NEURAL NETWORKS (METHODOLOGIES FOR PROCESS MODELLING AND CONTROL)

There are strong relationships between Artificial Neural Network and Radial Basis Function approaches to system modelling and representation. Indeed, the RBF representation can be implemented in the form of a two-layered network. This paper reviews the contributions that these two approaches can make to the process modelling and control. The development of dynamic system representations is then examined in order to provide a basis for predictive control. Two alternative network modelling philosophies are considered: a time series approach and a network structure with embedded dynamics. Potential applications of the methods discussed are highlighted through studies of typical industrial process control problems.

[1]  A. Sideris,et al.  A multilayered neural network controller , 1988, IEEE Control Systems Magazine.

[2]  H. Akaike.  A new look at the statistical model identification , 1974 .

[3]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[4]  Stephen A. Billings,et al.  Non-linear system identification using neural networks , 1990 .

[5]  A. J. Morris,et al.  Multivariable and multirate self-tuning control: a distillation column case study , 1991 .

[6]  M. J. D. Powell,et al.  An efficient method for finding the minimum of a function of several variables without calculating derivatives , 1964, Comput. J..

[7]  A. J. Morris,et al.  Bioprocess model building using artificial neural networks , 1991 .

[8]  Daniel Sbarbaro,et al.  Neural Networks for Nonlinear Internal Model Control , 1991 .

[9]  A. J. Morris,et al.  Artificial neural networks in process engineering , 1991 .

[10]  Mark A. Kramer,et al.  Improvement of the backpropagation algorithm for training neural networks , 1990 .

[11]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[12]  A. Morris,et al.  Multilayer feedforward neural networks : a canonical form approximation of nonlinearity , 1992 .

[13]  I. J. Leontaritis,et al.  Model selection and validation methods for non-linear systems , 1987 .

[14]  Gary Montague,et al.  Soft-sensors for process estimation and inferential control , 1991 .