• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.699-701
• /
• 2004

This paper proposes the algorithm of servo- writing based on feedback error learning neural networks. The controller consists of feedback controller using PID and feedforward controller using gaussian radial basis function network. Because the RBFNs are trained by on-line rule, the controller has adaptation capability. The performance of the proposed controller is compared to that of conventional PID controller. Proposed algorithm shows better performance than PID controller.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.11a
• /
• pp.994-998
• /
• 1996

We propose an approach to integrating fuzzy logic control with RBF(Radial Basis Function) networks and show how the integrated network can be applied to multivariable self-organizing and self-learning fuzzy controller. Using the hybrid learning algorithm. To investigate its usefulness and performance, this controller is applied to a time-delayed process system. Simulation results show good control performance and fast convergency in hybrid loaming method.

• Tribology and Lubricants
• /
• v.38 no.1
• /
• pp.27-31
• /
• 2022

Harmonic drives have attracted increasing attention with the development of materials, parts, and related equipment. Harmonic drives exhibit high deceleration, high accuracy, and light weight. The stiffness of flexible splines according to the radial load is studied using a commercial FEM program to design the structure of the flexible spline and finite element to improve the weight and price competitiveness of harmonic drives. In addition, several studies have measured and compared friction coefficients based on 3D printed tread patterns. However, owing to the characteristics of plastic materials, a decrease in stiffness in the radial direction is inevitable. To prevent a decrease in stiffness in the radial direction, we designed and manufactured flex splines with a wrinkle shape. Through structural analysis, the reaction force and stiffness in the radial direction were determined. In addition, the maximum angle of the mound was derived by theoretical calculations, and the performance of the harmonic drive was compared with the results obtained in the mound experiment. Structural analysis shows that the shape of wrinkles decreased the stress and reaction force and increased the safety factor in comparison with that of the circular shape. During performance verification through continuous experiments, the developed harmonic drive showed continuous performance similar to that of an actual tank model. It is expected that the flex spline with a compliant spring and wrinkle shape will prevent a decrease in the radial stiffness.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.30-33
• /
• 2002

To obtain good performance of radial basis function (RBF) neural networks, it needs very careful consideration in design. The selection of several parameters such as the number of centers and widths of the radial basis functions must be considered carefully since they critically affect the network's performance. We propose a learning algorithm for growing of complexity of RBF neural networks which is adapted automatically according to the complexity of tasks. The algorithm generates a new basis function based on the errors of network, the percentage of decreasing rate of errors and the nearest distance from input data to the center of hidden unit. The RBF's center is located at the point where the maximum of absolute interference error occurs in the input space. The width is calculated based on the standard deviation of distance between the center and inputs data. The steepest descent method is also applied for adjusting the weights, centers, and widths. To demonstrate the performance of the proposed algorithm, general problem of function estimation is evaluated. The results obtained from the simulation show that the proposed algorithm for RBF neural networks yields good performance in terms of convergence and accuracy compared with those obtained by conventional multilayer feedforward networks.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 2000.06a
• /
• pp.106-113
• /
• 2000

A pump which is a fundamental device in a hydraulic system affects on overall system performance to a great deal. Such problems as leakage and solid friction loss become important in field applications, especially for the case of operation under high pressure and at high speed. So the research on this kind of subjects is necessary to improve the performance of hydraulic devices. A high pressure radial piston pump is analyzed here, which has a stationary cylinder block. It pumps hydraulic fluid by letting camring push a piston in a cylinder. Fluid leaks between the piston and cylinder so that it deteriorates the pump efficiency. Furthermore, the piston happens to touch the cylinder wall to increase the friction loss and wear. In this research, by means of FDM, volumetric, mechanical and overall efficiencies are observed by varying several design Parameters and operation conditions. Design values or their trends are presented to improve these efficiencies.

• Tribology and Lubricants
• /
• v.16 no.4
• /
• pp.259-265
• /
• 2000

Pump which is the fundamental device in the hydraulic system affects on overall system performance to a great deal. Such problems as leakage and solid friction loss become important in field applications, especially for the case of operation under high pressure and at high speed. So the research on this kind of subjects is necessary to improve the performance of hydraulic devices. A high pressure radial piston pump is analyzed here, which has a stationary cylinder block. It pumps hydraulic fluid by letting camring push a piston in a cylinder. Fluid leaks between the piston and cylinder so that it deteriorates the pump efficiency. Furthermore, the piston happens to touch the cylinder wall to increase the friction loss and wear. In this research, by means of FDA, volumetric, mechanical and overall efficiencies are observed by varying several design parameters and operation conditions. Design values or their trends are presented to improve these effciencies.

• Journal of Communications and Networks
• /
• v.12 no.6
• /
• pp.600-604
• /
• 2010

A method of width adaptation in the radial basis function network (RBFN) using stochastic gradient (SG) algorithm is introduced. Using Taylor's expansion of error signal and differentiating the error with respect to the step-size, the optimal time-varying step-size of the width in RBFN is derived. The proposed approach to adjusting widths in RBFN achieves superior learning speed and the steady-state mean square error (MSE) performance in nonlinear channel environment. The proposed method has shown enhanced steady-state MSE performance by more than 3 dB in both nonlinear channel environments. The results confirm that controlling over step-size of the width in RBFN by the proposed algorithm can be an effective approach to enhancement of convergence speed and the steady-state value of MSE.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.4
• /
• pp.739-745
• /
• 2011

This paper proposes a method for reducing the negative spatial harmonics of the radial flux density of an interior-type permanent magnet (IPM) motor. The reliability of the motor is increased by minimizing its vibrations under dynamic eccentricity (DE) state and normal state due to reduction of a negative spatial harmonics component through the influx of a zero spatial harmonics component in the radial flux density. To minimize the vibrations, optimal notches corresponding to the distribution shape of the magnetic field are designed on the rotor pole face. The variations of vibration computation by finite element method (FEM) and the validity of the analysis and rotor shape design are confirmed by vibration and performance experiments.

• The KSFM Journal of Fluid Machinery
• /
• v.19 no.1
• /
• pp.37-44
• /
• 2016

In this study, a parametric study of a centrifugal pump with double volute has been performed numerically using three-dimensional Reynolds-averaged Navier-Stokes equations. The shear stress transport model was selected as turbulence closure through turbulence model test. The finite volume method and unstructured grid system were used for the numerical analysis. The optimal grid system in the computational domain was determined through a grid dependency test. The expansion coefficient, circumferential and radial starting positions and length of divider were selected as the geometric parameters to be tested. And, the hydraulic efficiency and the radial thrust coefficient were considered as performance parameters. It was found that the radial thrust and hydrualic efficiency are more sensitive to the expansion angle and circumferential starting position of the divider than the other geometrical parameters.

• Journal of computational fluids engineering
• /
• v.18 no.1
• /
• pp.63-68
• /
• 2013

The purpose of this study is to investigate the cooling performance of radial heat sink used for high power LED lightings by natural convection cooling with surrounding air. Experimental and numerical analyses are carried out together. Parametric studies are performed to compare the effects of geometric parameters in radial heat sink such as the number of fins, fin height, fin length, and thickness of fin base as well as the surface coatings of radial heat sink. In this study, the cooling of 60 W LED lamp is examined with radiative heat transfer considered as well as natural convection. Numerical results show the optimum condition when the number of fin is 40, heat sink height is 120 mm, fin length is 15 mm, and fin base thickness is 3 mm. The difference in temperature of the LED metal PCB is within $1^{\circ}C$ between numerical analyses and experimental results. Also, the CNT coating on the heat sink surface is found to increase the cooling performance significantly.