期刊
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS
卷 46, 期 1, 页码 176-188出版社
TAYLOR & FRANCIS INC
DOI: 10.1080/03610926.2014.988262
关键词
Akaike information criterion; Bayesian evaluation; Change point; Real-time reliability; Two-phase Wiener degradation process
资金
- National Science Foundation of China (NSFC) [71171164]
Reliability modeling and evaluation for the two-phase Wiener degradation process are studied. For many devices, the degradation rates could possibly increase or decrease in a non smooth manner at some point in time due to the change of degradation mechanism. A two-phase Wiener degradation process with an unobserved change point is used to model the degradation process. And we assume that the change point varies randomly from device to device. Furthermore, we integrate historical data and up-to-date observation data to improve the degradation modeling and evaluation based on Bayesian method. The change point between the two phases was obtained based on the Akaike information criterion (AIC) and the criterion of the residual sum of squares. Finally, a real example of liquid coupling devices (LCDs) and a numeric example are discussed to demonstrate the effectiveness of the proposed method. The results show that the proposed method is effective and efficient.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据