Achieving growth in reliability

J.I. Ansell, L.A. Walls, J.L. Quigley

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

There exists a considerable literature on reliability growth modelling. Recently somecommon models have been extended to encompass innovation. They assume the time of aninnovation is known and that there is a coincidental improvement in performance. However,despite such developments, it remains that most models do not fully address the engineeringconcerns as they do not capture the underlying physical processes and they tend to beoptimistic about ensuing performance. This paper aims to address these issues by specifyinga general framework for reliability growth that supports more effective modelling. Further,we develop a strategy for using such models proactively during development to facilitatemeaningful improvements in reliability performance.
LanguageEnglish
Pages11-24
Number of pages13
JournalAnnals of Operations Research
Volume91
DOIs
Publication statusPublished - 1999

Fingerprint

Modeling
Innovation

Keywords

  • reliability growth
  • innovation
  • data analysis
  • Bayesian statistics
  • importance measures
  • Monte Carlo Markov chains

Cite this

@article{1605125e46cb42bd814e0fcec030a079,
title = "Achieving growth in reliability",
abstract = "There exists a considerable literature on reliability growth modelling. Recently somecommon models have been extended to encompass innovation. They assume the time of aninnovation is known and that there is a coincidental improvement in performance. However,despite such developments, it remains that most models do not fully address the engineeringconcerns as they do not capture the underlying physical processes and they tend to beoptimistic about ensuing performance. This paper aims to address these issues by specifyinga general framework for reliability growth that supports more effective modelling. Further,we develop a strategy for using such models proactively during development to facilitatemeaningful improvements in reliability performance.",
keywords = "reliability growth, innovation, data analysis, Bayesian statistics, importance measures, Monte Carlo Markov chains",
author = "J.I. Ansell and L.A. Walls and J.L. Quigley",
year = "1999",
doi = "10.1023/A:1018985303897",
language = "English",
volume = "91",
pages = "11--24",
journal = "Annals of Operations Research",
issn = "0254-5330",

}

Achieving growth in reliability. / Ansell, J.I.; Walls, L.A.; Quigley, J.L.

In: Annals of Operations Research, Vol. 91, 1999, p. 11-24.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Achieving growth in reliability

AU - Ansell, J.I.

AU - Walls, L.A.

AU - Quigley, J.L.

PY - 1999

Y1 - 1999

N2 - There exists a considerable literature on reliability growth modelling. Recently somecommon models have been extended to encompass innovation. They assume the time of aninnovation is known and that there is a coincidental improvement in performance. However,despite such developments, it remains that most models do not fully address the engineeringconcerns as they do not capture the underlying physical processes and they tend to beoptimistic about ensuing performance. This paper aims to address these issues by specifyinga general framework for reliability growth that supports more effective modelling. Further,we develop a strategy for using such models proactively during development to facilitatemeaningful improvements in reliability performance.

AB - There exists a considerable literature on reliability growth modelling. Recently somecommon models have been extended to encompass innovation. They assume the time of aninnovation is known and that there is a coincidental improvement in performance. However,despite such developments, it remains that most models do not fully address the engineeringconcerns as they do not capture the underlying physical processes and they tend to beoptimistic about ensuing performance. This paper aims to address these issues by specifyinga general framework for reliability growth that supports more effective modelling. Further,we develop a strategy for using such models proactively during development to facilitatemeaningful improvements in reliability performance.

KW - reliability growth

KW - innovation

KW - data analysis

KW - Bayesian statistics

KW - importance measures

KW - Monte Carlo Markov chains

UR - http://dx.doi.org/10.1023/A:1018985303897

U2 - 10.1023/A:1018985303897

DO - 10.1023/A:1018985303897

M3 - Article

VL - 91

SP - 11

EP - 24

JO - Annals of Operations Research

T2 - Annals of Operations Research

JF - Annals of Operations Research

SN - 0254-5330

ER -