简单步加寿命试验在定时截尾逐级删失模型下的优化设计  

Optimal design of simple step stress ALT under type Ⅰ progressive censoring

作　　者：杨春燕[1] 姜万民 YANG Chun-yan, JIANG Wan-min(School of Mathematics and Statistics, Yunnan University, Kunming 650091, China)

机构地区：[1]云南大学数学与统计学院,云南昆明650091

出　　处：《云南大学学报（自然科学版）》2018年第6期1063-1070,共8页Journal of Yunnan University(Natural Sciences Edition)

基　　金：云南大学理(工)校院级科研项目(2012);国家自然科学基金(11561072;11561075;11661081)

摘　　要：研究了简单步进应力加速寿命试验在带有随机移走的定时截尾逐级删失模型下应力转换时间的优化问题.假定产品寿命服从Weibull分布,推导了似然函数和Fisher信息阵,得到了产品平均寿命估计量的渐进方差的表达式,利用Monte-Carlo方法对不同程度的移走和不同的失效模型进行模拟,通过极小化渐进方差得到了双应力步进寿命试验中应力改变时间的最优值.研究结果对实验者进行该类实验具有指导意义.We investigate the optimal plans of step stress accelerated life tests （ALT） under type I progres- sive censoring with random removals. Assume that the lifetime of the product follows a Weibull distribution, the maximum likelihood function and the Fisher information matrix are derived.Then the expression of asymptotic va- riance of the estimator of the mean lifetime is obtained.Monte-Carlo simulation is conducted to find the optimal time changing points which minimizes the asymptotic variance for different removal probabilities and lifetime pa- rameters.The results of this study could provide the guidance for the experimenter to conduct the test.

关 键 词：步进应力加速寿命试验 WEIBULL分布 随机移走 定时截尾 逐级删失 

分 类 号：O213.2[理学—概率论与数理统计]