Global sensitivity analysis for multivariate outputs based on multiple response Gaussian process model
Pan Wang and
Reliability Engineering and System Safety, 2019, vol. 189, issue C, 287-298
The computational models in real-world applications commonly have multivariate dependent outputs of interest, and developing global sensitivity analysis techniques, so as to measure the effect of each input variable on each output as well as their dependence structure, has become a critical task. In this paper, a new moment-independent sensitivity index is firstly developed for quantifying the effect of each input variable on the dependence structure of model outputs. Then, the multiple response Gaussian process (MRGP) surrogate model with separable covariance is introduced for efficiently estimating the existing sensitivity indices for multiple response models and the newly developed one. Some indices are analytically derived based on the hyper-parameters of the MRGP model, while others are numerically estimated. One numerical example and three engineering examples are introduced to compare the newly developed sensitivity index with the classical ones, and to demonstrate the effectiveness of the MRGP-based method in estimating these sensitivity indices.
Keywords: Global sensitivity analysis; Multivariate outputs; Dependence structure; Copula; Multiple response Gaussian process model (search for similar items in EconPapers)
References: View references in EconPapers View complete reference list from CitEc
Citations: Track citations by RSS feed
Downloads: (external link)
Full text for ScienceDirect subscribers only
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: https://EconPapers.repec.org/RePEc:eee:reensy:v:189:y:2019:i:c:p:287-298
Access Statistics for this article
Reliability Engineering and System Safety is currently edited by Carlos Guedes Soares
More articles in Reliability Engineering and System Safety from Elsevier
Bibliographic data for series maintained by Dana Niculescu ().