 A novel learning function based on Kriging for reliability analysisYan Shi, Zhenzhou Lu, Ruyang He, Yicheng Zhou and Siyu Chen Reliability Engineering and System Safety, 2020, vol. 198, issue C Abstract: Adaptively constructing the surrogate model for reliability analysis has been widely studied for the advantage of guaranteeing the estimation accuracy while calling the real performance function as little as possible. A new learning function called Folded Normal based Expected Improvement Function (FNEIF) is proposed to efficiently estimate the failure probability. Firstly, an improvement function is constructed by treating the prediction of surrogate model as folded normal variable, while the expectation function of the folded normal variable is an excellent index for measuring the contribution of a point to improve the surrogate model. Secondly, the expectation of the improvement function is analytically derived to identify the new training sample. Thirdly, a new stopping criterion is established based on the uncertainty magnitude of the prediction. Numerical and engineering application examples are introduced to show the effectiveness of the proposed learning function FNEIF for reliability analysis. Keywords: Reliability analysis; Learning function; Folded normal distribution; Surrogate model; Stopping criterion (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:eee:reensy:v:198:y:2020:i:c:s0951832019304788 DOI: 10.1016/j.ress.2020.106857 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 |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.