Efficient variance-based reliability sensitivity analysis for Monte Carlo methods

TL;DR

This paper introduces an efficient Monte Carlo-based method for variance-based sensitivity analysis of scattering input parameters affecting failure probability, capable of handling correlated variables and arbitrary distributions with a single analysis run.

Contribution

It develops a novel approach combining importance sampling and alpha-factors for comprehensive sensitivity analysis in reliability assessments.

Findings

Requires only one Monte Carlo analysis run

Handles correlated input variables effectively

Applicable to arbitrary marginal distributions

Abstract

In this paper, a Monte Carlo based approach for the quantification of the importance of the scattering input parameters with respect to the failure probability is presented. Using the basic idea of the alpha-factors of the First Order Reliability Method, this approach was developed to analyze correlated input variables as well as arbitrary marginal parameter distributions. Based on an efficient transformation scheme using the importance sampling principle, only a single analysis run by a plain or variance-reduced Monte Carlo method is required to give a sufficient estimate of the introduced parameter sensitivities. Several application examples are presented and discussed in the paper.