Neural Networks (Methodologies for Process Modelling and Control)

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

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

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

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

[5]  A. J. Morris,et al.  Predictive Control of Distillation Columns Using Dynamic Neural Networks , 1992 .

[6]  A. J. Morris,et al.  Artificial neural network based multivariable predictive control , 1991 .

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

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

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

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

[11]  M.T. Tham,et al.  Multivariable Constrained Predictive Control (With Application to High Performance Distillation) , 1991, 1991 American Control Conference.

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

[13]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

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

[15]  M.J. Willis,et al.  A Comparison of Adaptive Estimation with Neural based Techniques for Bioprocess Application , 1990, 1990 American Control Conference.

[16]  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..

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

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

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

[20]  M. J. D. Powell,et al.  Radial basis functions for multivariable interpolation: a review , 1987 .