Efficient design of experiments for sensitivity analysis based on polynomial chaos expansions

被引：1
作者：
Evgeny Burnaev
Ivan Panin
Bruno Sudret
机构：
[1] Skolkovo Institute of Science and Technology,
[2] Kharkevich Institute for Information Transmission Problems,undefined
[3] ETH Zurich,undefined
[4] Chair of Risk,undefined
[5] Safety and Uncertainty Quantification,undefined
[6] National Research University Higher School of Economics,undefined
来源：
Annals of Mathematics and Artificial Intelligence | 2017年 / 81卷
关键词：
Design of experiment; Sensitivity analysis; Sobol indices; Polynomial chaos expansions; Active learning; 62K05; 62K20; 62J10;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Global sensitivity analysis aims at quantifying respective effects of input random variables (or combinations thereof) onto variance of a physical or mathematical model response. Among the abundant literature on sensitivity measures, Sobol indices have received much attention since they provide accurate information for most of models. We consider a problem of experimental design points selection for Sobol’ indices estimation. Based on the concept of D-optimality, we propose a method for constructing an adaptive design of experiments, effective for calculation of Sobol’ indices based on Polynomial Chaos Expansions. We provide a set of applications that demonstrate the efficiency of the proposed approach.
引用
收藏
页码：187 / 207
页数：20
相关论文
共 60 条
  • [1] Morris MD(1991)Factorial sampling plans for preliminary computational experiments Technometrics 33 161-174
  • [2] Yang J(2011)Convergence and uncertainty analyses in Monte-Carlo based sensitivity analysis Environ. Model. Softw. 26 444-457
  • [3] Belyaev M(2016)GTApprox: Surrogate modeling for industrial design Adv. Eng. Softw. 102 29-39
  • [4] Burnaev E(1993)Sensitivity estimates for nonlinear mathematical models Math. Model. Comp. Exp. 1 407-414
  • [5] Kapushev E(2010)How to avoid a perfunctory sensitivity analysis Environ. Model. Softw. 25 1508-1517
  • [6] Panov M(1978)Nonlinear sensitivity analysis of multiparameter model systems J. Comput. Phys. 26 1-42
  • [7] Prikhodko P(1974)Cross-validatory choice and assessment of statistical predictions J. R. Stat. Soc. Ser. B 36 111-147
  • [8] Vetrov D(2009)Calculations of the Sobol indices for the Gaussian process metamodel Reliab. Eng. Syst. Saf. 94 742-751
  • [9] Yarotsky D(2013)Properties of the posterior distribution of a regression model based on Gaussian random fields Autom. Remote. Control. 74 1645-1655
  • [10] Sobol’ IM(2013)The Bernstein-von Mises theorem for regression based on Gaussian processes Russ. Math. Surv. 68 954-956
123456