• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.04a
• /
• pp.403-413
• /
• 1996

Two-phase self-organizing neuro-modeling (SONM). the global SONM and local SONM, is designed for tracking non-stationary manufacturing processes. Radial basis function (RBF) neural network is employed, and self-tuning estimator is also developed for the determination of RBF network parameters on-line. A pattern recognition approach is presented for identifying a correct RBF neural network, which is used for identifying current manufacturing processes. Experimental results showed that the proposed approach is suitable for tracking non-stationary processes.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.434-437
• /
• 1999

The primary aim of this paper is to introduce and illustrate a radial basis function (RBF) modeling approach fur software module characterization, as an alternative to current techniques. The RBF model has been known to provide a rich analytical framework fur a broad class of so-called pattern recognition problems. Especially, it features both nonlinearity and linearity which in general are treated separately by its learning algorithm, leading to offer conceptual and computational advantages. Furthermore, our new modeling methodology fer determining model parameters has a sound mathematical basis and showed very interesting results in terms of model consistency as well as performance.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2002.05a
• /
• pp.545-550
• /
• 2002

Concrete is one of the essential structural materials in the construction. But, concrete consists of many materials and is affected by many factors such as properties of materials, site environmental situations, and skill of constructor. Therefore, concrete mixes depend on experiences of experts. However, it is more and more difficult to determine concrete mixes design by empirical means because more ingredients like mineral and chemical admixtures are included. Artificial Neural Networks(ANN) are a mimic models of human brain to solve a complex nonlinear problem. They are powerful pattern recognizers and classifiers, also their computing abilities have been proven in the fields of prediction, estimation and pattern recognition. Here, among them, the back propagation network and radial basis function network are used. Compositions of high-performance concrete mixes are eight components(water, cement, fine aggregate, coarse aggregate, fly ash, silica fume, superplasticizer and air-entrainer). Compressive strength and slump are measured. The results show that neural networks are proper tools to minimize the uncertainties of the design of concrete mixtures.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.8
• /
• pp.1615-1623
• /
• 2009

In order to develop reliable on-site partial discharge (PD) pattern recognition algorithm, we introduce Type-2 Fuzzy Neural Networks (T2FNNs) optimized by means of Particle Swarm Optimization(PSO). T2FNNs exploit Type-2 fuzzy sets which have a characteristic of robustness in the diverse area of intelligence systems. Considering the on-site situation where it is not easy to obtain voltage phases to be used for PRPDA (Phase Resolved Partial Discharge Analysis), the PD data sets measured in the laboratory were artificially changed into data sets with shifted voltage phases and added noise in order to test the proposed algorithm. Also, the results obtained by the proposed algorithm were compared with that of conventional Neural Networks(NNs) as well as the existing Radial Basis Function Neural Networks (RBFNNs). The T2FNNs proposed in this study were appeared to have better performance when compared to conventional NNs and RBFNNs.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.11 no.5
• /
• pp.29-34
• /
• 2012

This study describes the selection of optimum machining conditions for a high-hardness resin by using a large 5-axis machine. The experiments were conducted to examine the main factors that affect the surface roughness, such as the spindle speed, axial and radial depths of the cut, and pattern of the cutter path. To analyze the experiment results, the factor with the biggest impact on machining was determined using the smaller-the-better characteristic of the Taguchi method; the effectiveness of the experiment was then confirmed by verifying the selected optimum machining condition.

• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.1
• /
• pp.31.1-31.1
• /
• 2017

Spiral structure in disk galaxies is modeled with ncollisionless N-body simulations including live disks, halos, and bulges with a range of masses. Two of these simulations make long-lasting and strong two-arm spiral wave modes that last for about 5 Gyr with constant pattern speed. These two had a light stellar disk and the largest values of the Toomre Q parameter in the inner region at the time the spirals formed, suggesting the presence of a Q-barrier to wave propagation resulting from the bulge. The relative bulge mass in these cases is about 10%. Models with weak two-arm spirals had pattern speeds that followed the radial dependence of the Inner Lindblad Resonance. In addition to these, we also report a few more cases where two-armed spirals are developed and are maintained for a several rotation time scales.

• Environmental Engineering Research
• /
• v.10 no.1
• /
• pp.15-21
• /
• 2005

A computer program is developed for the prediction of the flow pattern and the removal efficiency of suspended solid (SS) in a circular secondary clarifier. In this study the increased density effect by SS on hydrodynamics has been systematically investigated in terms of Froude Number (Fr), baffle existence, and a couple of important empirical models associated with the particle settling and Reynolds stresses. A control-volume based-finite difference method by Patankar is employed together with the SIMPLEC algorithm for the resolution of pressure-velocity coupling. The k-ε turbulence and its modified version are incorporated for the evaluation of Reynolds stresses. The calculation results predicts well the overall flow pattern such as the waterfall phenomenon at the front end of the clarifier and the bottom density current with the formation of strong recirculation especially for the case of decrease of Fr. Even if there are some noticeable differences in the prediction of two turbulence models, the calculated results of the radial velocity profiles are generally in good agreement against experimental data appeared in open literature. Parametric investigation has been systematically made with the Fr and baffle condition with detailed analysis.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.58 no.3
• /
• pp.357-361
• /
• 2009

This study performed analysis on the thermal pattern and current characteristics of an LED ((Light Emitting Diode) street lamp. It did this using a TVS (Thermal Video System) to analyze the LED street lamp's thermal pattern, and measured its characteristics using an oscilloscope. The ambient temperature and humidity during the experiment were maintained at $24{\pm}2[^{\circ}C]$ and 50~60[%]. The capacity of the LED street lamp was 120[W] and nine sets of modules were arranged at uniform intervals. On one module, 24 LED lamps were arranged in a radial pattern. The analysis of the thermal diffusion pattern at the front of the LED lamp showed that the maximum surface temperature was approximately $34[^{\circ}C]$. In addition, there was almost no change in the temperature of the upper cover, and the temperature at the side showed a uniform thermal diffusion pattern. The surface temperature of the converter converting AC to DC increased to approximately $46[^{\circ}C]$. The analysis results of the thermal characteristics of one LED indicated uniform thermal characteristics for an initial eight minutes. However, the temperature at the center of the LED increased to approximately $82[^{\circ}C]$ after 12 minutes had elapsed. It can be seen from this that the temperature at the center of the LED was higher than the allowable temperature, $70[^{\circ}C]$ of the insulating material for general electrical devices. Therefore, it is necessary to design a lamp in such a way that the plastic insulating material does not come into contact with or get close to the LED lamp. The voltage of the LED lamp converted by the AC/DC converter was measured at DC 27[V] and the current was DC 13[A]. Consequently, it can be seen that in order to secure an adequate light source, it is important to supply a stable current that was greater than the current of other light sources. Therefore, appropriate radiation of heat is required to secure the stability and reliability of the system.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.12
• /
• pp.1923-1932
• /
• 2013

In order to solve the problem of severely distorted images from a wide-angle camera, we propose a calibration method which corrects a radial distortion in wide-angle images by estimation and validation of camera model. First, we estimate a camera model consisting of intrinsic and extrinsic parameters from calibration patterns, where intrinsic parameters are the focal length, the principal point and so on, and extrinsic parameters are the relative position and orientation of calibration pattern from a camera. Next we validate the estimated camera model by re-extracting corner points by inversing the model to images. Finally we correct the distortion of the image using the validated camera model. We confirm that the proposed method can correct the distortion more than 80% by the calibration experiments using the lattice shaped pattern images captured from a general web camera and a wide-angle camera.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.9
• /
• pp.1392-1401
• /
• 2017

In this study, the design methodology of pattern classification is introduced for avoiding faults through partial discharge occurring in the power facilities and local sites. In order to classify some partial discharge types according to the characteristics of each feature, the model is constructed by using the Radial Basis Function Neural Networks(RBFNNs) and Particle Swarm Optimization(PSO). In the input layer of the RBFNNs, the feature vector is searched and the dimension is reduced through Principal Component Analysis(PCA) and PSO. In the hidden layer, the fuzzy coefficients of the fuzzy clustering method(FCM) are tuned using PSO. Raw datasets for partial discharge are obtained through the Motor Insulation Monitoring System(MIMS) instrument using an Epoxy Mica Coupling(EMC) sensor. The preprocessed datasets for partial discharge are acquired through the Phase Resolved Partial Discharge Analysis(PRPDA) preprocessing algorithm to obtain partial discharge types such as void, corona, surface, and slot discharges. Also, when the amplitude size is considered as two types of both the maximum value and the average value in the process for extracting the preprocessed datasets, two different kinds of feature datasets are produced. In this study, the classification ratio between the proposed RBFNNs model and other classifiers is shown by using the two different kinds of feature datasets, and also we demonstrate the proposed model shows superiority from the viewpoint of classification performance.