NONLINEAR MULTISCALE FAULT DETECTION AND IDENTIFICATION

A nonlinear multiscale multivariate statistical process control method is proposed to address fault detection and diagnosis issues at different scales in nonlinear processes. A kernel principal component analysis (KPCA) model is built with the reconstructed data obtained by performing wavelet transform and inverse wavelet transform sequentially on measured data. New variable contributions to monitoring statistics are also derived. A CSTR simulation study compares the proposed approach with several existing methods in terms of false alarm rate, missed alarm rate and detection delay.