基于Bootstrap-Bayes的加工中心主轴可靠性建模  

Reliability modeling of machining center spindle based on Boosttrap-Bayes

作　　者：陈传海[1] 杨兆军[1] 陈菲[1] 郝庆波[1,2] 许彬彬[1] 阚英男 

机构地区：[1]吉林大学机械科学与工程学院,长春130022 [2]空军航空大学力学系,长春130022

出　　处：《吉林大学学报（工学版）》2014年第1期95-100,共6页Journal of Jilin University:Engineering and Technology Edition

基　　金：'高档数控机床与基础制造装备'国家科技重大专项项目(2010ZX04014-016)

摘　　要：针对采用常规Bayes方法对小样本加工中心主轴之类产品进行可靠性建模时与工程实际有较大差异的问题,提出了一种基于Bootstrap-Bayes的小样本可靠性建模方法:为减小先验分布的误差,应用Bootstrap抽样方法对研究对象相同制造环境下同类产品的可靠性模型进行再抽样,从而获得参数的先验分布;在计算后验分布过程中,利用马尔可夫链蒙特卡罗抽样方法,简化了计算,得到了研究对象的可靠性模型。以大样本下经典建模方法所得可靠性模型为基准,与利用Bootstrap-Bayes方法建立的可靠性模型和常规Bayes方法建立的可靠性模型进行比较,结果表明,基于Bootstrap-Bayes的可靠性建模方法所建模型的误差明显小于常规Bayes方法。The reliability model established using traditional statistical method for the spindle in machining center with small sample size may be biased in the real case. Therefore, a modified reliability modeling method for small sample size was proposed using Bootstrap-Bayes approach. First, the reliability function of time between failures using empirical modeling method was established. Then the accurate of the parameters prior distribution of Bayes method was provided. This method improves the precision of prior distribution built by traditional empirical method. In order to calculate the posterior distribution of parameters, Monte Carlo simulation was developed. Finally, a real-world example of the spindle of one kind of machining center was presented using the proposed approach to show its potential application. The results show that the proposed method can provide an accurate reliability model for small sample failure data.

关 键 词：机床 数控机床 Bootstrap抽样 BAYES 可靠性 小样本 

分 类 号：TG659[金属学及工艺—金属切削加工及机床]