Nonlinear dynamic principal component analysis for on-line process monitoring and diagnosis

Abstract

A nonlinear dynamic principal component analysis (ND-PCA) approach is developed in this paper based on dynamic PCA and the sigmoid basis function feed forward neural network (SBFN). Through ND-PCA an integrated framework for on-line monitoring and root-cause diagnosis is developed. The approach is verified and illustrated on the Tennessee Eastman benchmark process as a case study while noises were added on sensor readings. Results show that the proposed ND-PCA approach performs good incipient diagnosis capability and overall diagnosis correctness rate.