• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2002.03a
• /
• pp.219-227
• /
• 2002

In this paper, we designed neural network predictive PID controller to control sway happened in transfer of trolley for automatic travel control system. We include dynamic character of nonlinear system, and mathematical expression veny simple used neural network. When various establishment location and surrounding disturbance were approved based on mathematical modelling of crane, controller designed to become effective control location error and vibration angle of two control variables that simultaneously can predictive control. Neural network predictive PID controller produced parameter of PID controller using neural network self-tuner. Neural network self-tuner's input used crane's output and neural network predictive output. Neural network self-tuner using error back propagation algorithm. We analyzed control performance comparison through computer simulation when applied disturbance about sway of location and angle in transfer of crane. The results show that the proposed neural network predictive PID controller has better performances than general PID controller, neural network PID controller.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2005.05a
• /
• pp.409-411
• /
• 2005

In this literature, we mose the design method of a proportional pressure control valve using valve system analysis and finite element method. And it is shown that a manufactured proportional pressure control valve character is well matched to tile theoretical analysis results. Also it is verified that the proposed valve has excellent performance compared to the other foreign products.

• Proceedings of the KIEE Conference
• /
• 1989.11a
• /
• pp.337-341
• /
• 1989

This theory has fast response and low overshoot by transforming its structure and this system may have new character which did not appear in this system. The VSS system transform its structure by switching logic. Then, the state trajectory is to sliding along the switching line to the phase-plane orgin. The phase trajectory is known as the sliding mode of this controller. This paper performed position control in the theory and analysised the change in variable loads.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.04a
• /
• pp.288-292
• /
• 1997

Positioning accuracy largely depends on the variation of friction force in guide table, geometric accuracy of feed unit like as ballscrew and controllable accrecy of servo unit, in general. This paper deals with improvement of microstep resolution about hydrostatic table. Torque control mode have a advantage in microstep test, and more stable than velocity control mode in low velocity motion. Hydro static table have the elastic behavior within several .mu.m, so different character exist between the elastic motion and rolling motion. Integral gain is dominant than other gain in elastic motion. In order to improve response time in elastic motion,increasing gain is suggested within the stable region.

• Journal of Institute of Control, Robotics and Systems
• /
• v.2 no.3
• /
• pp.229-235
• /
• 1996

CAD diagrams generally consists of many basic components: symbols, character, and connection lines. Thus, to recognize the diagrams, it is necessary to extract each components, and understand their meanings and relation among them. This paper describes a method for linking basic components extracted efficiently from hand-down diagrams to OrCAD data format. Experimental results with a hand-drawn diagrams of electronic and logic circuit show utility of the proposed method.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 1997.11a
• /
• pp.369-375
• /
• 1997

At the present time in Russia proper programs of increasing museums fire safety are taking into account their specific character and means are not developed. But the problem of control for fire safety of museums should be solved. In connection with it approximate models for estimation el Level ol Fire Safety are developed on the basis of expert's assessment. Proposed approach permits to choose rational variants of fire safety system for specific museum.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.969-981
• /
• 2018

Recent advances in machine learning approaches such as deep neural network and reinforcement learning offer significant performance improvements in generating detailed and varied motions in physically simulated virtual environments. The optimization methods are highly attractive because it allows for less understanding of underlying physics or mechanisms even for high-dimensional subtle control problems. In this paper, we propose an efficient learning method for stochastic policy represented as deep neural networks so that agent can generate various energetic motions adaptively to the changes of tasks and states without losing interactivity and robustness. This strategy could be realized by our novel trajectory search method motivated by the trust region policy optimization method. Our value-based trajectory smoothing technique finds stably learnable trajectories without consulting neural network responses directly. This policy is set as a trust region of the artificial neural network, so that it can learn the desired motion quickly.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.6
• /
• pp.1338-1344
• /
• 2010

A person does communication between each other using language. But In the case of disabled person can not communication own idea to use writing and gesture. Therefore, In this paper, we embodied communication system using the facial muscle signals so that disabled person can do communication. Especially, After feature extraction of the EEG included facial muscle, it is converted the facial muscle into control signal, and then select character and communication using a minimum list keyboard.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.8
• /
• pp.760-768
• /
• 2007

This paper introduces an emotional behavior decision model based on linear system for intelligent service robots. An emotional model should make different behavior decisions according to the purpose of the robots. We propose an emotional behavior decision model which can change the character of intelligent service robots and make different behavior decisions although the situation and environment remain the same. We defined each emotional element such as reactive dynamics, internal dynamics, emotional dynamics, and behavior dynamics by state dynamic equations. The proposed system model is a linear dynamic system. If you want to add one external stimulus or behavior, you need to add just one dimensional vector to the matrix of external stimulus or behavior dynamics. The case of removing is same. The change of reactive dynamics, internal dynamics, emotional dynamics, and behavior dynamics also follows the same procedure. We implemented a cyber robot and an emotional head robot using 3D character for verifying the performance of the proposed emotional behavior decision model.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.25 no.3
• /
• pp.9-15
• /
• 2002

Due to the inconsiderateness of human capability and inappropriate arrangement of display and control unit at the industrial site, the human error leads to a various accidents. This study was performed to investigate the visual range at the eye field and stationary field at the various angles with three different visual stimuli of alphabetic character, color slip and light-emitting diode. Three kinds of various alphabetic characters depending on length and breadth ratio (1:1, 3:5, 5:3) and three different colors (red, yellow, green) were used for the stimuli. Twenty-five subjects (11 males and 14 females) participated for this study. The results showed that female had wider visual range than male at the eye field, however no significant difference was found at the stationary field. The light-emitting diode had a widest visual range then color slip and characters are in order at the eye field and stationary field. For the character stimulus, the widest visual range was shown at length and breadth ratio of 1:1. The other ratios (3:5 and 5:3) showed no significant difference. The color of red had a widest visual range on the light-emitting diode, however, the color of yellow showed a widest visual range on the just color slip at the eye field. The result of this study would be valuable in applying to the design of visual display and the panel layout of control and displays in the industrial site.