Intelligent “control” applications in the process industries

Abstract In this paper the author's experience in applying intelligent control in the process industries is discussed. A framework for intelligent control is presented in which intelligent control is defined in a broad sense to include items such as fault detection/isolation, modeling, and optimization. The focus of the paper is on techniques that have proven beneficial in the process industries. Methods utilizing multivariate statistical techniques are presented, with applications to soft sensing, batch process optimization, and fault detection/isolation. Potential problems with closing control loops around soft sensors are also discussed. The second broad technique considered involves model predictive control, and a wastewater application is discussed. Lastly, a brief discussion on expert systems and fuzzy control is presented, and finally a summary is given.

[1]  A. Höskuldsson.  PLS regression methods , 1988 .

[2]  Michael J. Piovoso,et al.  A multivariate statistical controller for on-line quality improvement , 1998 .

[3]  W. Gujer,et al.  Activated sludge model No. 3 , 1995 .

[4]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[5]  Thomas J. McAvoy,et al.  Nonlinear PLS Modeling Using Neural Networks , 1992 .

[6]  C. R. Cutler,et al.  Dynamic matrix control¿A computer control algorithm , 1979 .

[7]  T. McAvoy,et al.  Control of an alternating aerobic–anoxic activated sludge system — Part 2: optimization using a linearized model , 2000 .

[8]  Thomas E Marlin,et al.  Process Control , 1995 .

[9]  Thomas J. McAvoy,et al.  Control of an alternating aerobic–anoxic activated sludge system — Part 1: development of a linearization-based modeling approach , 2000 .

[10]  Gang Chen,et al.  Application of multivariate statistical analysis in batch processes , 2001 .

[11]  Nola D. Tracy,et al.  Multivariate Control Charts for Individual Observations , 1992 .

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

[13]  J. E. Jackson,et al.  Control Procedures for Residuals Associated With Principal Component Analysis , 1979 .

[14]  Mark A. Kramer,et al.  Modeling chemical processes using prior knowledge and neural networks , 1994 .

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

[16]  J. Macgregor,et al.  Monitoring batch processes using multiway principal component analysis , 1994 .

[17]  Venkat Venkatasubramanian,et al.  Intelligent systems for HAZOP analysis of complex process plants , 2000 .

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

[19]  T. McAvoy,et al.  Nonlinear principal component analysis—Based on principal curves and neural networks , 1996 .

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

[21]  Thomas J. McAvoy,et al.  A Data-Based Process Modeling Approach and its Applications , 1992 .

[22]  Barbara Hayes-Roth,et al.  Intelligent Control , 1994, Artif. Intell..

[23]  I. Jolliffe.  Principal Component Analysis , 2002 .

[24]  T. McAvoy,et al.  Use of Hybrid Models in Wastewater Systems , 2000 .

[25]  Thomas E. Marlin,et al.  Multivariate statistical monitoring of process operating performance , 1991 .

[26]  Dale E. Seborg,et al.  A Perspective on Advanced Strategies for Process Control (Revisited) , 1999 .