Design of developmental test programs for one-shot systems with two state reliability

Thumbnail Image
Date
1995
Authors
Huang, Mu-Yeh
Major Professor
Advisor
Stephen Vardeman
Douglas McBeth
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Altmetrics
Authors
Research Projects
Organizational Units
Organizational Unit
Journal Issue
Is Version Of
Versions
Series
Department
Statistics
Abstract

This dissertation considers efficient developmental testing for one-shot systems (for example, missiles) that are destroyed in testing or first normal use, where there is the possibility of "reliability growth" of the basic system design as a result of redesigns following failed developmental tests. We consider situations where the cost of redesign is negligible and there is a fixed procurement budget covering both system development and purchase, each developmental test produces either a binary (success-failure) or a continuous outcome. The analysis offered here is intended as an answer to the question "How much testing is enough?" posed by Seglie (1992) in the context of the procurement of military weapons systems. For a particular two-state model of system reliability, dynamic programming is used to identify testing plans/stopping rules that are optimal in the sense of maximizing the expected number of effective systems (of the final design) that can be purchased with the remaining budget when developmental testing is terminated. Several reasonable and easily implemented sub-optimal rules are also considered, and their performances are compared to that of the optimal rule for a variety of combinations of model parameters.

Comments
Description
Keywords
Citation
Source
Copyright
Sun Jan 01 00:00:00 UTC 1995