• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.3
• /
• pp.196-201
• /
• 2008

Statistical learning theory has three analytical tools which are support vector machine, support vector regression, and support vector clustering for classification, regression, and clustering respectively. In general, their performances are good because they are constructed by convex optimization. But, there are some problems in the methods. One of the problems is the subjective determination of the parameters for kernel function and regularization by the arts of researchers. Also, the results of the learning machines are depended on the selected parameters. In this paper, we propose an efficient method for objective determination of the parameters of support vector clustering which is the clustering method of statistical learning theory. Using evolutionary algorithm and bootstrap method, we select the parameters of kernel function and regularization constant objectively. To verify improved performances of proposed research, we compare our method with established learning algorithms using the data sets form ucr machine learning repository and synthetic data.

• Structural Engineering and Mechanics
• /
• v.25 no.1
• /
• pp.1-20
• /
• 2007

Dynamic behaviors of the contact surface between ball and raceway in a guideway mechanism vary with the applied loads and hence affect the mechanical responses of machine tools. The study aims to investigate the nonlinear characteristics of dynamic behaviors at the rolling contact interface in linear guideway mechanisms. Firstly, analytical method was introduced to understand the contact behaviors based on Hertz contact theory in a point-to-point way. Then, the finite element approach with a three-dimensional surface-to-surface contact model and appropriate contact stiffness was developed to study the dynamic characteristics of such linear guideways. Finally, experiments with modal test were conducted to verify the significance of both the analytical and the numerical results. Results told that the finite element approach may provide significant predictions. The study results also concluded that the current nonlinear models based on Hertz's contact theory may accurately describe the contact characteristic of a linear guideway mechanism. In the modal analysis, it was told that the natural frequencies vary a little with different loading conditions; however, the mode shapes are changed obviously with the magnitude of applied loads. Therefore, the stiffness of contact interface needs to be properly adjusted during simulation which may affect the dynamic characteristics of the machine tools.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 1998.02a
• /
• pp.334-339
• /
• 1998

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.10a
• /
• pp.182-182
• /
• 2003

• Journal of the Korean Society of Safety
• /
• v.9 no.4
• /
• pp.125-131
• /
• 1994

This paper proposes a dynamic recursive model with the effect analysis of machine state considering human factor(human skillfulness) In a single lot man-machine production system. This model obtained using Kalman Filtering Algorithm Is based on input state, output state, machine state. For sensitivity analysis, this model constructed is examined according to the impact of human skillfulness with computer simulation. The model studied in this paper has a great advance from the point of view a combination of three factors( human engineering, dynamic control theory, quality control ) and can also be extended in several applications.

• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.853-855
• /
• 1999

The induction machine has been used frequently for the system that needs static speed because of its simplicity, durability, credibility and efficiency. But it is nonlinear system for its multi-variable interference. Its controller is more complicated than DC machine's one. So vector control method is needed for its high Performance control. This paper shows that vector control algorithm could be more fast and stable by using Genetic algorithm (GA) based upon Darwin's evolution theory and Mendel's genetics. Methods proposed in here are used to design induction machine's vector controller and to use GA for optimizing the controller's parameter. SIMULINK of MATLAB is used for analysis and conviction of control property

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.113-114
• /
• 2008

For the supported high-technology, it is in need of estimation about power quality and reasonable price through machinism. The power system made much of precision digital industrial damage under sag. This study suggested electric machine under effects of power quality in the theory and test. A electric machine was simulated and experimented about sag. The test system made up IPC as voltage sag device. The test machine was magnetic contactor and PLC. The result, electric machines appeared to influence sag with CBEMA curve. It was make possible analysis of power system about a fault. This study was expected to method that investment and development of equipment on power market in the future.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.3
• /
• pp.157-167
• /
• 1998

In this paper it is purpose that reduces joint torques and their rate of change through optimizing trajectory planning of biped walking machine. The motion of biped walking machine is divided into leg motion for walking and body motion for keeping balance. The leg motion is planned by three phases, that are deploy, swing, and place phases, in terms of the state of foot against floor. The distribution of time assigned to each phase is optimized and that causes leg joint torques and their rate of change to minimize. The body notion is produced by using optimal control theory which minimizes body joint torques and satisfies Z.M.P. constraints defined as region of each phase.

• International Journal of Advanced Culture Technology
• /
• v.3 no.2
• /
• pp.67-76
• /
• 2015

This paper aims to study and design of Organic Rankine Cycle (ORC) Machine using Isopentane as working fluid expanding through Tesla turbine. The study on ORC machine expanding through Tesla turbine has result on the efficiency of Tesla turbine. In addition, Thermodynamics theory on isentropic efficiency proved to be a successful method for overcoming the difficulties associated with the determination of very low torque at very high angular speed. By using an inexpensive experiment device and a simple method, the angular acceleration method, for measuring output torque and power in a Tesla turbine is able to predict a tendency of output work. The experiments using two Tesla turbine sizes, the first size is 1.6 bigger than the second one. In comparison with the first size, the tesla turbine can produce power output more than 62% of the second size. Further study on the machine can be developed throughout the county due to its low cost and efficiency.

• Journal of Korea Multimedia Society
• /
• v.13 no.11
• /
• pp.1643-1656
• /
• 2010

It is necessary to develop a system to judge inferiority of goods to minimize the loss at small factories in which produces various kinds of goods with small amounts. That system can be developed based on HTM theory. HTM is a model to apply the operation principles of the neocortex in human brain to the machine learning. We have to build the trained HTM network to use the HTM-based machine learning system. It requires the knowledge for the HTM theory. This paper presents the design and implementation of the training system to support the development of HTM networks which recognize the molding parts to judge its badness. This training system allows field technicians to train the HTM network with high accuracy without the knowledge of the HTM theory. It also can be applied to any kind of the HTM-based judging systems for molding parts.