• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.54 no.10
• /
• pp.467-474
• /
• 2005

This paper presents a systematic method to compute a reliability measure for a short term electrical load forecasting system using neuro-fuzzy models. It has been realized that the reliability computation is essential for a load forecasting system to be applied practically. The proposed method employs a local reliability measure in order to exploit the local representation characteristic of the neuro-fuzzy models. It, hence, estimates the reliability of each fuzzy rule learned. The design procedure of the proposed short term load forecasting system is as follows: (1) construct initial structures of neuro-fuzzy models, (2) store them in the initial structure bank, (3) train the neuro-fuzzy model using an appropriate initial structure, and (4) compute load prediction and its reliability. In order to demonstrate the viability of the proposed method, we develop an one hour ahead load forecasting system by using the real load data collected during 1996 and 1997 at KEPCO. Simulation results suggest that the proposed scheme extends the applicability of the load forecasting system with the reliably computed reliability measure.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.18 no.1
• /
• pp.1-5
• /
• 2005

A new model of plasma etch process was constructed by using a radial basis function network (RBFN). This technique was applied to an etching of silicon carbide films in a NF$_3$ inductively coupled plasma. Experimental data to train RBFN were systematically collected by means of a 2$^4$ full factorial experiment. Appropriateness of prediction models was tested with test data consisted of 16 experiments not pertaining to the training data. Prediction performance was optimized with variations in three training factors, the number of pattern units, width of radial basis function, and initial weight distribution between the pattern and output layers. The etch responses to model were an etch rate and a surface roughness measured by atomic force microscopy. Optimized models had the root mean-squared errors of 26.1 nm/min and 0.103 nm for the etch rate and surface roughness, respectively. Compared to statistical regression models, RBFN models demonstrated an improvement of more than 20 % and 50 % for the etch rate and surface roughness, respectively. It is therefore expected that RBFN can be effectively used to construct prediction models of plasma processes.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.12 no.4
• /
• pp.101-109
• /
• 2004

Three models with various degree-of-freedom for a manual transmission clutch full-size tester have been developed and the models' reliability and accuracy have been verified using the measured data. A simulation study has also been conducted to understand dynamic behavior of the tester. The model for this simulation study includes clutch disk friction and damper dynamics. The developed model is very accurate in terms of maximum torque exerted on the clutch, slip duration and the vibration response except a slight difference compared to the measured data. In a history graph of the clutch torque, the maximum torque response from simulation is flat but the measured is sunken with a noticeable curvature. This phenomenon is found to be irrelevant to the dynamics of the full-size tester but is originated from the characteristics of the clutch itself. Thus, the full-size tester has been proven to be a reliable tester for clutch's power and torque transmission capability. To obtain a better understanding of clutch's characteristics and relationship between full-size tester and other testing methodologies, future research directions have been suggested.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.9
• /
• pp.186-192
• /
• 2002

As industry is developed, the faster transportation of freight train is demanded. The optimum design of a structure requires the determination of economical member size and shape of a structure which will satisfy the design conditions and the functions. In this study, it is attempted to minimize the dead weight of bogie frame. From the numerical results in the shape and size optimization of the bogie frame, it is known that the weight can be reduced up to 17.45% with the displacement, stress, first natural frequency and critical buckling-load constraints. The first natural frequency and the critical buckling load of the optimized model is larger than that of the lowest design value. Stress and displacement conditions are also satisfied within the design conditions. From the results, the optimal model is stable and useful for the improvement of railway carriages.

• Computers and Concrete
• /
• v.15 no.2
• /
• pp.167-181
• /
• 2015

"Mortar or concrete pneumatically projected at high velocity onto a surface" is called Shotcrete. Models that predict shotcrete design parameters (e.g. compressive strength, slump etc) from any mixing proportions of admixtures could save considerable experimentation time consumed during trial and error based procedures. Artificial Neural Network (ANN) has been widely used for similar purposes; however, such models have been rarely applied on shotcrete design. In this study 19 samples of shotcrete test panels with varying quantities of water, steel fibers and silica fume were used to determine their slump, cost and compressive strength at different ages. A number of 3-layer Back propagation Neural Network (BPNN) models of different network architectures were used to train the network using 15 samples, while 4 samples were randomly chosen to validate the model. The predicted compressive strength from linear regression lacked accuracy with $R^2$ value of 0.36. Whereas, outputs from 3-5-3 ANN architecture gave higher correlations of $R^2$ = 0.99, 0.95 and 0.98 for compressive strength, cost and slump parameters of the training data and corresponding $R^2$ values of 0.99, 0.99 and 0.90 for the validation dataset. Sensitivity analysis of output variables using ANN can unfold the nonlinear cause and effect relationship for otherwise obscure ANN model.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.24 no.2
• /
• pp.167-175
• /
• 2011

