Abstract
A radial basis function (RBF) neural network model based predictive control scheme is developed for multivariable nonlinear systems in this paper. A fast convergence algorithm is proposed and employed in multidimensional optimisation in the control scheme to reduce the computing time and save required computer memory. The scheme is applied to a simulated two-input two-output nonlinear process for set-point tracking control. Simulation results demonstrate the effectiveness of the control strategy and the fast learning algorithm for multivariable non-linear processes. Comparison of the performance with PID control is included.
Similar content being viewed by others
References
Hunt KJ, Sbarbaro R, Zbikowski R and Gawthrop PJ (1992) Neural networks for control systems—a survey. Automatica 16:575–587
Gomm JB, Evans JT and Williams D (1997) Development and performance of a neural network predictive controller. Contr Engin Prac 5(1):49–59
Battiti R (1992) First and second order methods for learning: between steepest descent and Newton’s method. Neur Comput 4:141–166
Yu XU, Chen GA and Cheng SX (1995) Dynamic learning rate optimisation of the back-propagation algorithm. IEEE Trans Neur Netwks 6(3):669–677
Leonard JA, Kramer MA (1991) Radial basis functions for classifying process faults. IEEE Contr Sys Mag 11(3):31–38
Yu DL, Gomm JB and Williams D (1997) A recursive orthogonal least squares algorithm for training RBF networks. Neur Process Lett 5:167–176
Yu DL, Gomm JB and Williams D (1999) On-line predictive control of a chemical process using neural network models. In: Proceedings of the IFAC 14th World Congress, Beijing, China, 5–9 July 1999
Senborg DE, Edgar TF and Mellichamp DA (1989) Process dynamics and control. Wiley, New York
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yu, D.W., Yu, D.L. Neural network control of multivariable processes with a fast optimisation algorithm. Neural Comput & Applic 12, 185–189 (2003). https://doi.org/10.1007/s00521-003-0381-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-003-0381-0