TY - JOUR
T1 - A Bayesian reliability evaluation method with different types of data from multiple sources
AU - Wang, Lizhi
AU - Pan, Rong
AU - Wang, Xiaohong
AU - Fan, Wenhui
AU - Xuan, Jinquan
N1 - Funding Information:
The first, third, fourth and fifth authors gratefully acknowledge the support of the Fundamental Research Funds for the Central Universities and the Aero-Science Fund (No. 2014ZC51031 and No. 2015ZD51044). The second author thanks the NSF grant CMMI 1301075 for its support of his research. We would like to thank the reviewers for their helpful and valuable comments on the previous version of this paper.
Publisher Copyright:
© 2017 Elsevier Ltd
PY - 2017/11
Y1 - 2017/11
N2 - Bernoulli data (pass/fail), lifetime data, and degradation data are commonly encountered in product reliability assessment. Oftentimes these data are collected from different sources (such as field use, accelerated tests, history, and so on), and it is desirable to utilize these heterogeneous data within one computational framework to provide a comprehensive evaluation of product reliability. In this paper, three Bayesian inference models are proposed to establish the relationship among pass/fail-type Bernoulli data, lifetime data, and degradation data, and to integrate them to solve relevant problems and improve the accuracy of reliability prediction. The proposed methods are demonstrated by a synthetic example and two real examples. The evaluation results can be used for formulating product development strategies.
AB - Bernoulli data (pass/fail), lifetime data, and degradation data are commonly encountered in product reliability assessment. Oftentimes these data are collected from different sources (such as field use, accelerated tests, history, and so on), and it is desirable to utilize these heterogeneous data within one computational framework to provide a comprehensive evaluation of product reliability. In this paper, three Bayesian inference models are proposed to establish the relationship among pass/fail-type Bernoulli data, lifetime data, and degradation data, and to integrate them to solve relevant problems and improve the accuracy of reliability prediction. The proposed methods are demonstrated by a synthetic example and two real examples. The evaluation results can be used for formulating product development strategies.
KW - Bayesian method
KW - Bernoulli data
KW - Data from multiple sources
KW - Data integration
KW - Reliability evaluation
UR - http://www.scopus.com/inward/record.url?scp=85020005311&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85020005311&partnerID=8YFLogxK
U2 - 10.1016/j.ress.2017.05.039
DO - 10.1016/j.ress.2017.05.039
M3 - Article
AN - SCOPUS:85020005311
SN - 0951-8320
VL - 167
SP - 128
EP - 135
JO - Reliability Engineering and System Safety
JF - Reliability Engineering and System Safety
ER -