8 0

Bayesian Approach for Two-Phase Degradation Data Based on Change-Point Wiener Process With Measurement Errors

Title
Bayesian Approach for Two-Phase Degradation Data Based on Change-Point Wiener Process With Measurement Errors
Author
배석주
Keywords
Change-point; degradation data; hierarchical Bayesian method; measurement errors; two-phase; wiener process
Issue Date
2018-06
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation
IEEE TRANSACTIONS ON RELIABILITY, v. 67, no. 2, page. 688-700
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.
URI
https://ieeexplore.ieee.org/document/8281548http://repository.hanyang.ac.kr/handle/20.500.11754/118955
ISSN
0018-9529; 1558-1721
DOI
10.1109/TR.2017.2785978
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > INDUSTRIAL ENGINEERING(산업공학과) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE