论文信息 - Research of the New Principal Component Analysis Algorithm Based on the Dynamic Model

Research of the New Principal Component Analysis Algorithm Based on the Dynamic Model

An extension algorithm, exponentially weighted dynamic principal component analysis (EWDPCA) algorithm is proposed to monitor the dynamic process, in particular for disturbances and set points changes in process. The technique is validated through simulation in the process of actual chemical polymerization. The results show that the EWDPCA algorithm can eliminate the linear relationship among variables and reflect the real-time information in dynamic process.

[1] T. R. Fortescue,et al. Implementation of self-tuning regulators with variable forgetting factors , 1981, Autom..

[2] A. J. Morris,et al. Application of exponentially weighted principal component analysis for the monitoring of a polymer film manufacturing process , 2003 .

[3] Bhupinder S. Dayal,et al. Recursive exponentially weighted PLS and its applications to adaptive control and prediction , 1997 .

[4] S. Wold. Exponentially weighted moving principal components analysis and projections to latent structures , 1994 .

[5] Christos Georgakis,et al. Disturbance detection and isolation by dynamic principal component analysis , 1995 .

[6] Weihua Li,et al. Recursive PCA for adaptive process monitoring , 1999 .

[7] S. Qin. Recursive PLS algorithms for adaptive data modeling , 1998 .