Combination Method of Kernel Principal Component Analysis and Independent Component Analysis for Process Monitoring

Abstract

A combination method of kernel principal component analysis (KPCA) and independent component analysis (ICA) for process monitoring is proposed. The new method is a two-phase algorithm: whitened KPCA plus ICA. KPCA spheres data and makes the data structure become as linearly separable as possible by virtue of an implicit nonlinear mapping determined by kernel. ICA seeks the projection directions in the KPCA whitened space, making the distribution of the projected data as non-gaussian as possible. The application to the Tennessee Eastman (TE) simulated process indicates that the proposed process monitoring method can effectively capture the nonlinear relationship in process variables. Its performance significantly outperforms monitoring method based on ICA or KPCA.