Nonlinear process monitoring using dynamic kernel slow feature analysis and support vector data description

Abstract

For effective fault detection in nonlinear process, this paper proposed a novel nonlinear monitoring method based on dynamic kernel slow feature analysis and support vector data description (DKSFA-SVDD). SFA is a newly emerged data feature extraction technique which can find invariant features of temporally varying signals. For effective analysis on nonlinear dynamic process data, DKSFA is built which uses kernel trick to mine the nonlinear data feature and applies an augmented matrix to extract the dynamic information in measured data. In order to monitor the dynamic nonlinear data features from DKSFA, SVDD is applied to describe the distribution region of normal operation data and one monitoring index is constructed to indicate the occurrence of the abnormal event. Simulation using a continuous stirred tank reactor (CSTR) system shows that the proposed method has a good fault detection performance and outperforms the traditional KPCA method.