Bayes Inference for General Repairable Systems

• Autores: Rong Pan, Steve E. Rigdon
• Localización: Journal of quality technology: A quarterly journal of methods applications and related topics, ISSN 0022-4065, Vol. 41, Nº. 1, 2009, págs. 82-94
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Models for repairable systems can be characterized by the effect of the failure and the subsequent repair. Conventional repair models consider two extremes: As-bad-as-old models that lead to the nonhomogeneous Poisson process and the as-good-as-new models that lead to the renewed process. Bayesian methods are considered for models that are a compromise between these extremes. For multiple systems, a hierarchical Bayesian model is proposed. Markov chain Monte Carlo methods are use to approximate properties of the posterior distributions.