基于样条函数的多气体传感器信号建模分析  

Signal of Multi-gas-sensor Modeling and Analyzing Based on Spline Function

作　　者：滕炯华[1] 袁朝辉[1] 王磊[2] 

机构地区：[1]西北工业大学自动控制系,陕西西安710072 [2]同济大学中德学院,上海200092

出　　处：《同济大学学报（自然科学版）》2002年第7期858-861,共4页Journal of Tongji University:Natural Science

基　　金：国家自然科学基金资助项目 ( 6 0 172 0 76 )

摘　　要：样条函数理论作为数学工具已广泛应用于逼近论、曲线数据拟合、数值分析等方面 .在研究一般多项式最小二乘法建模的基础上 ,针对所建模型易产生欠拟合和过拟合及模型阶数高的问题 ,提出了采用样条最小二乘数据拟合方法来建立数学模型 .基于样条最小二乘数据拟合方法建立的数学模型不仅可以提高模型精度和拟合程度 ,而且模型阶数较低 ,光滑性好 .将该建模方法用于多气体传感器输出信号的建模 ,结果表明 ,方法正确并有效 .The theory of spline function as a mathematical tool has been widely used in the approximation theory,the curve data fit,the numerical analysis and etc.Based on researching the least square method modeling of general polynomial this article presents a method to build a mathematical model with data fit method of spline least square in order to solve some problems of local owe fit,over fit and high degree model which often occur during modeling.The mathematical model built by the data fit method based spline least square has not only higher precision of model and fit coherence,but low degree of model,more smooth also.This method of modeling is used to build the model of the output signal from multi-gas-sensor.The result shows it is valid and proper.

关 键 词：多气体传感器 信号建模 样条函数 多项式最小二乘拟合 气体检测 样条最小二乘数据拟合方法 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置] N945.12[自动化与计算机技术—控制科学与工程]