Engineering Commons^™

Kpca-Rvm Modeling Method And Its Application For Soft Sensor, Xuefeng Yan, Jia Chen, Chunping Hu, Feng Qian

Chunping Hu

A novel modeling method integrated KPCA with RVM is proposed. Firstly, kernel primary component analysis (KPCA) is employed to identify the principal components from the nonlinear transform data of independent variables, which are regarded as character variables. Then, regression between character variables and dependent variables is done based on RVM, and the optimal number of the character variables is adaptively determined according to the generalization performance of the regression model. Thus, KPCA-RVM method can eliminate the disturbance of redundant information and achieve the best nonlinear model with good generalization performance. Finally, the method of KPCA-RVM is demonstrated by a 4-CBA's …