Adaptive CAD-Model Construction Schemes

被引:5
作者
Lamecki, Adam [1 ]
Balewski, Lukasz [1 ]
Mrozowski, Michal [1 ]
机构
[1] Gdansk Univ Technol, PL-80952 Gdansk, Poland
关键词
Artificial neural networks (ANNs); CAD models; multivariate rational interpolation; radial basis functions (RBF); MICROWAVE CIRCUITS; NEURAL-NETWORKS; CAUCHY METHOD; INTERPOLATION; ALGORITHM;
D O I
10.1109/TMAG.2009.2012736
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Two advanced surrogate model construction techniques are discussed in this paper. The models employ radial basis function (RBF) interpolation scheme or artificial neural networks (ANN) with a new training algorithm. Adaptive sampling technique is applied with respect to all variables. Histograms showing the quality of the models are presented. While the quality of RBF models is satisfactory, the performance of the ANN models obtained with a new training scheme is superior and comparable to the rational function models.
引用
收藏
页码:1538 / 1541
页数:4
相关论文
共 15 条