http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
유전 알고리즘을 이용한 모듈라 웨이블릿 신경망의 최적 구조 설계
서재용,조현찬,김용택,전홍태,Seo, Jae-Yong,Cho, Hyun-Chan,Kim, Yong-Taek,Jeon, Hong-Tae 대한전자공학회 2001 電子工學會論文誌-SC (System and control) Vol.38 No.5
단일 신경망에 기반한 웨이블릿 이론과 모듈라 개념을 결합하여 기존의 웨이블릿 신경망이나 모듈라 네트워크의 일종인 모듈라 웨이블릿 신경망이 제안되었다. 본 논문에서는 유전 알고리즘을 사용하여 모듈라 웨이블릿 신경망의 최적구조를 효과적으로 설계하는 방법을 제시하였다. 각 모듈을 구성하는 웨이블릿 신경망의 웨이블릿 기저함수의 팽창과 이동계수를 결장하기 위해 유전 알고리즘을 사용하였다. 제안한 최적 구조 설계 알고리즘을 근사화 문제에 적용하여 우수성을 검증하였다. Modular wavelet neural network combining wavelet theory and modular concept based on single layer neural network have been proposed as an alternative to conventional wavelet neural network and kind of modular network. In this paper, an effective method to construct an optimal modular wavelet network is proposed using genetic algorithm. Genetic Algorithm is used to determine dilations and translations of wavelet basis functions of wavelet neural network in each module. We apply the proposed algorithm to approximation problem and evaluate the effectiveness of the proposed system and algorithm.
리튬 2차 전지의 열적 모델링 및 용량 예측에 관한 연구
김종원,조현찬,김광선,조장군,이정수,호빈,Kim, Jong-Won,Cho, Hyun-Chan,Kim, Kwang-Sun,Jo, Jang-Gun,Lee, Jung-Su,Hu, Bin 한국반도체디스플레이기술학회 2007 반도체디스플레이기술학회지 Vol.6 No.1
In this paper, the intelligent estimation algorithm is developed for residual quantity estimate of lithium secondary cell and we suggest the control algorithm to get battery SOC through thermal modeling of electric cell. Lithium secondary cell gives cycle life, charge characteristic, discharge characteristic, temperature characteristic, self-discharge characteristic and the capacity recovery rate etc. Therefore, we make an accurate estimate of the capacity of battery according to thermal modeling to know the capacity of electric cell that is decreased by various special quality of lithium secondary cell. And we show effectiveness through comparison of value as result that use simulation and fuzzy logic.
다수의 FET를 이용한 2차 전지의 셀 밸런스에 관한 연구
임근욱,조현찬,김종원,김광선,이정수,유상길,강희선,Lim, Geun-Wook,Cho, Hyun-Chan,Kim, Jong-Won,Kim, Kwang-Sun,Lee, Jung-Su,Yoo, Sang-Gil,Kang, Hee-Sun 한국반도체디스플레이기술학회 2008 반도체디스플레이기술학회지 Vol.7 No.2
In this paper, the cell balance of secondary battery using a large number of MOSFETs is discussed. We can balance the cells by controlling battery charging current with help of MOSFETs. If the cells are not balanced, we can not use the whole energy of the battery while charging and discharging, therefore, the energy efficiency is decreased. To increase the energy efficiency, we propose the MOSFET control algorithm which will perform cell balancing by controlling the charging current.
김종원,홍광진,조현찬,김광선,김두용,조중근,Kim Jong Won,Hong Kwagn Jin,Cho Hyun Chan,Kim Kwang Sun,Kim Doo Yong,Cho Jung Keun 한국반도체디스플레이기술학회 2005 반도체디스플레이기술학회지 Vol.4 No.3
As the integrated devices become more and more sophistcated, the diameter of wafers increased up to 300 mm and strict level of cleaning is necessary to remove the particulates on the surface of wafer. Therefore we need a new type of wet-station which can reduce DI water and chemical in the cleaning process. Moreover, it is important to control the temperature and the concentration of chemical in the wet-station. In the conventional chemical supply system, it is difficult not only to fit the mixing rate of chemicals in cleaning process, but also to fit the quantity and temperature. Thus, we propose a new chemicals supply system, which overcomes above problems by the analysis of fluid and thermal transfer on chemical supply system.
