A NUMERICAL INTEGRATION MOMENT ESTIMATION METHOD USING ANISOTROPIC SPARSE GRID
Statistic moments estimation is a paramount task in structure design optimization under uncertainty.In the existing isotropic sparse grid based moments estimation method, each dimension is simply considered to be of equal importance.Therefore, curse of dimensionality more or less exists.To address this issue, a new numerical integration based moment estimation approach is developed by employing the anisotropic sparse grid technique in this paper.A new rule which allows different accuracy levels to each dimension according to their varying importance is proposed to determine the eligible multi-index combinations.Therefore, integration points can be collocated more reasonably that more points can be removed from the unimportant dimensions to the important ones.The effectiveness of the proposed approach is demonstrated through comparative studies on two mathematical examples.It is observed that compared to the existing method, the proposed approach can mitigate the curse of dimensionality problem and significantly improve the accuracy of statistic moment estimation with even less or almost equal computational cost.
Moment Estimation Numerical Integration Sparse Grid Curse of Dimensionality
Fenfen Xiong Shuxing Yang Gaorong Sun Liangyu Zhao
School of Aerospace Engineering,Beijing Institute of Technology,Beijing 100081,China
国际会议
黄山
英文
1-6
2012-06-18（万方平台首次上网日期，不代表论文的发表时间）