基于Bayes小子样理论的导弹贮存可靠性评估方法研究

Research on Reliability Evaluation Method of Missile Storage Base on Bayes Small Sample Theory

针对导弹造昂贵价、样本少、贮存可靠性验证难度大的特点,本文探讨了基于小样本的Bayes统计分析模型,这种模型以故障率的共轭验前分布Gamma分布为先验分布,充分利用了历史试验数据的同时,结合导弹现场试验数据,给出了导弹故障率的后验分布,并推算出可靠性Bayes点估计和置信限。最后以某型导弹为例,利用其试验数据验证了此方法的有效性。

Aimed at the characteristics of the missile＇s high cost, low sample and the difficulty of storage reliability verification, Bayes statistical analysis model based on small sample is discussed in this paper. This model is conjugated failure rate of prior distribution for the prior distribution Gamma distribution. By full use of the historical test data, combined with missile field test data, gives the posterior distribution of the failure rate of missile, and calculates the reliability Bayes point estimate and confidence limits. Finally, the validity of this approach is verified by an example of a type of missile using its test data.