Long-Term Life Test Data Modeling and Field Correlation — An HDD Experience

Not every company can afford or is willing to invest in long-term life testing due to time and cost constraints. But such a test can provide very valuable insight about product field behavior during its lifetime. Authors of this paper present a case study on hard disk drive long-term life test data...

Full description

Saved in:
Bibliographic Details
Published in:International journal of reliability, quality, and safety engineering quality, and safety engineering, 2017-04, Vol.24 (2), p.1750008
Main Authors: Sun, Feng-Bin, Zhang, Yao
Format: Article
Language:English
Subjects:
Data analysis
Disk drives
Modelling
Parameter estimation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Not every company can afford or is willing to invest in long-term life testing due to time and cost constraints. But such a test can provide very valuable insight about product field behavior during its lifetime. Authors of this paper present a case study on hard disk drive long-term life test data analysis. In order to deal with the non-monotonic hazard rate behavior, the bi-modal mixed life distribution and bi-modal competing failure modeling are applied to fit the time to failure data. The model parameters’ estimation, their physical implications, and field long-term reliability predictions using these two approaches are discussed and compared. The recommendations are given regarding the applicability of each model from an engineering application perspective.
ISSN:0218-5393
1793-6446
DOI:10.1142/S0218539317500085