Abstract
A new method of designing direct controllers of the PID type for nonlinear plants by using RBF neural networks is proposed, and its satisfactory performance is demonstrated through simulations. This method does not put too much restriction on the type of plant to be controlled, and it has a stable performance for the type of inputs for which it has been trained. Unlike backpropagation or other supervised methods of training, this approach does not require knowledge of the appropriate form of controller output for each given input, and neither does it require identification of the plant or its inverse model. The PID controller design methodology presented here has certain advantages over conventional methodologies.
Similar content being viewed by others
References
Miller III WT, Sutton RS, Werbos PJ (Eds.). Neural Networks for Control. Cambridge, MA: MIT Press, 1990
Warwick K, Irwin GW, Hunt KJ (Eds.). Neural Networks for Control and Systems. London: Peter Peregrinus, 1992
White D, Sofge D. (Eds.) Handbook of Intelligent Control: Neural, Fuzzy and Adaptive Approaches. Amsterdam: Van Nostrand, 1992
Psaltis D, Sideris A, Yamamura A. Neural controllers. IEEE Int. Conf. on Neural Networks 1987; IV 551–558
Saerens M, Soquet A. A neural controller. 1st IEE Conf. on Artif. Neural Networks 1989; 211–215
Åström KJ, Witternmark B. Adaptive Control. Reading, MA: Addison-Wesley, 1989
Ziegler JG, Nichols NB. Optimum settings for automatic controllers. Trans. ASME 1942; 64: 759–768
Swiniarski RW. Novel neural network based self-tuning PID controller which uses pattern recognition technique. Proc. Am. Control Conf., San Diego, CA, 1990; 3023-3024
Scott GM, Shavlik JW, Ray WH. Refining PID controllers using neural networks. In J Moody, S Hanson, R Lippmann (Eds.), Advances in Neural Information Processing Systems 4. San Diego, CA: Morgan Kaufmann, 1992
Widrow B. Adaptive inverse control. Adaptive Systems in Control and Signal Processing: Proc. IFAC Workshop, Lund, Sweden, 1986
Jordan ML, Jacobs RA. Learning to control an unstable system with forward modelling. In D Touretzky (Ed.), Advances in Neural Information Processing Systems 2. San Diego, CA: Morgan Kaufmann, 1990; 324–331
Moody J, Darken CJ. Fast learning in networks of locally-tuned processing units. Neural Computation 1989; 1: 281–294
Narendra KS, Parthasarathy K. Identification and control of dynamical systems using neural networks. IEEE Trans. Neural Networks 1990; 1: 4–27
Atkenson CG. Memory based approaches to approximating continuous functions. Proc. 6th Yale Workshop on Adaptive and Learning Systems, New Haven, CT 1990; 202–217
Sontag ED. Mathematical Control Theory. New York, NY: Springer-Verlag, 1990
Park J, Sandberg W. Universal approximation using radial basis function networks. Neural Computation 1991; 3: 246–257.
Narendra KS, Levin AU. Regulation of nonlinear dynamical systems using multiple neural networks. Proc. Am. Control Conf., Boston MA, 1991; 1609–1614.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bahrami, M., Tait, K.E. A neural network-based proportional integral derivative controller. Neural Comput & Applic 2, 134–141 (1994). https://doi.org/10.1007/BF01415009
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01415009