• 응용통계연구
• /
• 제7권2호
• /
• pp.173-182
• /
• 1994

Han(1993)의 임의의 오차분포하에서 회귀모형에의 기울기 추정법을 응용하여 회귀분위선(regression quantile)에 의해 적당한 상.하위절사가 주어질 때 점근적으로 최량의 회귀모형에서의 기울기 추정량을 구성할 수 있음을 보였다.

• 응용통계연구
• /
• 제23권2호
• /
• pp.375-382
• /
• 2010

본 논문에서는 다변량 자료의 위치모수에 대한 로버스트 추정량으로 공간중위수에 대한 절사 추정량을 제안하였다. 최적절사율은 붓스트랩 방법을 이용하여 결정하였으며, 이중붓스트랩을 활용하여 추정된 절사공간중위수의 공분산행렬을 추정하였다. 모의실험 결과 붓스트랩 방법에 의한 절사공간중위수는 자료가 다변량 코시분포를 따르는 경우 기존 공간중위수에 비하여 작은 평균제곱오차를 보여 효율적인 추정량으로 나타났다. 아울러 이중붓스트랩을 이용한 절사추정량의 공분산행렬 추정량은 단순붓스트랩 방법에 의하여 추정된 공분산행렬이 갖는 과소추정의 문제를 해결하는 방법으로 나타났다.

• 소성∙가공
• /
• 제15권4호
• /
• pp.281-288
• /
• 2006

Most of automobile member parts experience severe springback problems because of their complicated shape and high yielding strength. Now it becomes imperative to develop an effective method to resolve these problems. However, there remain several obstacles to get accurate estimation of dimensional shape. Especially the effective algorithms to simulate sheet metal forming processes including drawing, trimming, flanging and springback is demanded for the multi stage simulation of automobile member parts. In this study, for the purpose of accurate springback calculation, a simulation program which is robust in springback analysis is developed. Favorable enhancement in computation time for springback analysis by using latest equation solving technique and robust solution convergence by continuation method are achieved with the program. In analysis, the multi processes of rear side member are simulated to verify the system. For the evaluation of springback accuracy practically, all conditions including boundary conditions for springback analysis and inspection conditions for dimensional accuracy are applied. The springback results of simulations show good agreement with the experiments.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2004년도 제3회 금형가공 심포지엄
• /
• pp.71-78
• /
• 2004

Most of member parts have experienced severe springback problems because of their open shape Now it becomes imperative to develop an effective method, which can resolve these problems. However, there remain several obstacles to get accurate estimation of shape error. In analysis, we have to analyze the total process including forming, trimming and flanging. Furthermore, it is another challenge to compare the computed result with the real shape. In this study we developed an analysis program for the springback analysis. We could achive a big enhancement in computation time in springback analysis by using latest equation solving technique and could get a more robust solution conversence by contination method. We have approached this problem in two steps. In the first step, we analyzed forming stage to solve tearing and wrinkling problems. In the second step, we have analyzed full process and have done springback analysis with the same boundary condition as field measuring conditions. We have investigated the accuracy of springback analysis in terms of gap and flush used for insfection of real autobody panels. We found good and effective agreement with the observed results.