환경과학회지
• /
• 제33권6호
• /
• pp.435-442
• /
• 2024

We investigated the accuracy of surface air temperature prediction according to the selection of land-use data and initial meteorological data using the Weather Research and Forecasting model-v4.2.1. A numerical experiment was conducted at the Daegu Dyeing Industrial Complex. We initially used meteorological input data from GFS (Global forecast system)and GDAPS (Global data assimilation and prediction system). High-resolution input data were generated and used as input data for the weather model using the land cover data of the Ministry of Environment and the digital elevation model of the Ministry of Land, Infrastructure, and Transport. The experiment was conducted by classifying the terrestrial and topographic data (land cover data) and meteorological data applied to the model. For simulations using high-resolution terrestrial data(10 m), global data assimilation, and prediction system data(CASE 3), the calculated surface temperature was much closer to the automatic weather station observations than for simulations using low-resolution terrestrial data(900 m) and GFS(CASE 1).

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2009년도 춘계학술대회 논문집
• /
• pp.1536-1541
• /
• 2009

When water inside the concrete member evaporates by high temperature, the evaporation heat which absorbs surrounding temperature occurs. The rate of increment of the internal temperature in concrete is reduced due to the evaporation heat in spite of continuously increasing external temperature. In this paper, the prediction method of internal temperature of high strength concrete members considering the evaporation heat under the high temperature is presented. Finite element method is employed to facilitate thermal analysis for any position of member. And the thermal characteristics models of high strength concrete affected by high temperature are proposed. To demonstrate the validity of this numerical procedure, the prediction by the proposed algorithm is compared with the test results of other researchers. The proposed algorithm shows a good agreement with the experimental results including the phenomenon that temperature is lost by the evaporation heat.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제17권2호
• /
• pp.92-102
• /
• 2017

Purpose: Reliability prediction standards consider environmental conditions, such as temperature, humidity and vibration in order to predict the reliability of the electronics components. There are many types of standards, and each standard has a different failure rate prediction model, and requires different environmental conditions. The purpose of this study is to make a sensitivity analysis by changing the temperature which is one of the environmental conditions. By observing the relation between the temperature and the failure rate, we perform the sensitivity analysis for standards including MIL-HDBK-217F, RiAC-HDBK-217Plus and FIDES. Methods: we establish environmental conditions in accordance with maneuver weapon systems's OMS/MP and mission scenarios then predict the reliability using MIL-HDBK-217F, RiAC-HDBK-217Plus and FIDES through the case of DC-DC Converter. Conclusion: Reliability prediction standards show different sensitivities of their failure rates with respect to the changing temperatures.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2016년도 춘계 학술논문 발표대회
• /
• pp.199-200
• /
• 2016

Accurate fire diagnoses are needed to properly repair and strengthen buildings affected by fire. The current diagnosis method of fire takes time and is ineffective. In previous research, Melting point temperature of each sequence to grasp easily the temperature of the concrete up to 200 ~ 600 ℃ was to estimate the temperature by utilizing a different sequence representing material.But In the form of conventional hydrothermal temperature prediction simple measuring device, it is difficult in the future buried in application to the construction site, there is a problem of damage when concrete pouring, and only the extension of life measured by the zinc has a problem does not distinguish between 400 ℃ and 500 ℃. Therefore this study is conducted by utilizing a titanium metal changes the color depending on the temperature to check for the applicability of the simple apparatus for measuring the temperature prediction sequence.

• 대한기계학회논문집
• /
• 제17권9호
• /
• pp.2271-2279
• /
• 1993

In the case of life prediction on the structures and machines after long service, it is natural to consider a degradation problems. Most of degradation data form practical structures are isolated data obtained at the time of periodical inspection or repair. From such data, it may be difficult to obtain the degradation curve available and necessary for life prediction. In this paper, for the purpose of obtaining a degradation curves, developed the simulate degradation method and fatigue test and Charpy impact test were conducted on the degraded, simulate degraded and recovered materials. Fatigue life prediction were conducted by using the relationship between fracture transition temperature (DBTT : vTrs) obtained from the Charpy impact test through the degradation process and fatigue crack growth constants of m and C obtained from the fatigue test.