• IE interfaces
• /
• v.24 no.4
• /
• pp.351-361
• /
• 2011

Forecasting of electricity demand have difficulty in adapting to abrupt weather changes along with a radical shift in major regional and global climates. This has lead to increasing attention to research on the immediate and accurate forecasting model. Technically, this implies that a model requires only a few input variables all of which are easily obtainable, and its predictive performance is comparable with other competing models. To meet the ends, this paper presents an energy demand forecasting model that uses the variable selection or extraction methods of data mining to select only relevant input variables, and employs support vector regression method for accurate prediction. Also, it proposes a novel performance measure for time-series prediction, shift index, followed by description on preprocessing procedure. A comparative evaluation of the proposed method with other representative data mining models such as an auto-regression model, an artificial neural network model, an ordinary support vector regression model was carried out for obtaining the forecast of monthly electricity demand from 2000 to 2008 based on data provided by Korea Energy Economics Institute. Among the models tested, the proposed method was shown promising results than others.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2005.10a
• /
• pp.469-478
• /
• 2005

Understanding of an accurate state of consolidation of underconsolidated clay body, like a recently dredged or reclaimed clay deposits, is one of the most difficult tasks. The estimation of the consolidation status of these clay bodies is often made by laboratory tests of numerical analyses. However these methods demonstrated crucial limitations in the accurate prediction. Therefore, the predicted degree of consolidation from various techniques is verified by actual measured field data. The degree of consolidation of clay body in the East Side Hinterland of Gwangyang Port(2nd Phase) is evaluated in this study by using various techniques such as oedometer test, CPTu, numerical analysis and piezometer tests etc. And the results are compared each other to find the most reliable prediction technique. The merit and reliability of each method is discussed in detail. It is revealed from in this study that the estimation of degree of consolidation by an actual pore water pressure measurements is the most reliable technique.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11b
• /
• pp.122-127
• /
• 2002

A frequency-domain PES estimation and its prediction method are proposed for the tightly-coupled servo/mechanical design of high-TPI HDD system above 100 kTPI. The major two disturbance energies which are related with mechanical vibrations inside of HDD are used to predict the drive-level PES, while considering closed-loop servo dynamics. One is the torque disturbance which mainly comes from aerodynamic excitation of HSA system and the other is the displacement disturbance from disk-spindle dynamics. In order to obtain the accurate error transfer function of closed-loop servo control, the plant model is measured by accurate experiment. The measured PES is compared with predicted one in terms of frequency-domain PES spectrum and its standard variation value. It is proved that the proposed frequency-domain PES estimation/prediction method is capable of predicting drive-level PES of high-TPI hard disk drive.

• Earthquakes and Structures
• /
• v.11 no.4
• /
• pp.723-740
• /
• 2016

Reinforced concrete corbels are generally used to transfer loads within a structural system, such as buildings, bridges, and facilities in general. They commonly present low aspect ratio, requiring an accurate model for shear strength prediction in order to promote flexural behavior. The model described here, originally developed for walls, was adapted for corbels. The model is based on a reinforced concrete panel, described by constitutive laws for concrete and steel and applied in a fixed direction. Equilibrium in the orthogonal direction to the shearing force allows for the estimation of the shear stress versus strain response. The original model yielded conservative results with important scatter, thus various modifications were implemented in order to improve strength predictions: 1) recalibration of the strut (crack) direction, capturing the absence of transverse reinforcement and axial load in most corbels, 2) inclusion of main (boundary) reinforcement in the equilibrium equation, capturing its participation in the mechanism, and 3) decrease in aspect ratio by considering the width of the loading plate in the formulation. To analyze the behavior of the theoretical model, a database of 109 specimens available in the literature was collected. The model yielded an average model-to-test shear strength ratio of 0.98 and a coefficient of variation of 0.16, showing also that most test variables are well captured with the model, and providing better results than the original model. The model strength prediction is compared with other models in the literature, resulting in one of the most accurate estimates.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.49 no.1
• /
• pp.37-42
• /
• 2000

The radio noise produced by corona discharge in high voltage transmission lines is one of the most important line design considerations. Therefore it is necessary for transmission line designers to pre-evaluate radio noise using prediction formulas or field test results. In this paper, more accurate and useful formulas for predicting radio noise during fair and foul weathers in high voltage AC transmission lines were proposed through comparison with the existing formulas. Also it was verified by comparing with the long-term measured data from operating lines that the proposed formulas are more accurate. The proposed prediction formulas are developed by the applications of nonlinear least squares optimization method to radio noise database collected from lines throughout the world.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.10a
• /
• pp.368-373
• /
• 2003

