Flooding Fragility Model Development Using Bayesian Regression

Alison Wells and Chad L. Pope

A chapter in The Monte Carlo Methods - Recent Advances, New Perspectives and Applications from IntechOpen

Abstract: Traditional component pass/fail design analysis and testing protocol drives excessively conservative operating limits and setpoints as well as unnecessarily large margins of safety. Component performance testing coupled with failure probability model development can support selection of more flexible operating limits and setpoints as well as softening defense-in-depth elements. This chapter discuses the process of Bayesian regression fragility model development using Markov Chain Monte Carlo methods and model checking protocol using three types of Bayesian p-values. The chapter also discusses application of the model development and testing techniques through component flooding performance experiments associated with industrial steel doors being subjected to a rising water scenario. These component tests yield the necessary data for fragility model development while providing insight into development of testing protocol that will yield meaningful data for fragility model development. Finally, the chapter discusses development and selection of a fragility model for industrial steel door performance when subjected to a water-rising scenario.

Keywords: fragility model development; Bayesian regression; Markov Chain Monte Carlo; fragility model checking; Bayesian p-value (search for similar items in EconPapers)
JEL-codes: C10 (search for similar items in EconPapers)
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.intechopen.com/chapters/78082 (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:ito:pchaps:243406

DOI: 10.5772/intechopen.99556

Access Statistics for this chapter

More chapters in Chapters from IntechOpen
Bibliographic data for series maintained by Slobodan Momcilovic ().