基于改进Bayesian Bootstrap陀螺仪寿命预测研究.pdf

收稿日期:20130712 作者简介:董金龙(1988),男,陕西西安人,硕士生,主要从事惯性仪表寿命与可靠性分析的研究。 文章编号:10042474(2014)03038405基于改进 Bayesian Bootstrap 陀螺仪寿命预测研究董金龙,汪立新,盛立昊,吴双磊(第二炮兵工程大学 304 教研室,陕西西安 710025) 摘要:陀螺仪是惯性导航系统的核心部件之一,其剩余寿命预测是惯导系统作战使用、战备测试和维修决策的重要依据。首先采用漂移布朗运动对陀螺仪进行退化建模,针对陀螺仪性能参数样本容量小的实际情况,将Bayesian Bootstrap 方法引入到退化模型参数估计中。该方法是一种通过数字仿真技术扩大样本容量的方法,它完全依赖于样品本身的数据,不需要任何主观假设。面对特小样本 Bayesian Bootstrap 方法估计结果可信度下降的情况,提出了一种改进的 Bayesian Bootstrap 方法,在保证期望与方差点估计不变的情况下,缩短了其置信区间,有效地提高了预测精度,最后通过陀螺仪的寿命预测实例验证了该方法的有效性和实用性。关键词:Bayesian Bootstrap;陀螺仪;漂移布朗运动;寿命预测;小样本中图分类号: 文献标识码:AStudy on Gyroscope Life Prediction Based On Improved Bayesian BootstrapDONG Jinlong,WANG Lixin,SHENG Lihao,WU Shuanglei(304 Teaching and Research Section,The Second Artillery Engineering University,Xi’an 710025,China) Abstract:The gyroscope was one of the ponents of the inertial navigation system (INS),whose residual lifetime distribution prediction of INS was of great importance in operational bat readiness test and maintenance decision ,the gyroscope was modeled in its degradation process with the drift Brownian view of the small sample of the gyroscope performance parameters,the Bayesian Bootstrap method was introduced into the degradation model of parameter method extended the amount of samples by numerical the credibility of Bayesian Bootstrap method estimation fell for the partic