Saddlepoint approximation-based reliability analysis method for structural systems with parameter uncertainties

Ning-Cong Xiao, Yan-Feng Li, Le Yu, Zhonglai Wang and Hong-Zhong Huang

Journal of Risk and Reliability, 2014, vol. 228, issue 5, 529-540

Abstract: Due to epistemic uncertainty, precisely determining parameters of all distribution is impossible in engineering practice. In this article, a novel reliability analysis method based on the saddlepoint approximation is proposed for structural systems with parameter uncertainties. The proposed method includes four main steps: (1) sampling for random and probability-box variables, (2) approximating the cumulant generating functions for systems under the best and worst cases, (3) calculating saddlepoints for the best and worst cases, and (4) calculating the lower and upper bounds of the probability of failure. The proposed method is effective because it does not require a large sample size or solving complicated integrals. Furthermore, the proposed method provides results that have the same accuracy as the existing interval Monte Carlo simulation method, but with significantly reduced computational effort. The effectiveness of the proposed method is demonstrated with three examples that are compared against with the interval Monte Carlo simulation method.

Keywords: Epistemic uncertainty; probability-box; Monte Carlo simulation; saddlepoint approximation; parameter uncertainty (search for similar items in EconPapers)
Date: 2014
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.sagepub.com/doi/10.1177/1748006X14537619 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sae:risrel:v:228:y:2014:i:5:p:529-540

DOI: 10.1177/1748006X14537619

Access Statistics for this article

More articles in Journal of Risk and Reliability
Bibliographic data for series maintained by SAGE Publications ().