The purpose of this study is to examine the impact that change in speed and modeling methods has on maglevs' runnability. The study constructed equations of motion on 4-DOF, 6DOF, and 10-DOF vehicles respectively and carried out numerical analysis, applying 4th Runge Kutta method, in order to run six different model maglev as changing the vehicles speed on the same bridge that had 2000 to 1 deflection. The analysis revealed that maglev's runnability improved as speed was lower and the specific model had higher number of bogey and EMS.

• Proceedings of the KSR Conference
• /
• 2004.10a
• /
• pp.1322-1327
• /
• 2004

There are some previous studies that utilize constant impedance models or constant current models for electric trains to perform the static analysis of AT feeding systems. These mentioned models have some merits of linear systems but yield erroneous results because of the innate restraints of the models since linear models cannot represent the features of constant power in inverter-driven trains. From these reasons, it is suitable that the train be considered as a constant load model when it drives or as a constant source model when it applies regenerative brake. However, excessive rise of regenerative voltage during the braking may damage the vehicle itself and the feeding systems so the voltage must be restricted below a certain value. Keeping these facts in minds, we suggest new methods of analyzing AT feeding systems using the constant power models with the conditions of voltage constraints. The simulation results from a sample system using the proposed method illustrate both the states of system variables and the supply-demand relation of power among the trains and the systems very clearly, so it is believed that the proposed method yields more accurate results than conventional methods do.

• International Journal of Railway
• /
• v.4 no.4
• /
• pp.109-115
• /
• 2011

An analysis and design method for reducing aerodynamic noise in high-speed trains based on biomimetics of noiseless flight of owl is proposed. Five factors related to the morphology of the flight feather have been selected, and the candidate optimal shape of the flight feather is determined. The turbulent flow field analysis demonstrates that the optimal shape leads to diminished vortex formation by causing separation of the flow as well as allowing the fluid to climb up along the surface of the flight feather. To determine the effect of scaling of the owl's flight feather on the noise reduction, a two-fold and a four-fold scaled up model of the feather are constructed, and the numerical simulations are carried out to obtain the aerodynamic noise levels for each scale. Original model is found to reduce the noise level by 10 dBA, while two-fold increase in length dimensions reduces the noise by 12 dBA. Validation of numerical solution using wind tunnel experimental measurements is presented as well.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.7
• /
• pp.711-719
• /
• 2010

Heliostat, as a concentrator reflecting the incident solar energy to the receiver located at the tower, is the most important system in the tower-type solar thermal power plant, since it determines the efficiency and performance of solar thermal plower plant. Thus, a good sun tracking ability as well as its good optical property are required. In this paper, we propose a method to compensate the heliostat sun tracking error. We first model the sun tracking error, which could be measured using BCS (Beam Characterization System), by multilayered neural network. Then the extended Kalman filter was employed to train the neural network. Finally the model is used to compensate the sun tracking errors. Simulated result shows that the method proposed in this paper improve the heliostat sun tracking performance dramatically. It also shows that the training of neural network by the extended Kalman filter provides faster convergence property, more accurate estimation and higher measurement noise rejection ability compared with the other training methods like gradient descent method.

• Journal of Electrical Engineering and Technology
• /
• v.7 no.1
• /
• pp.115-123
• /
• 2012

A video analysis system used to detect events in video streams generally has several processes, including object detection, object trajectories analysis, and recognition of the trajectories by comparison with an a priori trained model. However, these processes do not work well in a complex environment that has many occlusions, mirror effects, and/or shadow effects. We propose a new approach to a context-aware video surveillance system to detect predefined contexts in video streams. The proposed system consists of two modules: a feature extractor and a context recognizer. The feature extractor calculates the moving energy that represents the amount of moving objects in a video stream and the stationary energy that represents the amount of still objects in a video stream. We represent situations and events as motion changes and stationary energy in video streams. The context recognizer determines whether predefined contexts are included in video streams using the extracted moving and stationary energies from a feature extractor. To train each context model and recognize predefined contexts in video streams, we propose and use a new ensemble classifier based on the AdaBoost algorithm, DAdaBoost, which is one of the most famous ensemble classifier algorithms. Our proposed approach is expected to be a robust method in more complex environments that have a mirror effect and/or a shadow effect.