Skip to main navigation Skip to search Skip to main content

Belief reliability evaluation with uncertain information using max entropy principle

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Belief reliability is a new reliability metric aiming to describe the reliability of components or systems affected by both aleatory uncertainty and epistemic uncertainty. A key point in belief reliability evaluation is to determine belief reliability distribution with uncertain information such as statistical characteristics of data. This paper will propose an optimal model to determine belief reliability distribution using the maximum entropy principle when k-th central moments of uncertain parameters can be obtained. An approximation algorithm based on the linear interpolation and the genetic algorithm is subsequently developed to solve the optimal model. The proposed approximation algorithm is validated by the existing max entropy theorem when only the first and second central moments are available. To further demonstrate the proposed model, it is used in the belief reliability evaluation of a suspension bridge under vessel-bridge collision when the central moments of its performance parameters are available.

Original languageEnglish
Title of host publicationProceedings of the 29th European Safety and Reliability Conference, ESREL 2019
EditorsMichael Beer, Enrico Zio
PublisherResearch Publishing Services
Pages2641-2647
Number of pages7
ISBN (Electronic)9789811127243
DOIs
StatePublished - 2020
Event29th European Safety and Reliability Conference, ESREL 2019 - Hannover, Germany
Duration: 22 Sep 201926 Sep 2019

Publication series

NameProceedings of the 29th European Safety and Reliability Conference, ESREL 2019

Conference

Conference29th European Safety and Reliability Conference, ESREL 2019
Country/TerritoryGermany
CityHannover
Period22/09/1926/09/19

Keywords

  • Belief reliability distribution
  • Belief reliability evaluation
  • Genetic algorithm
  • Linear interpolation
  • Max entropy principle

Fingerprint

Dive into the research topics of 'Belief reliability evaluation with uncertain information using max entropy principle'. Together they form a unique fingerprint.

Cite this