CONFIDENCE INTERVALS FOR THE RELIABILITY OF MULTI-COMPONENT SYSTEMS

Abstract

A procedure for finding a confidence interval for the reliability, P, of a multi-component device is presented which utilizes Bernoulli test data pertaining to the component parts. In particular, Bernoulli trials are carried out for part of a system built up from k different parts. On the basis of the number of observed failures an interval estimate of the reliability (or probability of functioning) of the system is constructed. In the series case, with k parts, the minimum and maximum of P (as a function of q's) is found. In the general case, that is, for a system having a mixture of series and parallel-connected parts, parametric minima and maxima for P are found using several approaches.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 1962
Accession Number
AD0277709

Entities

People

  • John K. Abraham

Organizations

  • Ballistic Research Laboratory

Tags

Communities of Interest

  • Weapons Technologies

DTIC Thesaurus Topics

  • Air Force
  • Air Force Facilities
  • California
  • Confidence Limits
  • Data Science
  • Experimental Design
  • Information Science
  • Military Research
  • Munitions
  • Numerical Analysis
  • Ordnance Laboratories
  • Quality Control
  • Reliability
  • Statistics
  • Universities
  • Weapon Systems
  • Weapons

Fields of Study

  • Mathematics

Readers

  • Business Analytics
  • Electronics Engineering
  • Statistical inference.