김종원,서재용,조현찬,조태훈,강흥석,Kim, Jong-Won,Seo, Jae-Yong,Cho, Hyun-Chan,Cho, Tai-Hoon,Kang, Heung-Seok 한국반도체디스플레이기술학회 2006 반도체디스플레이기술학회지 Vol.5 No.4
Expose equipment system that is used for manufacturing process of Flat Panel Display, is most important equipment in whole process. Expose equipment that is for making pattern of mask on substrate, consists of optical part, stage part and transport part. The stage is an important part that aligns mask and substrate for delivering pattern of mask to substrate exactly. In this paper, control system of expose stage that is able to use mask and substrate of diverse size, with PC controller using GUI interface instead of PLC control system. The existing PLC control system does not have the suitable structure for using mask of diverse size. GUI interface integration control system is based on PC. So it has the advantage of convenient use and active operation. We embodied PLC control system in integration control system based on PC, and verified utility possibility through the standard test course.
접촉형 변위센서를 이용한 LCD노광기용 스테이지 시스템
임광국,서화일,조현찬,김광선,강흥석,Yim, Kwang-Kuk,Seo, Hwa-Il,Cho, Hyun-Chan,Kim, Kwang-Sun,Kang, Heung-Seok 한국반도체디스플레이기술학회 2007 반도체디스플레이기술학회지 Vol.6 No.1
In an effort to reduce weaknesses of existing laser displacement sensor-based system, a sensing device for distance and balance of mask-substrate gap using touch-type displacement sensor was suggested. The device suggested in this study is expected to solve the problems of prices and reflections, by means of a touch-type sensor. LCD exposure equipment stage system including suggested sensing device was realized to assess the characteristics of sensing the balance and gap between mask and substrate. It was verified that a touch-type displacement sensor-based device to adjust the balance and distance of mask-substrate gap suggested in this study can be applicable to LCD expose equipment in practice.
시간-주파수 분석을 이용한 모듈라 웨이블렛 신경망의 최적 구조 설계
서재용,김용택,조현찬,전홍태,Seo, Jae-Yong,Kim, Yong-Taek,Cho, Hyun-Chan,Jeon, Hong-Tae 대한전자공학회 2001 電子工學會論文誌-SC (System and control) Vol.38 No.2
본 논문에서는 새로운 구조의 모듈라 시스템의 최적구조 설계 알고리즘을 제안하였다. 모듈라 시스템은 구조의 단순화와 시간 주파수 분석법을 이용하기 위해 웨이블렛 신경망으로 구성하였다. 제안한 최적구조 설계 알고리즘을 이용하여 근사화 대상함수의 시간-주파수 특성을 분석하여 모듈의 개수와 부-시스템의 노드의 개수를 결정할 수 있다. 제안한 최적 구조 설계 알고리즘은 시스템의 특성을 분석하여 모듈라 웨이블렛 신경망의 최적구조를 설계할 수 있는 방법론을 제공할 수 있다. 제안한 새로운 구조와 최적 구조 설계 알고리즘을 근사화 문제에 적용하여 우수성을 검증하였다. In this paper, we propose the new algorithm which can design on the optimal structure of modular system. This system is composed to the wavelet neural network in order to simplify the structure of modular system and use the time-frequency analysis. We will determine the number of module and node of each sub-system using the proposed algorithm. This algorithm provides the methodology, which we will design optimal structure of modular wavelet neural network through analyzing the character of system. We apply the proposed new structure and algorithm to approximation problem and evaluate the effectiveness of the proposed system and algorithm.