Abstract
The paper presented describes two possible applications of artificial neural networks. The first application is related to solve optimal control problems with discrete time delays in state and control variables subject to control and state constraints. The optimal control problem is transcribed into nonlinear programming problem which is implemented with feed forward adaptive critic neural network to find optimal control and optimal trajectory. The proposed simulation methods are illustrated by the optimal control problem of nitrogen transformation cycle model with discrete time delay of nutrient uptake. The second application deals with backpropagation learning of infinite-dimensional dynamical systems. The proposed simulation methods are illustrated by the back-propagation learning of continuous multilayer Hopfield neural network with discrete time delay using optimal trajectory as teacher signal. Results show that adaptive critic based systematic approach are promising in obtaining the optimal controlwith discrete time delays in state and control variables subject to control and state constraints and that continuous Hopfield neural networks are able to approximate signals generated from optimal trajectory.
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
Barron, A.R.: Universal approximation bounds for superpositions of a sigmoidal function. IEEE Transactions on Information Theory 39, 930–945 (1993)
Bryson Jr., A.E.: Dynamic Optimization. Addison-Wesley Longman Inc., New York (1999)
Buskens, C., Maurer, H.: SQP-methods for solving optimal control problems with control and state constraints: adjoint variable, sensitivity analysis and real-time control. Journal of Computational and Applied Mathematics 120, 85–108 (2000)
Hopfield, J.J.: Neural Networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. 79, 2554–2554 (1982)
Hopfield, J.J.: Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Nat. Acad. Sci. 81, 3088–3092 (1984)
Hornik, M., Stichcombe, M., White, H.: Multilayer feed forward networks are universal approximators. Neural Networks 3, 256–366 (1989)
Hrinca, I.: An Optimal Control Problem for the Lotka-Volterra System with Delay. Nonlinear Analysis, Theory, Methods, Applications 28, 247–262 (1997)
Gnecco, A.: A Comparison Between Fixed-Basis and Variable-Basis Schemes for Function Approximation and Functional Optimization. Journal of Applied Mathematics 2012, article ID 806945 (2012)
Gollman, L., Kern, D., Mauer, H.: Optimal control problem with delays in state and control variables subject to mixed control-state constraints. Optim. Control Appl. Meth. 30, 341–365 (2009)
Chai, Q., Loxton, R., Teo, K.L., Yang, C.: A class of optimal state-delay control problems. Nonlinear Analysis: Real World Applications 14, 1536–1550 (2013)
Kirk, D.E.: Optimal Control Theory: An Introduction. Dover Publications, Inc., Mineola (1989)
Kmet, T.: Material recycling in a closed aquatic ecosystem. I. Nitrogen transformation cycle and preferential utilization of ammonium to nitrate by phytoplankton as an optimal control problem. Bull. Math. Biol. 58, 957–982 (1996)
Kmet, T.: Neural network solution of optimal control problem with control and state constraints. In: Honkela, T. (ed.) ICANN 2011, Part II. LNCS, vol. 6792, pp. 261–268. Springer, Heidelberg (2011)
Kmet, T., Kmetova, M.: Adaptive Critic Neural Network Solution of Optimal Control Problems with Discrete Time Delays. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds.) ICANN 2013. LNCS, vol. 8131, pp. 483–494. Springer, Heidelberg (2013)
Makozov, Y.: Uniform approximation by neural networks. Journal of Approximation Theory 95, 215–228 (1998)
Padhi, R., Unnikrishnan, N., Wang, X., Balakrishnan, S.N.: Adaptive-critic based optimal control synthesis for distributed parameter systems. Automatica 37, 1223–1234 (2001)
Padhi, R., Balakrishnan, S.N., Randoltph, T.: A single network adaptive critic (SNAC) architecture for optimal control synthesis for a class of nonlinear systems. Neural Networks 19, 1648–1660 (2006)
Polak, E.: Optimization Algorithms and Consistent Approximation. Springer, Heidelberg (1997)
Pontryagin, L.S., Boltyanskii, V.G., Gamkrelidze, R.V., Mischenko, E.F.: The Mathematical Theory of Optimal Process. Nauka, Moscow (1983) (in Russian)
Rumelhart, D.F., Hinton, G.E., Wiliams, R.J.: Learning internal representation by error propagation. In: Rumelhart, D.E., McClelland, D.E. (eds.) PDP Research Group: Parallel Distributed Processing: Foundation, vol. 1, pp. 318–362. The MIT Press, Cambridge (1987)
Sandberg, E.W.: Notes on uniform approximation of time-varying systems on finite time intervals. IEEE Transactions on Circuits and Systems-1: Fundamental Theory and Applications 45, 305–325 (1998)
Sharif, H.R., Vali, M.A., Samat, M., Gharavisi, A.A.: A New Algorithm for Optimal Control of Time-Delay Systems. Applied Mathematical Science 5, 595–606 (2011)
Sun, D.Y., Huang, T.C.: A solutions of time-delayed optimal control problems by the use of modified line-up competition algorithm. Journal of the Taiwan Institute of Chemical Engineers 41, 54–64 (2010)
Tokuda, I., Tokunaga, R., Aihara, K.: Back-propagation learning of infinite-dimensional dynamical systems. Neural Networks 16, 1179–1193 (2003)
Werbos, P.J.: Approximate dynamic programming for real-time control and neural modelling. In: White, D.A., Sofge, D.A. (eds.) Handbook of Intelligent Control: Neural Fuzzy, and Adaptive Approaches, pp. 493–525 (1992)
Xia, Y., Feng, G.: A New Neural Network for Solving Nonlinear Projection Equations. Neural Network 20, 577–589 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Kmet, T., Kmetova, M. (2015). Neural Networks Solution of Optimal Control Problems with Discrete Time Delays and Time-Dependent Learning of Infinitesimal Dynamic System. In: Koprinkova-Hristova, P., Mladenov, V., Kasabov, N. (eds) Artificial Neural Networks. Springer Series in Bio-/Neuroinformatics, vol 4. Springer, Cham. https://doi.org/10.1007/978-3-319-09903-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-09903-3_15
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-09902-6
Online ISBN: 978-3-319-09903-3
eBook Packages: EngineeringEngineering (R0)