Abstract: Selection of secondary variables is an effective way to reduce redundant information and to improve efficiency in nonlinear system modeling. A novel method based on kernel principal components analysis (KPCA) and false nearest neighbor method (FNN) is proposed on select the most suitable secondary process variables used as nonlinear modeling inputs. In the proposed approach, the KPCA can be employed to overcome difficulties encountered with the existing multicollinearity between the factors. In the new KPCA feature subspace, it is inspired by FNN that interpretation of primary variable would be estimated by calculating the variables’ map distance in the KPCA space to select secondary variables. Nonlinear model form the production processing of hydrogen cyanide is used to verify the validity of the method, and compared with the fully parametric model. The results show that the method is effective and suitable for variable selection. Therefore, a new method is provided for the variable selection of nonlinear system modeling.

Key words: False nearest neighbor(FNN), Kernel principal components analysis (KPCA), Modeling, Nonlinear systems, Variable selection