Response surface method for optimum design of composite stiffened shells
暂无分享,去创建一个
Publisher Summary This chapter presents a paper that discusses response surface method for the optimum design of composite stiffened shells. It focuses on application of response-surface method in the design of composite shells. The response-surface method consists of two stages. In the first stage, an experimental design is selected to perform a deterministic computer simulation in the sample points. The experimental design considered is based on a combination of the Latin hypercube approach and the D-optimal design. In the second stage, the approximation of the original functions is performed to obtain response surfaces. The original functions represent behavioral constraints in the optimum design problem of the structure. Values of the original function in the points of experimental designs are obtained by the finite element method. The design variables are the thickness of layers in the skin and in blade-type stiffeners and the stiffener geometric parameters.
[1] T. Simpson,et al. Comparative studies of metamodelling techniques under multiple modelling criteria , 2001 .
[2] Timothy W. Simpson,et al. On the Use of Statistics in Design and the Implications for Deterministic Computer Experiments , 1997 .
[3] Art B. Owen,et al. 9 Computer experiments , 1996, Design and analysis of experiments.
[4] R. H. Myers,et al. Response Surface Methodology: Process and Product Optimization Using Designed Experiments , 1995 .