Neural network based adaptive control via temporal pattern recognition

This paper presents a neural network approach to adaptive control through pattern recognition techniques. Two interconnected backpropagation networks are trained to translate error patterns resulting from sustained set point changes into predictions of mismatch between current internal model parameters, model gain and model time constant, and those which restore desired performance. The network predictions are then used to update a model based PI controller. The strategy is demonstrated on two simulations and a pilot scale process which are undergoing severe changes in model gain and time constant. The strategy compares favorably against a more traditional rule based pattern recognition approach. On presente dans cet article une approche par reseau neuronal du controle adaptatif au moyen de techniques de reconnaissance des modeles. Deux eeseaux de retropropagation interconnectes sont entrainees a traduire les types d'erreurs resultant de changements constants des points de consigne en prediction de discordance entre les parametres de modele internes courants, le gain de modele et la constante de temps de modele, et ceux qui retablissent la performance desiree. On utilise ensuite les predictions du reseau pour mettre a jour un controleur PI base sur les modeles. Cette strategie est demontree a partir de deux simulations et d'un systeme a l'echelle pilote qui subissent des changements severes dans le gain et la constante de temps de modele. Cette strategie se compare favorablement a une approche de reconnaissance des modeles a partir des regles traditionnelles.

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

[2]  N.V. Bhat,et al.  Modeling chemical process systems via neural computation , 1990, IEEE Control Systems Magazine.

[3]  Bradley R. Holt,et al.  A Neural Network Structure for System Identification , 1990, 1990 American Control Conference.

[4]  F.-C. Chen,et al.  Back-propagation neural networks for nonlinear self-tuning adaptive control , 1990, IEEE Control Systems Magazine.

[5]  Douglas J. Cooper,et al.  Comparing two neural networks for pattern based adaptive process control , 1992 .

[6]  Mostafa Kaveh,et al.  Conjugate gradient learning algorithms for multilayer perceptrons , 1989, Proceedings of the 32nd Midwest Symposium on Circuits and Systems,.

[7]  Ming-Shong Lan,et al.  Adaptive Control of Unknown Dynamical Systems via Neural Network Approach , 1989, 1989 American Control Conference.

[8]  Levin,et al.  Neural network architecture for adaptive system modeling and control , 1989 .

[9]  Edgar H. Bristol,et al.  Pattern recognition: An alternative to parameter identification in adaptive control , 1977, Autom..

[10]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[11]  Maureen Caudill,et al.  Neural networks primer, part III , 1988 .

[12]  A. Guez,et al.  Neural network architecture for control , 1988, IEEE Control Systems Magazine.

[13]  W. T. Miller,et al.  CMAC: an associative neural network alternative to backpropagation , 1990, Proc. IEEE.

[14]  Lyle H. Ungar,et al.  Adaptive networks for fault diagnosis and process control , 1990 .

[15]  M. Morari,et al.  Internal model control: PID controller design , 1986 .

[16]  Douglas J. Cooper,et al.  Adaptive process control using pattern-based performance feedback , 1991 .

[17]  Karl Johan Åström,et al.  Auto-Tuning, Adaptation and Expert Control , 1985 .

[18]  David M. Himmelblau,et al.  FAULT DIAGNOSIS IN COMPLEX CHEMICAL PLANTS USING ARTIFICIAL NEURAL NETWORKS , 1991 .

[19]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .