基于FA-SVR的丙酮精制产品质量软测量模型  

FA-SVR based Soft-Sensor Model of Product Quality in Acetone Refining

作　　者：段莹[1] 范全义[1] 熊智华[1] 

机构地区：[1]清华大学自动化系

出　　处：《微计算机信息》2007年第3期1-3,共3页Control & Automation

基　　金：国家自然科学基金(60404012)

摘　　要：针对某丙酮精制过程,提出采用FA与SVR相结合的方法建立丙酮产品质量的软测量模型。采用因子分析(FA)方法提取辅助变量的特征信息,并消除各变量之间的相关性,然后利用支持向量回归(SVR)建立丙酮产品质量指标的软测量模型。在实际生产过程数据上进行了仿真实验,并与传统的稳健回归分析及神经网络等方法进行了比较,结果表明本方法具有良好的预测效果。A soft-sensor model of product quality in acetone refining process is proposed by combining factor analysis (FA) and support vector regression (SVR). During the data processing, FA is applied to extract the characteristics of secondary variables and elimi-nate the collinearity among these variables.The extracted principal factors are then used as input parameters of soft sensor model,andthe model is built by using SVR to predict the acetone quality.The experiment results on the real industrial data show that themethod of FA- SVR is more effective than robust regression and neural network methods.

关 键 词：软测量 支持向量回归 因子分析 丙酮精制 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]