Reliability Growth of Continuous Systems.

Abstract

A three-parameter reliability growth model is developed for continuous systems, which model assumes failure rates are improved only after each failure and times between failures are exponential. The basic model is given by lambda sub n = lambda sub u + alpha n (lambda sub o - lambda sub u) where lambda sub n is the failure rate after the nth failure, lambda sub o is the initial failure rate, lambda sub u is the ultimate failure rate, and alpha is a shape parameter. Both maximum likelihood and Bayesian methods of estimating the parameters from test data were investigated. Use of the model for assessment and prediction are addressed and some comparisons are made with the AMSAA model currently in use. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 08, 1982
Accession Number
ADA114099

Entities

People

  • Darrell D. Penrod

Organizations

  • Auburn University

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Bayes Theorem
  • Bayesian Networks
  • Complex Systems
  • Computational Science
  • Computer Programs
  • Computers
  • Control Systems
  • Difference Equations
  • Differential Equations
  • Equations
  • Mechanical Engineering
  • Monte Carlo Method
  • Numerical Analysis
  • Probability
  • Random Variables
  • Reliability

Readers

  • Life Cycle Cost Analysis
  • Statistical inference.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks