• 한국항해학회지
• /
• 제24권3호
• /
• pp.147-155
• /
• 2000

In this paper, we propose the Chaos Fuzzy controller to analyze the chaotic character of time series obtained from the specific plant and to predict the short-term for power consumption of the plant using the Fuzzy controller. We compared the predicted data with the active ones and checked the error generated by them after we time series of supplied power to the proposed controller. As a result of the simulation, we obtained a admirable consequence that the proposed controller can be advanced through various and accurate data acquisition, and continuous analysis of the resident and industrial environment.

• Nuclear Engineering and Technology
• /
• 제53권8호
• /
• pp.2610-2615
• /
• 2021

The prediction of irradiation-induced transition temperature shift for RPV steels is an important method for long term operation of nuclear power plant. Based on the irradiation embrittlement data, an irradiation-induced transition temperature shift prediction model is developed with machine learning method XGBoost. Then the residual, standard deviation and predicted value vs. measured value analysis are conducted to analyze the accuracy of this model. At last, Cu content threshold and saturation values analysis, temperature dependence, Ni/Cu dependence and flux effect are given to verify the reliability. Those results show that the prediction model developed with XGBoost has high accuracy for predicting the irradiation embrittlement trend of RPV steel. The prediction results are consistent with the current understanding of RPV embrittlement mechanism.

• 한국항행학회논문지
• /
• 제21권4호
• /
• pp.365-370
• /
• 2017

본 연구는 전력수요 패턴이 다른 평일과 특수일 데이터가 가지는 상관관계를 분석하여, 별도의 데이터 셋을 구축하고, 각 데이터 셋에 적합한 딥 러닝 네트워크를 이용하여, 전력수요예측 오차를 감소하는 방안을 제시하였다. 또한, 기본적인 전력수요 예측요소인 기상요소에 환경요소, 구분요소 등 다양한 예측요소를 추가하여 예측율을 향상하는 방안을 제시하였다. 전체데이터는 시계열 데이터 학습에 적합한 LSTM을 이용하여 전력수요예측을 하였으며, 특수일 데이터는 DNN을 이용하여 전력수요예측을 하였다. 실험결과 기상요소 이외의 예측요소 추가를 통해 예측율이 향상되었다. 전체 데이터 셋의 평균 RMSE는 LSTM이 0.2597이며, DNN이 0.5474로 LSTM이 우수한 예측율을 보였다. 특수일 데이터 셋의 평균 RMSE는 0.2201로 DNN이 LSTM보다 우수한 예측율을 보였다. 또한, 전체 데이터 셋의 LSTM의 MAPE는 2.74 %이며, 특수 일의 MAPE는 3.07 %를 나타냈다.

• 산업경영시스템학회지
• /
• 제39권1호
• /
• pp.64-72
• /
• 2016

In this paper, we utilize a Gaussian process to predict the power consumption in the air-conditioning system. As the power consumption in the air-conditioning system takes a form of a time-series and the prediction of the power consumption becomes very important from the perspective of the efficient energy management, it is worth to investigate the time-series model for the prediction of the power consumption. To this end, we apply the Gaussian process to predict the power consumption, in which the Gaussian process provides a prior probability to every possible function and higher probabilities are given to functions that are more likely consistent with the empirical data. We also discuss how to estimate the hyper-parameters, which are parameters in the covariance function of the Gaussian process model. We estimated the hyper-parameters with two different methods (marginal likelihood and leave-one-out cross validation) and obtained a model that pertinently describes the data and the results are more or less independent of the estimation method of hyper-parameters. We validated the prediction results by the error analysis of the mean relative error and the mean absolute error. The mean relative error analysis showed that about 3.4% of the predicted value came from the error, and the mean absolute error analysis confirmed that the error in within the standard deviation of the predicted value. We also adopt the non-parametric Wilcoxon's sign-rank test to assess the fitness of the proposed model and found that the null hypothesis of uniformity was accepted under the significance level of 5%. These results can be applied to a more elaborate control of the power consumption in the air-conditioning system.

• 전자공학회논문지D
• /
• 제34D권4호
• /
• pp.62-72
• /
• 1997

The optical power splitter/couplers based on MMI(multimode interference) in GaAs/AlGaAs are studied. We presetn a design of optical power splitter/couplers, which have deeply etched multimode waveguide. The properties and fabrication tolerance on the etching depth, multimode waveguide width are simulatedusing a FD-BPM (finite difference beam propgation method). Proposed 1*N optical of designed device is 0.7dB smaller than the optical power splitter with a shallowly etched MMI section. For 0.5dB excess loss, the predicted fabrication tolerance is 0.6.mu.m on the multimode waveguide width of the 14 optical power splitter with a deeply etched MMI section. Also excess loss and uniformity of poposed 32*32 optical power coupler are below 0.3dB. The excess loss of proposed 32*32 optical power coupler is 2dB smaller than the optical power coupler with a shallowly etched MMI section. It is shown that the optical power splitters/couplers with a deeply etched mMI section have low loss, good uniformity, and improved fabriction tolerance.

• Nuclear Engineering and Technology
• /
• 제34권1호
• /
• pp.68-79
• /
• 2002

The approach for evaluating the critical heat flux (CHF) margin using the departure from nucleate boiling ratio (DNBR) concept has been widely applied to PWR core design, while DNBR in this approach does not indicate appropriately the CHF margin in terms of the attainable power margin-to-CHF against a reactor core condition. The CHF power margin must be calculated by increasing power until the minimum DNBR reaches a DNBR limit. The Critical Power Ratio (CPR), defined as the ratio of the predicted CHF power to the operating power, is considered more reasonable for indicating the CHF margin and can be calculated by a CPR orrelation based on the heat balance of a test bundle. This approach yields directly the CHF power margin, but the calculated CPR must be corrected to compensate for many local effects of the actual core, which are not considered in the CHF test and analysis. In this paper, correction of the calculated CPR is made so that it may become equal to the DNB overpower margin. Exemplary calculations showed that the correction tends to be increased as power distribution is more distorted, but are not unduly large.

• 한국음향학회지
• /
• 제43권2호
• /
• pp.162-167
• /
• 2024

풍력발전기에서 방사되는 저주파 소음은 가장 관심이 높은 불만족 사항 중의 하나이다. 이에 본 연구에서는 공학적으로 유용하게 사용할 수 있는 덴마크 모델과 ISO 9613에 기초한 상용 프로그램인 SoundPLAN과 ENPro에 의한 풍력발전기 저주파 소음 예측값들과 측정값을 비교함으로써 모델들에 대한 신뢰성을 살펴보았다. 육상에서 대표적인 3 MW급 풍력발전기를 대상으로 적용한 결과 주파수 12.5 Hz에서 80 Hz 범위에서 측정값과 예측값은 최대 5 dB 이내의 차이를 보였다. 이러한 원인으로는 대상 풍력발전기는 7년 이상 운영되었기 때문에 음향파워레벨의 변화가 생겼기 때문으로 추정할 수 있다. 하지만 저주파 대역에서 가장 정확하다고 할 수 있는 Boundary Element Method (BEM) 예측값과 다른 모델에 의한 예측값 그리고 측정값은 2.5 dB 이내로 잘 일치한 점을 고려할 때 본 연구 대상의 모델들은 3 dB 이내의 편차로 활용될 수 있을 것으로 기대된다.

• Tribology and Lubricants
• /
• 제35권5호
• /
• pp.300-309
• /
• 2019

Gas foil thrust bearings (GFTBs) support axial loads in oil-free, high speed rotating machinery using air or gas as a lubricant. Due to the inherent low viscosity of the lubricant, GFTBs often have super-laminar flows in the film region at operating conditions with high Reynolds numbers. This paper develops a mathematical model of a GFTB with turbulent flows and validates the model predictions against those from the literature. The pressure distribution, film thickness distribution, load carrying capacity, and power loss are predicted for both laminar and turbulent flow models and compared with each other. Predictions for an air lubricant show that the GFTB has high Reynolds numbers at the leading edge where the film thickness is large and relatively low Reynolds numbers at the trailing edge. The predicted load capacity and power loss for the turbulent flow model show little difference from those for the laminar flow model even at the highest speed of 100 krpm, because the Reynolds numbers are smaller than the critical Reynolds number. On the other hand, refrigerant (R-134a) lubricant, which has a higher density than air, had significant differences due to high Reynolds numbers in the film region, in particular, near the leading and outer edges. The predicted load capacity and power loss for the turbulent flow model are 2.1 and 2.3 times larger, respectively, than those for the laminar flow model, thus implying that the turbulent flow greatly affects the performance of the GFTB.

• 한국소음진동공학회논문집
• /
• 제23권4호
• /
• pp.308-314
• /
• 2013

The vibration and stress analysis program of comprehensive vibration assessment program(CVAP) is to theoretically verify the structural integrity of reactor vessel internals(RVI) and to provide the basis for selecting the locations monitored in measurement and inspection programs. This paper covers the applicability of the vibration and stress analysis method of APR1400 RVI CVAP. The analysis method was developed to use 3-dimensional detail hydraulic and structural models with ANSYS and CFX. To assess the method, the hydraulic loads and structural reponses of OPR1000 were predicted and compared with the measured data in the OPR1000 RVI CVAP. The results predicted with this method were close to the measured values considerably. Therefore, the analysis method was developed properly.

• 한국컴퓨터산업학회논문지
• /
• 제3권5호
• /
• pp.547-556
• /
• 2002

본 논문은 MLP 모델과 전파 특성 파라미터를 이용하여 실내환경에서 무선근거리통신망에 대한 전파 경로 손실 예측 알고리듬을 제안하였다. 100mW의 송신출력과 2.4GHz의 주파수를 갖는 무선근거리통신망에 대한 실내 경로손실을 예측하고 측정된 값과 비교하였다. 비교된 측정값과 예측값 사이의 차이는 다양한 경로손실 요인들에 대한 정확한 분석을 통하여 감소시킬 수 있다. 제안된 전파 경로 손실 예측 모델을 이용하여 특정 실내환경에서의 AP 위치를 선정함으로써 최적 셀 설계를 수행하였다.