Design of Fault Diagnosis System of FPSO Production Process Based on MSPCA

Based on the theory of wavelet analysis and principal component analysis, multiscale PCA is introduced which combines the ability of PCA to decorrelate the variables by extracting a linear relationship, with that of wavelet analysis to extract deterministic features and approximately decorrelate autocorrelated measurements to improve the performance of PCA whose modeling is limited to a single scale. It is applied to the fault monitor and diagnose of floating production storage and off loading system. The result show: the fault diagnose method based on multiscale principal components analysis can realized FPSO earlier period fault monitor and diagnose accurately, and the capability of multiscale principal components analysis fault diagnosis is better than the principal components analysis for the small disturbance.