A novel active learning-based Gaussian process metamodelling strategy for estimating the full probability distribution in forward UQ analysis

Wang, Ziqi and Broccardo, Marco ORCID: 0000-0003-4058-260X (2020) A novel active learning-based Gaussian process metamodelling strategy for estimating the full probability distribution in forward UQ analysis. STRUCTURAL SAFETY, 84. 101937-.

Text 2020_W_B_ALCDF_f (6).pdf - Author Accepted Manuscript Download (9MB) | Preview

Abstract

This paper proposes an active learning-based Gaussian process (AL-GP) metamodelling method to estimate the cumulative as well as complementary cumulative distribution function (CDF/CCDF) for forward uncertainty quantification (UQ) problems. Within the field of UQ, previous studies focused on developing AL-GP approaches for reliability (rare event probability) analysis of expensive black-box solvers. A naive iteration of these algorithms with respect to different CDF/CCDF threshold values would yield a discretized CDF/CCDF. However, this approach inevitably leads to a trade-off between accuracy and computational efficiency since both depend (in opposite way) on the selected discretization. In this study, a specialized error measure and a learning function are developed such that the resulting AL-GP method is able to efficiently estimate the CDF/CCDF for a specified range of interest without an explicit dependency on discretization. Particularly, the proposed AL-GP method is able to simultaneously provide accurate CDF and CCDF estimation in their median-low probability regions. Three numerical examples are introduced to test and verify the proposed method.

Item Type:	Article
Uncontrolled Keywords:	Active learning, Distribution function, Gaussian process model, Rare event simulation, Uncertainty quantification
Depositing User:	Symplectic Admin
Date Deposited:	07 Apr 2020 10:25
Last Modified:	17 Mar 2024 07:07
DOI:	10.1016/j.strusafe.2020.101937
Related URLs:	Author
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3082170