.png){kind=icon}
返回
Reliability-oriented global sensitivity analysis using subset simulation and space partition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ress.2023.109794.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper presents a novel reliability-oriented global sensitivity analysis method using the Subset Simulation (SS) method and the Space Partition (SP) scheme. It can exploit the inherent information of uncertainty within all the conditional samples in each simulation level of SS along the spirit of the SP scheme. The reasoning of the first order indices is firstly provided, followed by a heuristic study on the influence of parametric settings upon the statistical properties of the indices. By extending the calculation process to the higher order indices and formally optimizing the partition scheme considering the coefficient of variation of all the indices, the framework of the proposed reliability-oriented global sensitivity for arbitrary order of indices can be formed. The performance of the direct Monte Carlo method, the Quasi-Monte Carlo method, SP and the proposed method is compared through three numerical examples and two engineering applications, to demonstrate the merits of the proposed one.
Keyword:
Global sensitivity
Reliability-oriented sensitivity analysis
Space-partition scheme
Subset simulation
期刊
R
IF:
11
论文数:
9.0K
被引数:
4.2W
机构
引用论文
.png){kind=icon}
分享收藏
查看更多内容