• Journal of the Korean Solar Energy Society
• /
• v.39 no.5
• /
• pp.41-52
• /
• 2019

The purpose of the work is to develop a simple solar irradiance prediction model using a deep learning method, the LSTM (long term short term memory). Other than existing prediction models, the proposed one uses only the cloudiness among the information forecasted from the national meterological forecast center. The future cloudiness is generally announced with four categories and for three-hour intervals. In this work, a daily irradiance pattern is used as an input vector to the LSTM together with that cloudiness information. The proposed model showed an error of 5% for learning and 30% for prediction. This level of error has lower influence on the load prediction in typical building cases.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.4
• /
• pp.907-914
• /
• 1999

This paper studies on the model identification of electro-hydraulic servo systems, which are composed of servo valves, double-rod cylinder and load mass. The identified plant is described as a discrete-time ARX or ARMAX model which is respectively obtained from the identification algorithms of least square error method, instrumental variable method and prediction error method. where a nominal model and the variation of model parameters are quantitatively evaluated.

• KIEAE Journal
• /
• v.17 no.4
• /
• pp.83-88
• /
• 2017

Purpose: The objective of this study is to develop a predictive model for calculating the amount of cooling load for the different setback temperatures during the setback period. An artificial neural network (ANN) is applied as a predictive model. The predictive model is designed to be employed in the control algorithm, in which the amount of cooling load for the different setback temperature is compared and works as a determinant for finding the most energy-efficient optimal setback temperature. Method: Three major steps were conducted for proposing the ANN-based predictive model - i) initial model development, ii) model optimization, and iii) performance evaluation. Result:The proposed model proved its prediction accuracy with the lower coefficient of variation of the root mean square errors (CVRMSEs) of the simulated results (Mi) and the predicted results (Si) under generally accepted levels. In conclusion, the ANN model presented its applicability to the thermal control algorithm for setting up the most energy-efficient setback temperature.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.1
• /
• pp.38-50
• /
• 2018

Spatio-temporal load forecasting (STLF) is a foundation for building the prediction-based power map, which could be a useful tool for the visualization and tendency assessment of urban energy application. Constructing one point-forecasting model for each electricity cell in the geographic space is possible; however, it is unadvisable and insufficient, considering the aggregation features of electricity cells and uncertainties in input variables. This paper presents a new STLF method, with a data-driven framework consisting of 3 subroutines: multi-level clustering of cells considering their aggregation features, load regression for each category of cells based on SLS-SVRNs (sparse least squares support vector regression networks), and interval forecasting of spatio-temporal load with sampled blind number. Take some area in Pudong, Shanghai as the region of study. Results of multi-level clustering show that electricity cells in the same category are clustered in geographic space to some extent, which reveals the spatial aggregation feature of cells. For cellular load regression, a comparison has been made with 3 other forecasting methods, indicating the higher accuracy of the proposed method in point-forecasting of spatio-temporal load. Furthermore, results of interval load forecasting demonstrate that the proposed prediction-interval construction method can effectively convey the uncertainties in input variables.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1999.03b
• /
• pp.71-75
• /
• 1999

An approximate similarity theory has been applied to predict the forming load of non-axisymmetric forging of aluminum alloys through model material tests. The approximate similarity theory is applicable when strain rate sensitivity geometrical size and die velocity of model materials are different from those of real materials. Actually the forming load of yoke which is an automobile part made of aluminum alloys(Al-6061) is predicted by using this approximate similarity theory. Firstly upset forging tests are have been carried out to determine the flow curves of three model materials and aluminum alloy(Al-6061) and a suitable model material is selected for model material test of Al-6061 And then and forging tests of aluminum yokes have been performed to verify the forming load predicted from the model material which has been selected from above upset forging tests, The forming loads of aluminum yoke forging predicted by this approximate similarity theory are in good agreement with the experimental results of Al-6061 and the results of finite element analysis using DEFORM-3D.

