The prediction of remaining useful lifetime for the Weibull k-out-of-n load-sharing system. (May 2023)

• Record Type: Journal Article
• Authors: Qin, Shuidan; Wang, Bing Xing; Tsai, Tzong-Ru; Wang, Xiaofei
• Is Part Of: Reliability engineering & system safety. Volume 233(2023)
• Publication Date: 2023-05
• Subjects: Reliability -- Load-sharing system -- Remaining useful lifetime -- Tampered failure rate model -- Bootstrap-type prediction interval; Reliability (Engineering) -- Periodicals; System safety -- Periodicals; Industrial safety -- Periodicals; Fiabilité -- Périodiques; Sécurité des systèmes -- Périodiques; Sécurité du travail -- Périodiques; 620.00452
• DOI: 10.1016/j.ress.2023.109091
• Languages: English
• ISSNs: 0951-8320

Abstract

Abstract: In this paper, the prediction intervals of the off-line and online remaining useful lifetimes for the k -out-of- n load-sharing system is studied under the equal load-sharing rule. When the lifetime of each component follows the Weibull distribution, the maximum likelihood estimators and two-stage estimators of the model parameters, system reliability and mean lifetime are proposed. The Wald and bootstrap-type confidence intervals for the model parameters are developed. The performance of the proposed prediction intervals is assessed by using Monte Carlo simulation. The simulation results indicate that the coverage probabilities of the proposed bootstrap-type prediction intervals are close to the nominal confidence levels even if the sample size is small. A real example is utilized to illustrate the proposed bootstrap-type prediction interval methods. Highlights: Distributions of off-line and online remaining useful life are derived. Existence of maximum likelihood estimates is discussed. Two-stage estimators of model parameters are provided. Prediction intervals of off-line and online remaining useful life are obtained.