Bayesian Approach for Two-Phase Degradation Data Based on Change-Point Wiener Process With Measurement Errors
- Authors
- Wang, Pingping; Tang, Yincai; Bae, Suk Joo; Xu, Ancha
- Issue Date
- Jun-2018
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Change-point; degradation data; hierarchical Bayesian method; measurement errors; two-phase; wiener process
- Citation
- IEEE TRANSACTIONS ON RELIABILITY, v.67, no.2, pp.688 - 700
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEEE TRANSACTIONS ON RELIABILITY
- Volume
- 67
- Number
- 2
- Start Page
- 688
- End Page
- 700
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/149925
- DOI
- 10.1109/TR.2017.2785978
- ISSN
- 0018-9529
- Abstract
- Degradation test is an effective method in assessing product reliability when measurements of degradation leading to failure can be observed. The accuracy of reliability inference in degradation analysis highly depends on the fitted model to the observed degradation data. Sometimes, observed degradation paths of the products exhibit multiphase pattern over the testing period. In this paper, we propose a change-point Wiener process with measurement errors (CPWPME) to fit two-phase degradation paths of organic light-emitting diodes (OLEDs). We assume the unit-specific parameters of the CPWPME model by using hierarchical Bayesian method. Based upon the proposed approach, the failure-time distribution and the remaining useful life distribution along with mean time to failure and mean residual life function are derived in closed form. A simulation study shows the utility of the proposed CPWPME model and the validity of the hierarchical Bayesian approach for the degradation data possessing two-phase degradation characteristics. In the analysis of OLED degradation data, the hierarchical Bayesian CPWPME model provides higher modeling flexibility and prediction power for future testing units than existing three degradation models.
- 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.