小样本条件下双应力步降加速退化试验优化设计

针对小样本条件下高可靠性长寿命产品的性能往往受到多个应力的影响,且在加速退化试验中该类产品在有限试验时间内难以获得大量性能退化信息的问题,提出一种小样本条件下双应力步降加速退化试验优化设计方法。采用Monte-Carlo对加速试验进行仿真模拟,在样本量大小一定的条件下,以监测频率、应力水平数、监测次数作为设计变量,以总的试验费用作为约束条件,以正常使用应力下的p阶分位寿命渐进方差估计作为目标函数,建立小样本条件下双应力步降加速退化试验优化设计模型。通过仿真实例,验证该方法的有效性、可行性。

Optimization design of double-step-down-stress accelerated degradation test for small sample

Performance of the high reliability and long life products on the condition of the small sample are affected by several stresses and it is hard to get the performance degraded information in limited test time in accelerated degradation test. This paper presented a method of optimal designs for the double-step-down-stress accelerating degradation test on condition of small sample. Simulating procedure of the test with Monte-Carlo and on the condition of the sample size was specified. Numbers of stress and inspection frequency were considered as variables. Asymptotic variance estimation of 100pth percentile of the lifetime distribution of the product at use condition was considered as goal function under the constraint of the total experiments cost. Finally, optimal designed model of the double-step-down-stress accelerated degradation test on condition of the small sample was established. Simulation results verify feasibility and the validity of this method.