Statistical analysis of accelerated degradation testing for old products with initial working time

Yuanyuan Tan, Chunhua Zhang, Xun Chen and Yashun Wang

Journal of Risk and Reliability, 2015, vol. 229, issue 2, 143-150

Abstract: Statistical analysis of accelerated degradation testing has been of interest to researchers and developers for some time. Relevant study on accelerated degradation testing mainly assumes that samples subjected to accelerated degradation testing are new products, with samples that have not pre-degraded and possess reliability equal to 1 at the beginning of accelerated degradation testing. Old products, which have a pre-existing period of initial working time under use stress, are occasionally selected for accelerated degradation testing in practice. Old products are usually considered for economical reasons, occasionally when new products are no longer manufactured. For the purposes of this study, samples of old products have been degraded to a reliability less than 1 at the beginning of accelerated degradation testing, thus preventing the use of current accelerated degradation testing methods. Improved accurate life prediction for old products is proposed through our models of degradation path and lifetime distribution for constant stress accelerated degradation testing. Initial working time under use stress is evaluated, and actual circumstances are described. A suggested maximum likelihood estimation approach is then detailed accordingly, by combining accelerated degradation testing data and field data to obtain a more accurate estimation for model parameters. Simulation and case studies prove the proposed method’s validity, effectiveness, and ability to accurately obtain improved life prediction for old products with initial working time using accelerated degradation testing.

Keywords: Accelerated degradation testing; old product; cumulative exposure model; Monte Carlo simulation; data fusion (search for similar items in EconPapers)
Date: 2015
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.sagepub.com/doi/10.1177/1748006X14566020 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sae:risrel:v:229:y:2015:i:2:p:143-150

DOI: 10.1177/1748006X14566020

Access Statistics for this article

More articles in Journal of Risk and Reliability
Bibliographic data for series maintained by SAGE Publications ().