基于贝叶斯信息融合的测量不确定度评定与实时更新

姜瑞; 陈晓怀; 王汉斌; 肖颖; 徐磊; 程银宝; 程真英

doi:10.3969/j.issn.1000-1158.2017.01.26

PDF(1761 KB)

计量学报 ›› 2017, Vol. 38 ›› Issue (1) : 123-126. DOI: 10.3969/j.issn.1000-1158.2017.01.26

计量学总论、不确定度

基于贝叶斯信息融合的测量不确定度评定与实时更新

姜瑞,陈晓怀,王汉斌,肖颖,徐磊,程银宝,程真英

作者信息 +

Evaluation and Real Time Updating of Measurement Uncertainty Based on Bayesian Information Fusion

JIANG Rui,CHEN Xiao-huai,WANG Han-bin,XIAO Ying,XU Lei,CHENG Yin-bao,CHENG Zhen-ying

Author information +

文章历史 +

摘要

基于贝叶斯信息融合与统计推断原理,建立不确定度动态评定模型,对测量不确定度进行实时更新。引入最大熵原理和爬山搜索优化算法,确定先验分布概率密度函数及样本信息似然函数,结合贝叶斯公式求出后验分布概率密度函数,实现不确定度的优化估计。仿真及实例分析表明,基于贝叶斯和最大熵方法评定及更新的测量不确定度更加接近理论值。

Abstract

Based on the principle of Bayesian information fusion and statistical inference, the dynamic evaluation model of uncertainty was established and the uncertainty of measurement results was updated in real time. The maximum entropy principle and hill-climbing algorithm were introduced to determine the prior distribution probability density function and the likelihood function of the sample information. The distribution of posterior distribution of PDF was calculated by combining the Bayes formula. And the optimal estimation of uncertainty was achieved. The case and simulation showed that the measurement uncertainty obtained by Bias and maximum entropy method was more accord with the standard requirement.

导出引用

姜瑞,陈晓怀,王汉斌,肖颖,徐磊,程银宝,程真英. 基于贝叶斯信息融合的测量不确定度评定与实时更新[J]. 计量学报. 2017, 38(1): 123-126 https://doi.org/10.3969/j.issn.1000-1158.2017.01.26

JIANG Rui,CHEN Xiao-huai,WANG Han-bin,XIAO Ying,XU Lei,CHENG Yin-bao,CHENG Zhen-ying. Evaluation and Real Time Updating of Measurement Uncertainty Based on Bayesian Information Fusion[J]. Acta Metrologica Sinica. 2017, 38(1): 123-126 https://doi.org/10.3969/j.issn.1000-1158.2017.01.26

中图分类号： TB9

参考文献

［1］余学锋.不确定度的Bayes表征与分析［J］. 计量学报,2000,21（4）:314-318.
［2］张海滨,王中宇,刘智敏.测量不确定度评定的验证研究［J］. 计量学报,2007,28（3）:193-197.
［3］Zanobini A, Ciani L, Pellegrini G. Quantifying the Measurement Uncertainty Using Bayesian Inference［DB］.DOI: 10.1109/AMUEM.2007.4362560 Conference: Advanced Methods for Uncertainty Estimation in Measurement, 2007 IEEE International Workshop on Source: IEEE Xplore.
［4］Battistelli L, Chiodo E, Lauria D. A new methodology for uncertainty evaluation in risk assessment. Bayesian estimation of a safety index based upon extreme values［C］ //International Symposium on Power Electronics, Electrical Drives, Automation & Motion. IEEE, 2008: 439 - 444.
［5］宋明顺,王伟.贝叶斯定理在合并样本方差估计中的应用［J］.计量学报, 2008, 29(2):186-189.
［6］Iuculano G, Nielsen L, Zanobini A, et al. The Principle of Maximum Entropy Applied in the Evaluation of the Measurement Uncertainty［J］. IEEE Transactions on Instrumentation & Measurement, 2007, 56(3):717-722.
［7］Izbenko Y, Kovtun V, Kuznetsov A. The Design of Boolean Functions by Modified Hill Climbing Method［C］// Information Technology: New Generations, 2009. ITNG '09. Sixth International Conference on IEEE, 2009: 356-361.