Bayesian Estimation of Reliability for Components with Independent, Normally Distributed Characteristics.

Abstract

This report presents an approach to component reliability assessment for the case where component reliability is defined as the probability that an appropriate set of observable characteristics will fall within specified limits and where the component characteristics are assumed to be independently and normally distributed. A Bayesian statistical approach is employed, the results of which can be directly applied in a system reliability assessment approach previously documented. The formulation, computational algorithm, and examples of applications are provided. The approach is then generalized and, as an example, applied to the Poisson process yielding time-to-failure data from an exponential distribution.

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1974
Accession Number
ADA003248

Entities

People

  • John G. Mardo
  • Thomas G Mccarthy

Organizations

  • Picatinny Arsenal

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Probability
  • Reliability

Fields of Study

  • Engineering

Readers

  • Computational Modeling and Simulation
  • Statistical inference.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms