基于变点伽马过程的退化数据分析——贝叶斯角度  

Degradation Data Analysis Based on Change-Point Gamma Process:A Bayesian Perspective

作　　者：王平平 汤银才[2] 程恭品 WANG Pingping;TANG Yincai;CHENG Gongpin(School of Economics,Nanjing University of Finance and Economics,Nanjing,210023,China;School of Statistics,East China Normal University,Shanghai,200062,China)

机构地区：[1]南京财经大学经济学院,南京210023 [2]华东师范大学统计学院,上海200062

出　　处：《应用概率统计》2022年第5期674-692,共19页Chinese Journal of Applied Probability and Statistics

基　　金：supported by the National Natural Science Foundation of China(Grant Nos.12001266,11801265);the Natural Science Foundation of Jiangsu Province(Grant No.BK20180813);the Natural Science Foundation of Higher Education Institutions of Jiangsu Province(Grant No.18KJB110010);the Ministry of Education Humanities and Social Sciences Research Youth Fund Project(Grant No.19YJCZH166)。

摘　　要：随着科技的进步和材料科学的发展,产品的可靠性不断增强,具有较长的寿命.因此传统的寿命试验逐渐被退化实验所替代.在退化实验中,质量特征(QC)随着时间退化,它可以反应产品的可靠性状态.有些质量特征的退化轨道通常随时间单调递增且非光滑的函数.本文受N通道功率金属氧化物半导体场效应晶体管(MOSFET)的实验退化数据的启发,提出了层次贝叶斯框架下的两阶段伽马过程模型对单调非光滑的退化数据建模.模拟研究验证了三种情形下所提出模型的有用性.为了证明所提出方法的应用性,分析了一个说明性的抗辐射性能案例数据.As the development of the technology and material science,products become highly reliable with long lifetimes.Consequently,the traditional life tests are gradually replaced by the degradation tests.In the degradation tests,the quality characteristic(QC)which degrades over time,can reflect the reliability status of the product.Some of the degradation paths of the QC are usually monotonically increasing and non-smooth function of time.In this paper,motivated by the degradation data from the tests of N-channel power metal oxide semiconductor field-effect transistor(MOSFET),we propose a two-phase gamma process under hierarchical Bayesian framework to model the monotonic and non-smooth degradation data.A simulation study is performed to verify the utility of the proposed model under three scenarios.An illustrative anti-radiation performance case study is analyzed to show the applicable power of the proposed model.

关 键 词：变点 退化数据 层次贝叶斯方法 伽马过程 

分 类 号：O212.1[理学—概率论与数理统计]