Reliability Estimation in Load-Sharing System Model with Application to Real Data

This study deals with the reliability analysis of a multi-component load sharing system where failure of any component within the system induces higher failure rate on the remaining surviving components. It is assumed that each component failure time follows Chen distribution. In classical set up, t...

Full description

Saved in:
Bibliographic Details
Published inAnnals of data science Vol. 5; no. 1; pp. 69 - 91
Main Authors Pundir, Pramendra Singh, Gupta, Puneet Kumar
Format Journal Article
LanguageEnglish
Published Berlin/Heidelberg Springer Berlin Heidelberg 01.03.2018
Springer Nature B.V
Subjects
Artificial Intelligence
Business and Management
Component reliability
Confidence intervals
Data analysis
Economics
Failure analysis
Failure rates
Failure times
Finance
Insurance
Load sharing
Management
Maximum likelihood estimates
Parameter estimation
Reliability analysis
Statistics for Business
System reliability
Gibbs sampler
Metropolis-Hasting algorithm
Load-sharing system model
Chen distribution
Simulation
Online AccessGet full text

Cover

More Information
Summary:This study deals with the reliability analysis of a multi-component load sharing system where failure of any component within the system induces higher failure rate on the remaining surviving components. It is assumed that each component failure time follows Chen distribution. In classical set up, the maximum likelihood estimates of the load sharing parameters, system reliability and hazard rate along with their standard errors are computed. Since maximum likelihood estimates are not in closed form, so asymptotic confidence intervals and two bootstrap confidence intervals for the unknown parameters have also been constructed. Further, by assuming both informative and non-informative prior for the unknown parameters, Bayes estimates along with their posterior standard errors and HPD intervals of the parameters are obtained. Thereafter, a simulation study elicitates the theoretical developments. A real data analysis, at the end, eshtablishes the applicability of the proposed theory.
ISSN:2198-5804
2198-5812
DOI:10.1007/s40745-017-0120-5