实验数据的拟合及其不确定度表示  

Experimental Data Fitting and Uncertainty Expression

作　　者：来雪梅[1] 王雪萍 张海燕[3] 

机构地区：[1]中北大学信息与通信工程学院,山西太原030051 [2]内蒙古第一机械制造(集团)有限公司,内蒙古包头014032 [3]中国北方车辆研究所,北京100072

出　　处：《中北大学学报（自然科学版）》2009年第5期481-484,共4页Journal of North University of China(Natural Science Edition)

基　　金：山西省自然科学基金资助项目(2009011023)

摘　　要：针对测试系统校准、比对过程中两个变量的实验数据,研究变量之间变化规律的拟合方法及其不确定度表示.利用最小二乘法和拉格朗日法对实验数据的曲线拟合及其不确定度表示方法进行了归纳与推导,考虑了两种情况:一种是不考虑自变量的不确定度,另一种是考虑自变量的不确定度.通过一组实验数据,给出了两种数据拟合方法及其不确定度的表达式,并且比较了这两种方法的结果,说明考虑自变量的不确定度比不考虑自变量的不确定度时实验数据拟合结果的不确定度较小.Aiming at the experimental data in the process of calibration and comparison of measurement system, based on the least square method and Lagrange method, data fitting methods between two variables and their uncertainty expressions are studied. Two cases are considered. One takes into consideration uncertainty of independent variable, and the another neglects uncertainty of independent variable in fitting process. Two kinds of fitting results were given and compared by using a set of real experimental data. It is concluded that the fitting uncertainty in the first case is less than that in the second case.

关 键 词：实验数据 拟合 最小二乘法 不确定度 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]