A major concern at present is the simultaneous control of transverse thickness profile and flatness in the finishing stages of hot rolling process. The mathematical modeling of hot rolling process has long been recognized to be a desirable approach to investigate rolling operating practice and the design of mill equipment to improve productivity and quality. However, many factors make the mathematical analysis of the rolling process very complex and time-consuming. In order to overcome these problems and to obtain an accurate rolling force, the predicted model of rolling force using neural networks has widely been employed. In this paper, Radial Basis Function Network(RBFN) is applied to improve the accuracy of rolling force prediction in hot rolling mill. In order to verify and analysis the performance of applied neural network, the comparison with the measured rolling force and the predicted results using two different neural networks - RBFN, MLP, has respectively been carried out. The results obtained using RBFN neural network are much more accurate those obtained the MLP.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.13 no.6
• /
• pp.29-33
• /
• 2004

A major concern at present is the simultaneous control of transverse thickness profile and flatness in the finishing stages of hot rolling process. The mathematical modeling of hot rolling process has long been recognized to be a desirable approach to investigate rolling operating practice and the design of mill equipment to improve productivity and quality. However, many factors make the mathematical analysis of the rolling process very complex and time-consuming. In order to overcome these problems and to obtain an accurate rolling force, the predicted model of rolling force using neural networks has widely been employed. In this paper, Radial Basis Function Network(RBFN) is applied to improve the accuracy of rolling force prediction in hot rolling mill. In order to verify and analyze the performance of applied neural network the comparison with the measured rolling force and the predicted results using two different neural networks-RBFN, MLP, has respectively been carried out. The results obtained using RBFN neural network are much more accurate those obtained the MLP.

• Journal of ILASS-Korea
• /
• v.5 no.2
• /
• pp.53-60
• /
• 2000

An aerodynamically progressed model, which is called APTAB model. has been proposed for more accurate prediction of the deformation and breakup of a spray. Especially, the effects of the droplet deformation on the droplet aerodynamic external force are considered in this model, which was neglected in TAB model. It is found that the predicted droplet deformation using APTAB model shows better agreement with experimental data than those of other models for the droplets in both bag-type and shear-type breakup regimes. A new breakup criterion has been proposed to predict more reasonable breakup quantities, such as breakup deformation length, time and so on; i.e., it is defined that the breakup occurs when the internal liquid phase pressure of the deformed droplet at the equator is greater than that of the pole. The proposed breakup criterion shows more physical relationship between the degree of droplet deformation at breakup and the corresponding breakup Weber number as compared with the results with TAB and DDB models. Therefore, it provides better predictions of the experimental data than TAB and DDB models for the droplet deformation and time in both bag-type and shear-type breakup regimes.

• Journal of Korean Society for Atmospheric Environment
• /
• v.23 no.6
• /
• pp.752-759
• /
• 2007

For an accurate measurement of aerosol particle size distribution using a differential mobility analyser (DMA), a new calculation process, capable of predicting the masses for the various kinds of water cluster ions generated from a bipolar ionizer, was prepared by improving the previous process. The masses for the 5 kinds of positive and negative water cluster ions produced from a SMAC ionizer were predicted by the improved calculation process. The aerosol particle charging ratios calculated by applying the predicted ion masses to particle charging equations were in good accordance with the experimentally measured ones, indicating that the improved calculation process are more reasonable than the previous one in a mass prediction of bipolar water cluster ions.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2013.04a
• /
• pp.311-318
• /
• 2013

The paper describes the prediction method for the unsteady flow field and the aeroacoustic noise of an small axial fan. The prediction method is comprised of various CFD conditions and acoustic analogy by using Ffowcs Williams-Hawkings equation. The diameter of tested axial fan is 170 mm and number of blade is 5. Virtual anechoic room which has same size with real one was used for CFD. URANS and LES models were used. For mesh dependence study, a different mesh type was tested and optimized mesh was selected. Calculation conditions were also studied such as time step and turbulence model for accurate noise analysis. In this paper, we got optimum analysis conditions and computational results. The unsteady pressure fluctuation at given 4 points were compared between the measured data and computational results. Also, the predicted acoustic spectrum at 3 given microphone points were compared with measured ones.