Abstract:Because the dynamic characteristics of autocorrelation and lag correlation in production process are neglected in fault diagnosis

Kernel Independent Component AnalysisPrincipal Component Analysis (KICAPCA) is very poor in detecting small and gradual faults because of lacking available variable contribution analysis.In this paper

a dynamic kernel independent component analysis (KICAPCA) fault diagnosis method based on wavelet packet filtering is proposed.This method integrates wavelet packet filtering theory and AR model prediction data characteristics into KICAPCA to extract the feature information of process variable autocorrelation and lagrelated .In this paper

KICAPCA algorithm is used to extract the independent components and principal components of process variables to determine the control limits of three monitoring indicators T2

SPE

I2.Nonlinear contribution graph is used for fault diagnosis

and the advantage of FDKICAPCA method is verified by simulation results of Tennessee process.