批次效应对二元退化系统可靠性的影响

Batch effects on the reliability of binary degradation systems

利用随机过程建立退化系统模型时,考虑个体退化过程和相关性差异,即模型中加入退化特征多元化,并存在批次效应。退化模型中随机参数采用非共轭先验分布假设,分析随机参数对系统可靠度的影响,在此基础上,采用贝叶斯马尔可夫链蒙特卡罗方法对未知参数进行估计。由于似然方程包含未知参数多,采用智能优化算法,再通过计算此类系统实例进行可靠性分析验证考虑退化相关性和个体退化过程批次效应的必要性。

Individual degradation processes and correlation differences are considered when modelling degraded systems using stochastic processes,i.e.the model incorporates diversification of degradation characteristics and presence of batch effects.The random parameters in the degradation model are analyzed using the assumption of non-conjugate prior distribution,and the influence of the random parameters on the reliability of the system is analyzed,based on which the unknown parameters are estimated using a Bayesian Markov chain Monte Carlo method.As the likelihood equation contains many unknown parameters,an intelligent optimization algorithm is used,and then the need to consider degradation correlations and individual degradation process batch effects is verified by calculating such system examples for reliability analysis.