Enhanced Dimension-Reduction (eDR) method for sensitivity-free uncertainty quantification

Byeng D. Youn, Zhimin Xi, Lee J. Wells, Pingfeng Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

24 Scopus citations

Abstract

In this paper, the enhanced Dimension Reduction (eDR) method is proposed for uncertainty quantification that is an improved verskn of the DR method. It has been acknowledged that the DR method is accurate and efficient for assessing statistical mo ments of mildly nonlinear system responses. However, the recent investigation on the DR method has found difficulties of instability and inaccuracy for large-scale nonlinear systems, while maintaining reasonable efficiency. The eDR method is composed of four new technical elements: one-dimensional response approximation, Axial-Design of Experiment (A-DOE), numerical integration scheme, and a modified Pearson system. First, the Stepwise Moving Least Squares method is employed to accurately approximate the responses. Second, 2N+1 and 4N+1 A-DOEs are proposed to maintain high accuracy of the eDR method for UQ analysis. Third in aid of approximated responses, any numerical integration scheme can be used with accurate but free response values at any set of integration points. Fourth, a modified Pearson system will be proposed to avcid its singular behavior while precisely predicting reliability and quality of engineering systems. Results for some engineering examples indicate that the eD R method is better than any other probability analysismethods in estimating statistical moments, reliability, and quality of the systems.

Original languageEnglish (US)
Title of host publicationCollection of Technical Papers - 11th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference
Pages849-864
Number of pages16
StatePublished - 2006
Externally publishedYes
Event11th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference - Portsmouth, VA, United States
Duration: Sep 6 2006Sep 8 2006

Publication series

NameCollection of Technical Papers - 11th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference
Volume2

Other

Other11th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference
Country/TerritoryUnited States
CityPortsmouth, VA
Period9/6/069/8/06

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Fingerprint

Dive into the research topics of 'Enhanced Dimension-Reduction (eDR) method for sensitivity-free uncertainty quantification'. Together they form a unique fingerprint.

Cite this