【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.更多还原

【Abstract】 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.更多还原