Abstract
This paper deals with the problem of designing closed-loop feed-forward control strategies to drive the state of a dynamic system (in general, nonlinear) so as to track any desired trajectory joining the points of given compact sets, while minimizing a certain cost function (in general, nonquadratic). Due to the generality of the problem, conventional methods (e.g., dynamic programming, maximum principle, etc.) are difficult to apply. Then, an approximate solution is sought by constraining control strategies to take on the structure of multi-layer feed-forward neural networks. After discussing the approximation properties of neural control strategies, a particular neural architecture is presented, which is based on what has been called the “Linear-Structure Preserving Principle” (the LISP principle). The original functional problem is then reduced to a nonlinear programming one, and backpropagation is applied to derive the optimal values of the synaptic weights. Recursive equations to compute the gradient components are presented, which generalize the classical adjoint system equations of N-stage optimal control theory. Simulation results related to non-LQ problems show the effectiveness of the proposed method.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
A. P. Sage. Optimum Systems Control. Prentice-Hall, Englewood Cliffs, 1968.
A. E. Bryson and Y. C. Ho. Applied Optimal Control. Blaisdell Publishing Company, 1969.
R. E. Larson. State Increment Dynamic Programming. American Elsevier Publishing Company, 1968.
B. R. Eisenberg and A. P. Sage. “Closed-Loop Optimization of Fixed Configuration Systems”. International Journal of Control, Vol. 3, pp. 183–194, 1966.
D.L. Kleinman and M. Athans. “The Design of Suboptimal Linear Time-Varying Systems”. IEEE Trans. Automatic Control, Vol. AC-13, pp. 150–159, 1968.
P. M. Mäkilä and H. T. Toivonen. “Computational Methods for Parametric LQ Problems- A survey”. IEEE Trans. Automatic Control, Vol. AC-32, pp. 658–671, 1987.
T. Parisini and R. Zoppoli. “Neural Networks for the Solution of N-Stage Optimal Control Problems”, Artificial Neural Networks, T. Kohonen, K. Mäkisara, O. Simula, and J. Kangas, Eds., North-Holland, 1991.
T. Parisini and R. Zoppoli. “Multi-Layer Neural Networks for the Optimal Control of Nonlinear Dynamic Systems”, Proc. First IFAC Symposium on Design Methods of Control Systems, Zurich, Switzerland, 1991.
D. H. Nguyen and B. Widrow. “Neural Networks for Self-Learning Control Systems”. IEEE Control System Magazine, Vol. 10, pp. 18–23, 1990.
K. Hornik, M. Stinchombe, and H. White. “Multilayer Feedforward Networks are Universal Approximators”. Neural Networks, Vol. 2, pp. 359–366, 1989.
R. Hecht-Nielsen. “Theory of the. Backpropagation Neural Network”. Proc. Int. Joint Conf. on Neural Networks, San Diego, CA, 1989, pp. 593–605.
A. R. Barron. “Universal Approximation Bounds for Superpositions of a Sigmoidal Function”. Technical Report No. 58, Department of Statistics, University of Illinois, 1991.
T. Parisini and R. Zoppoli. “Backpropagation and Dynamic Programming in N-Stage Optimal Control Problems”. DIST Int. Rep. No. 90/4, University of Genoa, Italy, 1991.
Ya. Z. Tsypkin. Adaptation and Learning in Automatic Systems. Academic Press, 1971.
D. E. Rumelhart and J. L. McClelland. Parallel Distributed Processing, Vol. 1, Chapter 8, Cambridge, MA, MIT Press, 1986.
P. J. Werbos. “Beyond Regression: New Tools for Prediction and Analysis in the Behavioural Sciences”. Ph.D. Dissertation, Harvard University, Cambridge, MA, 1974.
G. Frisiani, T. Parisini, L. Siccardi, and R. Zoppoli. “Team Theory and Back-Propagation for Dynamic Routing in Communication Networks”. Proc. Int. Joint Conf. on Neural Networks, Seattle, WA, 1991, Vol. 1, pp. 325–334.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer Science+Business Media New York
About this chapter
Cite this chapter
Zoppoli, R., Parisini, T. (1992). Learning Techniques and Neural Networks for the Solution of N-Stage Nonlinear Nonquadratic Optimal Control Problems. In: Isidori, A., Tarn, TJ. (eds) Systems, Models and Feedback: Theory and Applications. Progress in Systems and Control Theory, vol 12. Birkhäuser, Boston, MA. https://doi.org/10.1007/978-1-4757-2204-8_15
Download citation
DOI: https://doi.org/10.1007/978-1-4757-2204-8_15
Publisher Name: Birkhäuser, Boston, MA
Print ISBN: 978-1-4757-2206-2
Online ISBN: 978-1-4757-2204-8
eBook Packages: Springer Book Archive