Reconstruction-based Contribution for Process Monitoring with Kernel Principal Component Analysis

This paper presents a new method for fault diagnosis based on kernel principal component analysis (KPCA). The proposed method uses reconstruction-based contributions (RBC) to diagnose simple and complex faults in nonlinear principal component models based on KPCA. Similar to linear PCA, a combined index, based on the weighted combination of the Hotelling's T(2) and SPE indices, is proposed. Control limits for these fault detection indices are proposed using second order moment approximation. The proposed fault detection and diagnosis scheme is tested with a simulated CSTR process where simple and complex faults are introduced. The simulation results show that the proposed fault detection and diagnosis methods are efective for KPCA.