Missouri S&T Scholar's Mine Research RepositoryMissouri S&T Research
print 
Title: Generalized Hamilton-Jacobi-Bellman formulation-based neural network control of affine nonlinear discrete-time systems
Author (s): Chen, Zheng
Sarangapani, Jagannathan
Department/Lab Affiliations: Computer Science
Electrical and Computer Engineering
Engineering Management & Systems Engineering
Intelligent Systems Center
Keywords: generalized Hamilton–Jacobi–Bellman (BHJB) equation
neural network (NN)
nonlinear discrete-time (DT) system
Issue Date: 2008-01
Publisher: Institute of Electrical and Electronics Engineers IEEE
Citation: Chen, Z., S. Jagannathan,"Generalized Hamilton-Jacobi-Bellman formulation-based neural network control of affine nonlinear discrete-time systems," IEEE Transactions on Neural Networks, Vol. 19, pp. 90-106,2008.
Abstract: In this paper, we consider the use of nonlinear networks towards obtaining nearly optimal solutions to the control of nonlinear discrete-time (DT) systems. The method is based on least squares successive approximation solution of the generalized Hamilton-Jacobi-Bellman (GHJB) equation which appears in optimization problems. Successive approximation using the GHJB has not been applied for nonlinear DT systems. The proposed recursive method solves the GHJB equation in DT on a well-defined region of attraction. The definition of GHJB, pre-Hamiltonian function, HJB equation, and method of updating the control function for the affine nonlinear DT systems under small perturbation assumption are proposed. A neural network (NN) is used to approximate the GHJB solution. It is shown that the result is a closed-loop control based on an NN that has been tuned a priori in offline mode. Numerical examples show that, for the linear DT system, the updated control laws will converge to the optimal control, and for nonlinear DT systems, the updated control laws will converge to the suboptimal control.
Type: Article - Journal
text
In Title: IEEE Transactions on Neural Networks
Copyright Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
allows publisher's final version to be uploaded
FULL COPYRIGHT INFORMATION:
http://www.ieee.org/portal/cms_docs_iportals/iportals/publications/rights/downloads/IEEECForm121302pdf.pdf
http://www.ieee.org/web/publications/rights/index.html
http://www.ieee.org/web/publications/rights/policies.html
Publisher URL:
http://dx.doi.org/10.1109/TNN.2007.900227
Link to this page:
http://scholarsmine.mst.edu/post_prints/GeneralizedHamiltonJacobiBellmanFormulationBase_09007dcc805301f8.html
Full Text:
GeneralizedHamilton_09007dcc80530386.pdf



titleGeneralized Hamilton-Jacobi-Bellman formulation-based neural network control of affine nonlinear discrete-time systems
contributor.authorChen, Zheng
contributor.authorSarangapani, Jagannathan
contributor.deptlabComputer Science
contributor.deptlabElectrical and Computer Engineering
contributor.deptlabEngineering Management & Systems Engineering
contributor.deptlabIntelligent Systems Center
subjectgeneralized Hamilton–Jacobi–Bellman (BHJB) equation
subjectneural network (NN)
subjectnonlinear discrete-time (DT) system
date.issued2008-01
publisherInstitute of Electrical and Electronics Engineers IEEE
identifier.citationChen, Z., S. Jagannathan,"Generalized Hamilton-Jacobi-Bellman formulation-based neural network control of affine nonlinear discrete-time systems," IEEE Transactions on Neural Networks, Vol. 19, pp. 90-106,2008.
identifier.pub.URI
http://dx.doi.org/10.1109/TNN.2007.900227
description.abstractIn this paper, we consider the use of nonlinear networks towards obtaining nearly optimal solutions to the control of nonlinear discrete-time (DT) systems. The method is based on least squares successive approximation solution of the generalized Hamilton-Jacobi-Bellman (GHJB) equation which appears in optimization problems. Successive approximation using the GHJB has not been applied for nonlinear DT systems. The proposed recursive method solves the GHJB equation in DT on a well-defined region of attraction. The definition of GHJB, pre-Hamiltonian function, HJB equation, and method of updating the control function for the affine nonlinear DT systems under small perturbation assumption are proposed. A neural network (NN) is used to approximate the GHJB solution. It is shown that the result is a closed-loop control based on an NN that has been tuned a priori in offline mode. Numerical examples show that, for the linear DT system, the updated control laws will converge to the optimal control, and for nonlinear DT systems, the updated control laws will converge to the suboptimal control.
typeArticle - Journal
type.DCMITypetext
type.statusFinal version
rightsThis material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
rightsallows publisher's final version to be uploaded
rights.URI
http://www.ieee.org/portal/cms_docs_iportals/iportals/publications/rights/downloads/IEEECForm121302pdf.pdf
rights.URI
http://www.ieee.org/web/publications/rights/index.html
rights.URI
http://www.ieee.org/web/publications/rights/policies.html
relation.isPartOfIEEE Transactions on Neural Networks
date.accessioned2008-07-08T20:34:25Z
date.available2008-07-11T18:36:09Z
identifier.persist.URI
http://scholarsmine.mst.edu/post_prints/GeneralizedHamiltonJacobiBellmanFormulationBase_09007dcc805301f8.html
Full Text
GeneralizedHamilton_09007dcc80530386.pdf