On the fitting of bathtub-shaped failure models to lifetime data for selective maintenance optimization

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

Abstract

The maximum likelihood estimate is a method for fitting failure models to lifetime data. In the literature, a commonly used practice is to find a combination of model parameter values where the partial derivatives of the log-likelihood are zero. We show that greater log-likelihood values can be found by using the Nelder-Mead optimization algorithm with adaptive parameters. We demonstrate that the improved fitting has a significant impact on the decision-making on a selective maintenance optimization problem, defined using the failure model by Sarhan and Apaloo (Reliab Eng & Syst Saf, 2013, 112, 137-144).

Original languageEnglish
Title of host publicationComputer Aided Chemical Engineering
EditorsMetin Türkay, Rafiqul Gani
PublisherElsevier
Pages605-610
Number of pages6
ISBN (Electronic)978-0-323-88513-3
ISBN (Print)978-0-323-88506-5
DOIs
Publication statusPublished - 25 Jun 2021
MoE publication typeA4 Article in a conference publication
EventEuropean Symposium on Computer Aided Process Engineering - Virtual, Online
Duration: 6 Jun 20219 Jun 2021
Conference number: 31

Publication series

NameComputer Aided Chemical Engineering
Volume50
ISSN (Print)1570-7946

Conference

ConferenceEuropean Symposium on Computer Aided Process Engineering
Abbreviated titleESCAPE
CityVirtual, Online
Period06/06/202109/06/2021

Keywords

  • decision-making
  • model fitting
  • optimization
  • reliability

Fingerprint

Dive into the research topics of 'On the fitting of bathtub-shaped failure models to lifetime data for selective maintenance optimization'. Together they form a unique fingerprint.

Cite this