Document Type : Review Article

Authors

Abstract

In this paper we present a nonlinear optimal control method based on approximating the solution of Hamilton-Jacobi-Bellman (HJB) equation. Value function is approximated as the output of Multilayer Perceptron Neural Network (MLPNN). Parameters of MLPNN are weights and biases of each layer that form structure of the proposed neural network. These parameters are unknown thus we apply an Adaptive Extended Kalman Filter to approximate unknown parameters. In so doing, the problem of solution of HJB equation is converted to estimation of MLPNN parameters. Also, convergence of the estimation error of MLPNN parameters is proven. Two examples have been brought to show the merits of the proposed approach and to compare the obtained results by applying the multilayer Perceptron and the Radial Basic Function Neural Network (RBFNN). 

Keywords

[1] H.P Geering. "optimal control with engineering applications". springer 2007
[2] P M.pardalos. "nonlinear optimization with engineer application" . springer 2008
[3] W. L. Garrard and J.M.Jordan. "Design of nonlinear automatic flight control systems." Automatica, 1977; 13: 497-505
[4] S. Kumar, R. Padhi and L. Behra “Continuous-time Single Network Adaptive Critic for regulator Design of Nonlinear Control Affine Systems” Proceedings of 17th World Congress of the International Federation of Automatic Control, 2008, Seol, S. Korea
[5] G.saridis, C.S.Lee. "an approximation theory of optimal control for trainable manipulators" . IEEE transactions on systems, Man,Cybernetics, 1979
[6] M.S.Ahmed “Neural controllers for nonlinear state feedback L2- gain control” IEE Proceedings of Control Theory Applications, 2000.147(3).
[7] P.V medagam and F pourboghrat. "optimal control of nonlinear system using RBF neural network and adaptive extend kalman filter", American control conference 2009
[8] G. CORSINI, M. DIANI, R. GRASSO, M. DE MARTINO, P. MANTERO and S. B. SERPICO, " Radial Basis Function and Multilayer Perceptron neural networks for sea water optically active parameter estimation in case II waters: a comparison" Taylor and Francis, INT. J. REMOTE SENSING, 2003, VOL. 24, NO. 20, 3917–3932
[9] R.W.Beard, G.N,saridis and J.T wen. "approximate solution to the time invariant Hamilton-Jacobi-belman equation" journal of optimization theory and application .1998
[10] S Ressell, P Norvig, "artificial Intelligence A modern approach" 3rd edition .prenticle hall .2009
[11] D simon, "Training radial basis neural network with extended kalman filter", neurocomputing, 2001
[12] T cheng, F L lewis, "A neural network solution for fix-final time optimal control of nonlinear system." journal of optimization theory and applications. 2006
[13] D simon, " Training fuzzy system with extended kalman filter" fuzzy sets and system. 2002
[14] W.L.Garrard, D.F.Ennis and S.A. Snell. "Nonlinear feedback control of highly maneuverable aircraft" International journal of control, 1992;56(4): 799-812
[15] S.L Sun. "multi-sensor optimal information fusion kalman filter". Automatica 2004
[16] A Halme, R.P Hamalaine. " on the nonlinear regulator problem" journal of optimization theory and application, 1975
[17] Y Wang, D j Hill, R H Middleton and L Gao. "Transient stability enhancement and voltage regulation of power system" IEE transactions on power system, 1993
[18] J.R,D Clontier, C.N souza, and k,C P Mrace. "Nonlinear regulation and nonlinear H infinite control via the state dependent Riccati equation technique" .IFAC Word congress, sanfrancisco california 1996
[19] C Park, P tsioras. " sub optimal feedback control using a suxxessive Galerkin algorithm" .American control conference 2003
[20] P Dorato. "Linear quadratic control, an introduction Krieger publishing company" Florida 2000