摘要
提出了基于核函数主元分析(PCA)方法提取变量的特征信息以有效处理非线性数据,并在此基础上进行软测量建模的方法。利用该方法建立了工业萘初馏塔酚油含萘量软测量模型,工业应用结果表明了该方法的有效性和优越性。
A novel method is proposed in developing soft sensor based on the nonlinear principal components obtained from kernel principal component analysis (PCA) technique to deal with the nonlinear characteristics of data. Field application shows that the proposed method is effective and superior to traditional methods.
出处
《华东理工大学学报（自然科学版）》
CAS
CSCD
北大核心
2004年第5期567-570,共4页
Journal of East China University of Science and Technology
关键词
核函数
主元分析
软测量
建模
kernel function
principal component analysis
soft sensor
modeling
