On-line 학습 신경회로망을 이용한 열간 압연하중 예측

손준식,이덕만,김일수,최숭갑 한국공작기계학회 2003 한국공작기계학회 춘계학술대회논문집 Vol.2003 No.-

In the face of global competition, the requirements for the continuously increasing productivity, flexibility and quality(dimensional accuracy, mechanical properties and surface properties) have imposed a major change on steel manufacturing industries. Indeed, one of the keys to achieve this goal is the automation of the steel-making process using AI(Artificial Intelligence) techniques. The automation of hot rolling process requires the developments of several mathematical models for simulation and quantitative description of the industrial operations involved. In this paper, a on-line training neural network for both long-term learning and short-term learning was developed in order to improve the prediction of rolling force in hot rolling mill. This analysis shows that the predicted rolling force is very closed to the actual rolling force, and the thickness error of the strip is considerably reduced.

GMA용접에서 유전자 알고리즘을 이용한 비드높이 예측 모델 개발에 관한 연구

손준식,김일수,장경천,이동길 한국공작기계학회 2006 한국공작기계학회 추계학술대회논문집 Vol.2006 No.-

Gas metal arc welding process has been chosen as a metal joining technique due to the wide range of usable applications, cheap consumables and easy handling. Three main indicators such as arc voltage, welding speed and welding current have a big influence in the quality welding. Since all these factors affect the quality of the welded joining parts, the effect of these parameters was investigated experimentally. In this paper, an attempt has been made to develop the predicted models (quadratic and cubic) for bead height using genetic algorithm. Performance of the developed models were proved to be compared to the regression equation.

Monte Carlo 시뮬레이션을 이용한 이온 주입시의 점결함 분포의 계산

손명식,이준하,변기량,황호정 중앙대학교 기술과학연구소 1995 기술과학연구소 논문집 Vol.25 No.-

이온 주입시의 점결함 분포를 간접적으로 계산하기 위해 단결정 실리콘에서의 3차원 이온 주입 시뮬레이터인 TRICSI (TRansport Ions in Crystal Slilicon) Monte Carlo 코드를 확장하여 Boron 이온 주입시의 에너지와 dose에 따른 불순물(particle) 및 점결함 분포(point defect)를 계산하였다. 결함 분포는 Modified Kinchin-Pease equation을 단결정 실리콘에 적용하여 displacement damage에 의해 발생한 Frenkel Pair(vacancy-interstitial)분포를 계산하였으며 이온 주입시의 웨이퍼 온도에 의한 Frenkel Pair 소멸 효과는 고려하지 않았다. 계산 결과는 3차원 각면으로의 2차원 투영 불순물 농도로 표현하고 주입된 dose와 에너지에 다른 마스크 주입시의 에너지 및 dose 의존성 도펀트 분포와 이에 따른 damage 분포를 이해하는 데 중요한 정보가 될 것으로 기대된다. We extended our ion implantation simulator, TRICSI (TRansport lons in Crystal Slilicon) Monte Carlo(MC) code, and indirectly calculated particle and its generating point defect distributions depending on energy and dose during boron implantation into <100> single0crystal silicon. The point defect distribution of Frenkel Pair(vacancy-interstitial) was abtained by applying the modified Kinchin-Pease equation, which usually uses in MC simulation in amorphous target, to MC simulation in crystalline silicon. We did not considered the annihilation of Frenkel Pairs due to wafer temperature. The calculated results were projected onto each free-dimensional plane, presented as two-dimensional concentration profile on it. The particle concentration profile was presented with typical open mask structure. We expect that these results help understand the dopant and its generating damage distributions depending on energy and dose during boron implantation.

방사형기저함수망을 이용한 표면 비드폭 예측에 관한 연구

손준식,김인주,김일수,김학형 한국공작기계학회 2004 한국공작기계학회 추계학술대회논문집 Vol.2004 No.-

Despite the widespread use in the various manufacturing industries, the full automation of the robotic CO₂ welding has not yet been achieved partly because the mathematical model for the process parameters of a given welding task is not fully understood and quantified. Several mathematical models to control welding quality, productivity, microstructure and weld properties in arc welding processes have been studied. However, it is not an easy task to apply them to the various practical situations because the relationship between the process parameters and the bead geometry is non-linear and also they are usually dependent on the specific experimental results. Practically, it is difficult, but important to know how to establish a mathematical model that can predict the result of the actual welding process and how to select the optimum welding condition under a certain constraint. In this paper, an attempt has been made to develop an Radial basis function network model to predict the weld top-bead width as a function of key process parameters in the robotic CO₂ welding. and to compare the developed model and a simple neural network model using two different training algorithms in order to verify performance. of the developed model.

방사형기저함수망을 이용한 열간 사상압연의 압연하중 예측에 관한 연구

손준식,이덕만,김일수,최승갑 한국공작기계학회 2003 한국공작기계학회 추계학술대회논문집 Vol.2003 No.-

A major concern at present is the simultaneous control of transverse thickness profile and flatness in the finishing stages of hot rolling process. The mathematical modeling of hot rolling process has long been recognized to be a desirable approach to investigate rolling operating practice and the design of mill equipment to improve productivity and quality. However, many factors make the mathematical analysis of the rolling process very complex and time-consuming. In order to overcome these problems and to obtain an accurate rolling force, the predicted model of rolling force using neural networks has widely been employed. In this paper, Radial Basis Function Network(RBFN) is applied to improve the accuracy of rolling force prediction in hot rolling mill. In order to verify and analysis the performance of applied neural network, the comparison with the measured rolling force and the predicted results using two different neural networks - RBFN, MLP, has respectively been carried out. The results obtained using RBFN neural network are much more accurate those obtained the MLP.

