Optimization of variable blank holder force trajectory by sequential approximate optimization with RBF network

摘要: Sequential approximate optimization (SAO) is an attractive approach for design optimization. In this paper, the radial basis function (RBF) network employed SAO. First, we examine width of Gaussian kernel, which affects response surface. By examining simple estimate proposed by Nakayama, four sufficient conditions are introduced. Then, a new in kernel proposed. Second, sampling strategy with RBF also order to find sparse region, density developed. The and examined through benchmark problems. Finally, SAO applied optimal variable blank holder force (VBHF) trajectory square cup deep drawing. objective taken as minimization deviation whole thickness. constraints quantitatively defined forming limit diagram no wrinkling tearing can be observed. variables force. particular, risk both handled separately. Numerical simulation carried out VBHF It clear from numerical that