http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
오류역전파 알고리즘을 이용한 사출성형 금형 냉각회로 최적화
이병옥(B. O. Rhee),태준성(J. S. Tae),최재혁(J. H. Choi) 한국생산제조학회 2009 한국생산제조학회지 Vol.18 No.4
The cooling stage greatly affects the product quality in the injection molding process. The cooling system that minimizes temperature variance in the product surface will improve the quality and the productivity of products. The cooling circuit optimization problem that was once solved by a response surface method with 4 design variables. It took too much time for the optimization as an industrial design tool. It is desirable to reduce the optimization time. Therefore, we tried the back-propagation algorithm of artificial neural network(BPN) to find an optimum solution in the cooling circuit design in this research. We tried various ways to select training points for the BPN. The same optimum solution was obtained by applying the BPN with reduced number of training points by the fractional factorial design.
사출금형 냉각회로 자동최적화를 위한 설계변수 감소 방안
이병옥,최재혁,태준성,Rhee, B.O.,Choi, J.H.,Tae, J.S. 한국생산제조학회 2009 한국생산제조학회지 Vol.26 No.3
The injection mold cooling circuit optimization was studied with a response surface method in the previous research. It took so much time to find an optimum solution for a large product due to an extensive amount of calculation time for the CAE analysis. In order to use the optimization technique in the actual design process, the calculation time should be much reduced. In this study, we tried to reduce the number of design variables with the concept of the close relationship between the depth and the distance of cooling channel. The optimum ratio of the distance to the depth of cooling channels for a 2-dimensional problem was 2.0 so that the optimum ratio was again sought out for 4 large automotive parts. Therefore, the number of design variables for the cooling circuit optimization can be reduced in half, resulting in much faster running time for the optimization as a design tool.
오류역전파 알고리즘을 이용한 사출성형 금형 냉각회로 최적화
이병옥,태준성,최재혁,Rhee, B.O.,Tae, J.S.,Choi, J.H. 한국생산제조학회 2009 한국생산제조학회지 Vol.26 No.3
The cooling stage greatly affects the product quality in the injection molding process. The cooling system that minimizes temperature variance in the product surface will improve the quality and the productivity of products. The cooling circuit optimization problem that was once solved by a response surface method with 4 design variables. It took too much time for the optimization as an industrial design tool. It is desirable to reduce the optimization time. Therefore, we tried the back-propagation algorithm of artificial neural network(BPN) to find an optimum solution in the cooling circuit design in this research. We tried various ways to select training points for the BPN. The same optimum solution was obtained by applying the BPN with reduced number of training points by the fractional factorial design.
사출금형 냉각회로 자동최적화를 위한 설계변수 감소 방안
이병옥(B. O. Rhee),최재혁(J. H. Choi),태준성(J. S. Tae) 한국생산제조학회 2009 한국생산제조학회지 Vol.18 No.4
The injection mold cooling circuit optimization was studied with a response surface method in the previous research. It took so much time to find an optimum solution for a large product due to an extensive amount of calculation time for the CAE analysis. In order to use the optimization technique in the actual design process, the calculation time should be much reduced. In this study, we tried to reduce the number of design variables with the concept of the close relationship between the depth and the distance of cooling channel. The optimum ratio of the distance to the depth of cooling channels for a 2-dimensional problem was 2.0 so that the optimum ratio was again sought out for 4 large automotive parts. Therefore, the number of design variables for the cooling circuit optimization can be reduced in half, resulting in much faster running time for the optimization as a design tool.