基于实验数据的精确数学回归模型设计  

Model Design of Accurate Mathematical Regression Based on Experimental Data

作　　者：吴年祥[1] 陈小林[1] 卢万银[1] 

机构地区：[1]安徽国防科技职业学院,安徽六安237001

出　　处：《临沂大学学报》2014年第6期41-44,共4页Journal of Linyi University

基　　金：安徽省省级质量工程特色专业(20101685);电工电子省级示范实验实训中心(20101687)

摘　　要：在生产和科学实验中,因素与指标的关系,即数学模型是很难精确确定的.对因素进行水平划分后,通过实验来寻求其数学模型,选取的数学模型主要是线性回归方程形式,其实验次数确定数学模型中待定系数的个数.因素越多、实验次数越多时,这种方法会造成分析模型与实际模型间的误差较大,甚至造成实际生产应用中不可估量的损失.本文通过对回归分析模型进行修正加项的方式,求取精确数学模型,并给出了其应用.In the production and scientific experiments, the relationship between the factors and indicators, i.e., it is difficult to accurately determine the mathematical model. For factors level division, through the experiments to seek its mathematical model, the mathematical model is the main form of linear regression equation, the experiment to determine the number of undetermined coefficients of mathematical model. The more factors and experiment, this method cause the larger error between analysis model and practical model, and even results in actual production application immeasurable loss. In this paper, the regression analysis model of increasing number of factors, the revised to calculate the precise mathematical model, and gives its application.

关 键 词：数学模型 回归分析法 因素 指标 数据处理 

分 类 号：O242[理学—计算数学]