集成因子分析与卡尔曼滤波的计算光度分析方法  

A Novel Algorithm of Computational Spectral Analysis Integrating Factor Analysis with Kalman Filter

作　　者：陈闽军[1] 庄明珠[2] 赖奕坚[2] 刘玉敏[2] 贾伟[1] 

机构地区：[1]上海交通大学药学院,上海200030 [2]上海交通大学分析测试中心,上海200030

出　　处：《分析化学》2005年第8期1143-1146,共4页Chinese Journal of Analytical Chemistry

基　　金：上海交通大学校内青年教师启动基金资助项目(No.A2816A)

摘　　要：通过将因子分析与卡尔曼滤波法集成,提出一种多元光度分析新算法。该法运用因子分析法提取多组分化学体系量测数据矩阵中的因子构建卡尔曼滤波校正模型,以克服卡尔曼滤波法依赖于纯物质光谱建模的内在局限性。数值仿真及分析实验结果均表明,该法能获得准确可靠的计算分析结果,是一种有效的计算光度分析新算法。By integrating factor analysis （FA） with Kalman filter （ KF）, a novel algorithm used for computational spectral analysis is proposed. In the algorithm, the factors extracted from the data set of the multicomponent system with factor analysis technique have been employed to construct the calibration model of KF. In this way, the inherent limitation of KF, in which calibration modeling highly relies on the pure spectra of all the components in the multicomponent system, has been overcome. Computer simulatin indicates that the results obtained by the proposed algorithm are accurate. A typical example of three-lomponent drug including aminopyrine, caffein and phenacetin has been used to verify the effectiveness of algorithms. Compared with what obtained by KF, the total mean relative error obtained by the proposed algorithm decreases from 2.78% to 1.78%.

关 键 词：因子分析法 卡尔曼滤波 多元光度分析 化学计量学 

分 类 号：O657.3[理学—分析化学]