基于拟蒙特卡洛方法的动态测量不确定度评定  

Dynamic measurement uncertainty evaluation based on Quasi-Monte-Carlo method

作　　者：汉泽西[1] 邢靖虹[1] 

机构地区：[1]西安石油大学电子工程学院,陕西西安710065

出　　处：《电子测试》2011年第5期14-18,共5页Electronic Test

摘　　要：针对蒙特卡洛方法收敛速度较慢以及仿真结果不稳定的问题,本文从动态测量系统的特性出发,通过引进低偏差点集,产生空间分布较为均匀的拟随机数序列,代替蒙特卡洛方法中的伪随机数序列,提出一种基于拟蒙特卡洛方法的动态测量不确定度评定方法。实验结果表明,该方法与传统基于蒙特卡洛方法的动态测量不确定度评定方法相比,不但大幅度减少了抽样点数目,而且具有确定性误差,评定结果具有计算精度高、稳定性好、效率较高的优点。Owing to the disadvantages which lie in Monte-Carlo method exist in terms of low convergence and unstable result,as well as the characteristics of dynamic system,through replying pseudo random numbers which lies in Monte-Carlo method by various low-discrepancy sets that generate highly uniform quasi random sequence,dynamic measurement uncertainty evaluation based on quasi-Monte-Carlo method is proposed.Following comparing this method with conventional dynamic measurement uncertainty evaluation based on Monte-Carlo method,the result shows that the quasi-Monte-Carlo method can not only reduce obviously the number of samples,but also give certain errors.The result of evaluation has high precision,good stability and high efficiency.

关 键 词：动态测量 拟蒙特卡洛方法 蒙特卡洛方法 测量不确定度 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]