PCA-Based Process Diagnosis in the Presence of Control

Abstract In PCA-based fault diagnosis, additive faults have directional signatures in the residual space. Ideally, these are determined by the eigenvectors spanning this space. If the PCA model is obtained in the presence of linear control constraints, this relationship may be spoiled. However, by simply varying the control gains or setpoints, the open-loop fault isolation properties are retained.

[1]  Seongkyu Yoon,et al.  Statistical and causal model‐based approaches to fault detection and isolation , 2000 .

[2]  A. Negiz,et al.  Statistical monitoring of multivariable dynamic processes with state-space models , 1997 .

[3]  Weihua Li,et al.  Isolation enhanced principal component analysis , 1999 .

[4]  Seongkyu Yoon,et al.  Fault diagnosis with multivariate statistical models part I: using steady state fault signatures , 2001 .

[5]  Alan S. Willsky,et al.  A survey of design methods for failure detection in dynamic systems , 1976, Autom..

[6]  Janos Gertler,et al.  A new structural framework for parity equation-based failure detection and isolation , 1990, Autom..

[7]  Theodora Kourti,et al.  Statistical Process Control of Multivariate Processes , 1994 .

[8]  K. A. Kosanovich,et al.  Monitoring Process Performance in Real-Time , 1992, 1992 American Control Conference.

[9]  Janos Gertler,et al.  Principal Component Analysis and Parity Relations - A Strong Duality , 1997 .

[10]  A. Willsky,et al.  Analytical redundancy and the design of robust failure detection systems , 1984 .

[11]  Paul M. Frank,et al.  Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy: A survey and some new results , 1990, Autom..

[12]  S. Joe Qin,et al.  Joint diagnosis of process and sensor faults using principal component analysis , 1998 .

[13]  Harold Lee Jones,et al.  Failure detection in linear systems , 1973 .

[14]  Theodora Kourti,et al.  Multivariate SPC Methods for Process and Product Monitoring , 1996 .