Sparse Grid Initialization

When Design of Experiments Type is set to Sparse Grid Initialization for a Design of Experiments cell in a Response Surface system, the adaptive model that runs is driven by the accuracy that you request. This DOE type increases the accuracy of the response surface by automatically refining the matrix of design points in locations where the relative error of the output parameter is higher. It generates the levels 0 and 1 of the Clenshaw-Curtis Grid. Because Sparse Grid Initialization is based on a hierarchy of grids, the DOE generated contains all of the design points for the smallest required grid: the level 0 (the point at the current values) plus the level 1 (two points per input parameters).

One advantage of Sparse Grid Initialization is that it refines only in the directions necessary, so that fewer design points are needed for the same quality response surface. Another is that it is effective at handling discontinuities. Although you must use this DOE type to build a Sparse Grid response surface, you can also use it for other types of response surfaces.

No additional properties are available for Sparse Grid Initialization.


Release 18.2 - © ANSYS, Inc. All rights reserved.