표면 비드높이 예측을 위한 최적의 신경회로망 선정에 관한 연구

손준식,김인주,김일수,장경천,이동길 한국공작기계학회 2005 한국공작기계학회 춘계학술대회논문집 Vol.2005 No.-

The full automation of welding has not yet been achieved partly because the mathematical model for the process parameters of a given welding task is not fully understood and quantified. Several mathematical models to control welding quality, productivity, microstructure and weld properties in arc welding processes have been studied. However, it is not an easy task to apply them to the various practical situations because the relationship between the process parameters and the bead geometry is non-linear and also they are usually dependent on the specific experimental results. Practically, it is difficult, but important to know how to establish a mathematical model that can predict the result of the actual welding process and how to select the optimum welding condition under a certain constraint. In this paper, an attempt has been made to develop an neural network model to predict the weld top-bead height as a function of key process parameters in the welding. and to compare the developed model and a simple neural network model using two different training algorithms in order to select an optimal neural network model.

방사형기저함수망을 이용한 열간 사상압연의 압연하중 예측에 관한 연구

손준식,이덕만,김일수,최승갑 한국공작기계학회 2004 한국생산제조학회지 Vol.13 No.6

A major concern at present is the simultaneous control of transverse thickness profile and flatness in the finishing stages of hot rolling process. The mathematical modeling of hot rolling process has long been recognized to be a desirable approach to investigate rolling operating practice and the design of mill equipment to improve productivity and quality. However, many factors make the mathematical analysis of the rolling process very complex and time-consuming. In order to overcome these problems and to obtain an accurate rolling force, the predicted model of rolling force using neural networks has widely been employed. In this paper, Radial Basis Function Network(RBFN) is applied to improve the accuracy of rolling force prediction in hot rolling mill. In order to verify and analyze the performance of applied neural network, the comparison with the measured rolling force and the predicted results using two different neural networks-RBFN, MLP, has respectively been carried out. The results obtained using RBFN neural network are much more accurate those obtained the MLP.

On-line 학습 신경회로망을 이용한 열간 압연하중 예측

손준식,이덕만,김일수,최승갑 한국공작기계학회 2005 한국생산제조학회지 Vol.14 No.1

In the face of global competition, the requirements for the continuously increasing productivity, flexibility and quality(dimensional accuracy, mechanical properties and surface properties) have imposed a major change on steel manufacturing industries. Indeed, one of the keys to achieve this goal is the automation of the steel-making process using AI(Artificial Intelligence) techniques. The automation of hot rolling process requires the developments of several mathematical models for simulation and quantitative description of the industrial operations involved. In this paper, an on-line training neural network for both long-term learning and short-term learning was developed in order to improve the prediction of rolling force in hot rolling mill. This analysis shows that the predicted rolling force is very closed to the actual rolling force, and the thickness error of the strip is considerably reduced.

연속냉간압연의 두께제어 모델 개발에 관한 연구

손준식,김일수,권욱현,최승갑,박철재,이덕만 한국공작기계학회 2001 한국생산제조학회지 Vol.10 No.5

The quality requirements for thickness accuracy in cold rolling continue to become more stringent, particularly in response to exacting design specification from automotive customers. One of the major impacts from the tighter tolerance level is more unusable product on the head end and tail end of tandem mill coils when the mill is in transition to or from steady state rolling condition. A strip thickness control system for a tandem cold steel rolling mills is composed with blocked non-interacting controller and controllers for strip thickness and tension control of each rolling stands. An intelligent mathematical model included an elastic deformation of strip has been developed and applied to the field in order to predict the rolling force. The simulated results showed that the effect of elastic recovery should be included the model, even if the effect of elastic compression was not important.

퉁퉁마디로부터 염에 의하여 유도되는 Aldolase 유전자의 분리 및 발현분석

차준영,네티 엘마와티,김순길,이증주,임채오,정우식,이곤호,손대영 Plant molecular biology and biotechnology research 2003 Plant molecular biology and biotechnology research Vol.2003 No.-

Soil salinity is one of the most serious abiotic stresses limiting the productivity of agricultural crops. To cope with salt stress, plants respond with physiological, developmental and biochemical changes, including the synthesis of a number of proteins and the induction of gene expression. Salicornia herbacea is a halophytic plant that grows in salt marches and on muddy seashores. In order to understand the biochemical and molecular mechanisms of salt tolerance in S. herbacea, we isolated several genes that involved in the salt tolerance by mRNA differential display.Here we report the cloning of a cDNA encoding fructose-1, 6-bisphosphate aldolase, named ShADL, which is 1293 bp long and contains an open reading frame consisted of 359 amino acids with calculated molecular mass of 39 kDa. ShADL protein showed 86% identity with Arabidopsis and 78% with aldolase of common ice plant. Northern blot analysis revealed that the transcript of ShADL gene was increased dramatically depending on the NaCI concentrations.