• Environmental Engineering Research
• /
• v.10 no.2
• /
• pp.62-70
• /
• 2005

Pollution loading of Combined Sewer Overflows (CSOs) is frequently over the capacity of a wastewater treatment plant (WWTP) receiving the water. The objectives of this study are to investigate water quality of CSOs in Anmyun-ueup, Tean province and to apply Storm Water Management Model to predict flow rate and water quality of the CSOs. The capacity of a local WWTP was also estimated according to rainfall duration and intensity. Eleven water quality parameters were analyzed to characterize overflows. SWMM model was applied to predict the flow rate and pollutant load of CSOs during rain event. Overall, profile of the flow and pollutant load predicted by the model well followed the observed data. Based on model prediction and observed data, CSOs frequently occurs in the study area, even with light precipitation or short rainfall duration. Model analysis also indicated that the local WWTP’s capacity was short to cover the CSOs.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.4
• /
• pp.129-134
• /
• 2018

Recently, the artificial neural network (ANN) model is a promising technique in the prediction, numerical control, robot control and pattern recognition. We predicted the outside temperature of greenhouse using ANN and utilized the model in greenhouse control. The performance of ANN model was evaluated and compared with multiple regression model(MRM) and support vector machine (SVM) model. The 10-fold cross validation was used as the evaluation method. In order to improve the prediction performance, the data reduction was performed by correlation analysis and new factor were extracted from measured data to improve the reliability of training data. The backpropagation algorithm was used for constructing ANN, multiple regression model was constructed by M5 method. And SVM model was constructed by epsilon-SVM method. As the result showed that the RMSE (Root Mean Squared Error) value of ANN, MRM and SVM were 0.9256, 1.8503 and 7.5521 respectively. In addition, by applying the prediction model to greenhouse heating load calculation, it can increase the income by reducing the energy cost in the greenhouse. The heating load of the experimented greenhouse was 3326.4kcal/h and the fuel consumption was estimated to be 453.8L as the total heating time is $10000^{\circ}C/h$. Therefore, data mining technology of ANN can be applied to various agricultural fields such as precise greenhouse control, cultivation techniques, and harvest prediction, thereby contributing to the development of smart agriculture.

• Journal of Biosystems Engineering
• /
• v.16 no.3
• /
• pp.281-289
• /
• 1991

During the storage and transport of fruits in the bulk state, significant damage by dead load may occur. To reduce such damage, the prediction model of allowable pile depth, duration and optimum thickness of packaging cushion for fruits was developed in this study. From the preliminary experiment and some assumptions, the derived equations were verified to be a good prediction of the above three parameters.

• Computers and Concrete
• /
• v.8 no.3
• /
• pp.343-355
• /
• 2011

This paper presented the model to predict the chloride diffusion coefficient in tension zone of plain concrete under flexural cyclic load. The fictitious crack based analytical model was used together with the stress degradation law in cracked zone to predict crack growth of plain concrete beams under flexural cyclic load. Then, under cyclic load, the chloride diffusion, in the steady state and one dimensional regime, through the tension zone of the plain concrete beam, in which microcracks were formed by a large number of cycles, was simulated with assumptions of continuously straight crack and uniform-size crack. The numerical analysis in terms of the chloride diffusion coefficient, $D_{tot}$, normalized $D_{tot}$, crack width and crack length was issued as a function of the load cycle, N, and load level, SR. The nonlinear model as regarding with the chloride diffusion coefficient in tension zone and the load level was proposed. According to this model, the chloride diffusion increases with increasing load level. The predictions using model fit well with experimental data when we adopted suitable crack density and tortuosity parameter.

• Earthquakes and Structures
• /
• v.7 no.6
• /
• pp.1061-1070
• /
• 2014

An iterative hybrid structural dynamic reliability prediction model has been developed under multiple-time interval loads with and without consideration of stochastic structural strength degradation. Firstly, multiple-time interval loads have been substituted by the equivalent interval load. The equivalent interval load and structural strength are assumed as random variables. For structural reliability problem with random and interval variables, the interval variables can be converted to uniformly distributed random variables. Secondly, structural reliability with interval and stochastic variables is computed iteratively using the first order second moment method according to the stress-strength interference theory. Finally, the proposed method is verified by three examples which show that the method is practicable, rational and gives accurate prediction.