蒙特卡洛法验证不确定度A类评定方法  

Verification of Type A Evaluation Methods of Uncertainty Based on Monte Carlo Method

作　　者：严玲玲 程银宝[2] 陈晓怀[2] 李红莉[2] 范超 

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230009 [2]合肥工业大学仪器科学与光电工程学院,安徽合肥230009

出　　处：《河南科技大学学报（自然科学版）》2018年第5期17-20,共4页Journal of Henan University of Science And Technology:Natural Science

基　　金：国家重点研发计划基金项目(2016YFF0203801);国家自然科学基金项目(51275148)

摘　　要：针对客观概率的不确定度评定方法可靠性问题,利用蒙特卡洛法适合于计算机模拟的技术优势,验证3种不确定度A类评定方法的准确性。仿真实验结果表明:计算过程更为简单的极差法优于贝塞尔公式法,更具应用优势。由于评价的数据范围更广,合并样本标准差法比极差法和贝塞尔公式法更为可靠合理,但测量成本也更高。To solve the reliability problem of uncertainty evaluation method based on objective probability,by using the advantages of Monte Carlo method(MCM) suitable for computer simulation,the accuracy of three kinds of type A evaluation methods of uncertainty was verified.The simulation experimental results show that the range method with simple calculation process is better than the Bessel formula method and has more application advantages.Due to the wider range of evaluation data,the combined sample standard deviation method is more reliable and reasonable than the range method and the Bessel formula method,but the corresponding cost is higher.

关 键 词：计量学 蒙特卡洛法 不确定度评定方法 仿真验证 

分 类 号：TB92[一般工业技术—计量学]