Cost-effective degradation test plan for a nonlinear random-coefficients model
- Authors
- Kim, Seong-Joon; Bae, Suk Joo
- Issue Date
- Feb-2013
- Publisher
- ELSEVIER SCI LTD
- Keywords
- Degradation test; D-optimal design; Fisher information matrix; Nonlinear random-coefficients model; Reliability
- Citation
- RELIABILITY ENGINEERING & SYSTEM SAFETY, v.110, pp.68 - 79
- Indexed
- SCIE
SCOPUS
- Journal Title
- RELIABILITY ENGINEERING & SYSTEM SAFETY
- Volume
- 110
- Start Page
- 68
- End Page
- 79
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/163467
- DOI
- 10.1016/j.ress.2012.09.010
- ISSN
- 0951-8320
- Abstract
- The determination of requisite sample size and the inspection schedule considering both testing cost and accuracy has been an important issue in the degradation test. This paper proposes a cost-effective degradation test plan in the context of a nonlinear random-coefficients model, while meeting some precision constraints for failure-time distribution. We introduce a precision measure to quantify the information losses incurred by reducing testing resources. The precision measure is incorporated into time-varying cost functions to reflect real circumstances. We apply a hybrid genetic algorithm to general cost optimization problem with reasonable constraints on the level of testing precision in order to determine a cost-effective inspection scheme. The proposed method is applied to the degradation data of plasma display panels (PDPs) following a bi-exponential degradation model. Finally, sensitivity analysis via simulation is provided to evaluate the robustness of the proposed degradation test plan.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 산업공학과 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.