http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
파이프 내면용접조건 선정을 위한 데이터베이스 시스템 개발에 관한 연구
김학형(H. H. Kim),서주환(J. H. Seo),심지연(J. Y. Shim),손준식(J. S. Son),김일수(I. S. Kim),유관종(K. J. Yoo) 한국생산제조학회 2007 한국생산제조시스템학회 학술발표대회 논문집 Vol.2007 No.10
Welding process involves large number of interdependent variables which may affect product quality, productivity and cost effect in pipeline industry. Especially, it is essential to make the automated welding system on inner-pipe welding due to the change welding conditions for different welding environments. In this study, we have carried out the sequential experiment to select the standard welding conditions for inner-pipe welding and develop the suitable 3 neural network to predict the optimized welding conditions. Finally, Management system for inner-pipe welding conditions have develop to get better welding quality. With the use of the developed system, It can be more simple to use the automatic welding process and optimization technique.
김일수,김학형,조선영,강봉용,강문진,유관종 한국공작기계학회 2004 한국공작기계학회 춘계학술대회논문집 Vol.2004 No.-
Over the last few years, there has been a growing interest in quantitative representation of the weld pools in order to relate the processing conditions to the driving forces of the weldment produced and to use this information for the optimization of the welding process. A theoretical model offers a powerful alternative to check the physical concepts of the welding process and the effects of driving forces. To solve this problem, a 2-D thermo-fluid model were developed for determining temperature and velocity distribution for the GMA welding process.
김일수,김학형,장한기,김희진,곽성규,유회수,심지연,Kim, Ill-Soo,Kim, Hak-Hyoung,Jang, Han-Kee,Kim, Hee-Jin,Kwak, Sung-Kyu,Ryoo, Hoi-Soo,Shim, Ji-Yeon 대한용접접합학회 2009 대한용접·접합학회지 Vol.27 No.4
In the process to manufacture for metallic structures, control of welding deformation is one of an important problems connected with reliability of the manufactured structures so that welding deformation should be measured and controlled with quickly and actively. Also, welding parameters which have as lot of effects on welding deformation such as arc voltage, welding current and welding speed can also be controlled. The objectives for this study were to develop a simple 2-D FEM to calculate not only the transient thermal histories but also the sizes of fusion and heat-affected zone (HAZ) in multi pass arc welds including the butt and fillet weld type with dissimilar thickness, and to concentrate on a developed model for the finding the parameters of Godak's moving heat source model based on a GA. The developed model includes a GA program using MATLB and GA toolbox, and a batch mode thermal model using ANSYS software. Not only the thermal model was verified by comparison with Goldak's work but also the developed model was validated with molten zone section experimental data.
ANN 알고리즘을 통한 절단 가공의 실시간 표면거칠기 예측에 관한 연구
이보람,김학형,정영재,오원빈,김일수 대한기계학회 2022 大韓機械學會論文集A Vol.46 No.12
Cutting is the first step and key processing factor during the manufacturing of shipbuilding equipment. Recently, various environmental problems have emerged in cutting workshops owing to the increase in the importance of safety in shipyards during shipbuilding, which has created the need for high-quality and high-efficiency processing methods in the industry. In this study, a surface roughness prediction model was developed using real-time data obtained during the plasma cutting process of a A106 B pipe. Subsequently, a surface roughness prediction model was developed based on cutting process variables such as current and cutting speed using an ANN. The mean square error (MSE) of the ANN prediction model was determined based on the error and prediction performance. Additionally, the accuracy of the model was evaluated through an analysis of the surface roughness prediction model using the experimental value and predictive ability of the model (PAM), where a high prediction performance of 98.69% was obtained. 조선 기자재 제작 공정의 첫 단계이자 핵심 가공 요인은 절단이라 볼 수 있다. 최근 조선소의 선박건조에 있어서 안전의 중요성이 고조되면서 절단 작업장의 환경문제가 크게 대두되고 고품질 및 고능률 가공법이 산업계를 중심으로 요구되고 있다. 본 연구에서는 A106 B 재질의 pipe를 사용하여 플라즈마 절단공정시 획득한 실시간(real-time) 데이터를 활용하여 표면 거칠기 예측모델 개발을 목표로 하였다. 절단실험의 절단 공정변수인 전류 및 절단 속도를 선정하여 ANN을 통하여 절단 공정변수에 따른 표면거칠기 예측 모델을 개발하였다. ANN 예측모델을 오차 및 예측 성능을 기반으로 평균 제곱 오차(MSE)를 비교하였다. 또한 표면 거칠기 예측모델의 분석을 통해 실험값과 PAM(predictive ability of model)을 이용하여 정확도를 평가하여 98.69%로 높은 예측성능을 확인하였다.