STRUCTURAL OPTIMIZATION USING FEMLAB AND SMOOTH SUPPORT VECTOR REGRESSION
STRUCTURAL OPTIMIZATION USING FEMLAB AND SMOOTH SUPPORT VECTOR REGRESSION
复制标题
DOI：
10.2514/6.2007-1912
复制
发表时间：
2007-08
期刊：
影响因子：
--
通讯作者：
Divija Odapally
中科院分区：
文献类型：
--
作者：
Divija Odapally
本文提出了一种有效的结构优化算法。在该方法中，优化设计是基于光滑支持向量回归（SSVR）构造的代理模型依次实现的。建议的研究工作使用准蒙特卡罗（QMC）技术的选择训练数据的设计空间。使用径向基函数核的SSVR被用来建立结构优化的元模型。结构响应由商业有限元软件FEMLAB（最近更名为COMSOL）进行评估。几个例子来说明所提出的方法的有效性。
An effective algorithm for structural optimization is proposed in this paper. In the proposed method, the optimum design is achieved sequentially based on the surrogate model constructed by smooth support vector regression (SSVR). The proposed research work uses Quasi Monte Carlo (QMC) technique for the selection of training data in the design space. SSVR using a radial basis function kernel is used to build the metamodel for structural optimization. The structural responses are evaluated by a commercial finite element package, FEMLAB (recently renamed as COMSOL). Several examples are presented to illustrate the effectiveness of the proposed approach.