基于支持向量机的软测量模型及应用  

A model and application of soft-sensor based on support vector machine

作　　者：陶秀凤[1] 唐诗忠[1] 周鸣争[2] 

机构地区：[1]安徽工程科技学院电气工程系,安徽芜湖241000 [2]安徽工程科技学院计算机科学与工程系,安徽芜湖241000

出　　处：《安徽工程科技学院学报（自然科学版）》2004年第2期48-52,共5页Journal of Anhui University of Technology and Science

基　　金：安徽省教育厅自然科学基金资助项目(2004kj033zd)

摘　　要：支持向量机(SupportVectormachine,简称SVM)是一种基于结构风险最小化原理,具有很高泛化性能的学习算法.针对软测量过程中,被测系数与相关参数之间存在有较大的非线性和模糊关系,提出了一种基于支持向量机的软测量模型及算法.为小样本、非线性、高维数一类软测量问题的建模提供了一种有效的途径.通过对"纸张水分在线测量系统"应用表明,基于SVM的软测量模型及算法在测量精度和推广性能上都具有一定的优越性.The support vector machine(SVM) is an algorithm based on structure risk minimizing principle and having high generalization ability. In the course of soft-sensor, sensor has bigger nonlinearity and fuzzy relation between coefficient and relevant parameter. We put forward a kind of soft-sensor models and algorithms based on the Support Vector machine. The soft-sensor model offers a kind of effective way for small sample space, non-linearity, high dimensions. The application to 'paper moisture content online measuring system' shows that the model and algorithm of soft-sensor based on SVM all have certain superiority in measuring precision and performance of popularizing.

关 键 词：支持向量机 软测量模型 学习算法 回归 水分测量 SVM 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置] TP18[自动化与计算机技术—控制科学与工程]