Missouri S&T Scholar's Mine Research RepositoryMissouri S&T Research
print 
Title: Adaptive critic-based neural network controller for uncertain nonlinear systems with unknown deadzones
Author (s): Pingan He
Sarangapani, Jagannathan
Balakrishnan, S. N.
Department/Lab Affiliations: Computer Science
Electrical and Computer Engineering
Engineering Management & Systems Engineering
Mechanical & Aerospace Engineering
Keywords: Lyapunov approach
adaptive control
adaptive critic-based neural network controller
closed loop systems
closed-loop tracking error
control nonlinearities
control system synthesis
deadzone compensation scheme
deadzone nonlinearity
discrete time systems
dynamics approximation
learning (artificial intelligence)
multilayer neural network controller
multilayer perceptrons
neurocontrollers
nonlinear control systems
reinforcement learning scheme
tracking performance
uncertain nonlinear systems
uncertain systems
uniform ultimately boundedness
unknown deadzones
weight estimates
Issue Date: 2002
Publisher: Institute of Electrical and Electronics Engineers
Citation: Pingan He; Jagannathan, S.; Balakrishnan, S. N. "Adaptive critic-based neural network controller for uncertain nonlinear systems with unknown deadzones" Proceedings of the 41st IEEE Conference on Decision and Control, 2002. 10-13 Dec. 2002 Pages: 955- 960 vol.1
Abstract: A multilayer neural network (NN) controller in discrete-time is designed to deliver a desired tracking performance for a class of nonlinear systems with input deadzones. This multilayer NN controller has an adaptive critic NN architecture with two NNs for compensating the deadzone nonlinearity and a third NN for approximating the dynamics of the nonlinear system. A reinforcement learning scheme in discrete-time is proposed for the adaptive critic NN deadzone compensator, where the learning is performed based on a certain performance measure, which is supplied from a critic. The adaptive generating NN rejects the errors induced by the deadzone whereas a second NN based critic generates a signal, which is used to tune the weights of the action generating NN so that the deadzone compensation scheme becomes adaptive whereas a third multilayer NN simultaneously approximate the nonlinear dynamics of the system. Using the Lyapunov approach, the uniform ultimately boundedness (UUB) of the closed-loop tracking error and weight estimates of action generating NN, critic NN and the third NN are shown by using a novel weight update.
Type: Article - Conference proceedings
text
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.
FULL COPYRIGHT INFORMATION:
http://www.ieee.org/web/publications/rights/policies.html
Publisher URL:
http://ieeexplore.ieee.org/iel5/8437/26566/01184632.pdf?arnumber=118463
Link to this page:
http://scholarsmine.mst.edu/post_prints/01184632_09007dcc8030cd62.html
Full Text:
01184632_09007dcc8030cd67.pdf



titleAdaptive critic-based neural network controller for uncertain nonlinear systems with unknown deadzones
contributor.authorPingan He
contributor.authorSarangapani, Jagannathan
contributor.authorBalakrishnan, S. N.
contributor.deptlabComputer Science
contributor.deptlabElectrical and Computer Engineering
contributor.deptlabEngineering Management & Systems Engineering
contributor.deptlabMechanical & Aerospace Engineering
subjectLyapunov approach
subjectadaptive control
subjectadaptive critic-based neural network controller
subjectclosed loop systems
subjectclosed-loop tracking error
subjectcontrol nonlinearities
subjectcontrol system synthesis
subjectdeadzone compensation scheme
subjectdeadzone nonlinearity
subjectdiscrete time systems
subjectdynamics approximation
subjectlearning (artificial intelligence)
subjectmultilayer neural network controller
subjectmultilayer perceptrons
subjectneurocontrollers
subjectnonlinear control systems
subjectreinforcement learning scheme
subjecttracking performance
subjectuncertain nonlinear systems
subjectuncertain systems
subjectuniform ultimately boundedness
subjectunknown deadzones
subjectweight estimates
date.issued2002
date.submitted2007
publisherInstitute of Electrical and Electronics Engineers
identifier.citationPingan He; Jagannathan, S.; Balakrishnan, S. N. "Adaptive critic-based neural network controller for uncertain nonlinear systems with unknown deadzones" Proceedings of the 41st IEEE Conference on Decision and Control, 2002. 10-13 Dec. 2002 Pages: 955- 960 vol.1
identifier.issn0191-2216
identifier.pub.URI
http://ieeexplore.ieee.org/iel5/8437/26566/01184632.pdf?arnumber=118463
description.abstractA multilayer neural network (NN) controller in discrete-time is designed to deliver a desired tracking performance for a class of nonlinear systems with input deadzones. This multilayer NN controller has an adaptive critic NN architecture with two NNs for compensating the deadzone nonlinearity and a third NN for approximating the dynamics of the nonlinear system. A reinforcement learning scheme in discrete-time is proposed for the adaptive critic NN deadzone compensator, where the learning is performed based on a certain performance measure, which is supplied from a critic. The adaptive generating NN rejects the errors induced by the deadzone whereas a second NN based critic generates a signal, which is used to tune the weights of the action generating NN so that the deadzone compensation scheme becomes adaptive whereas a third multilayer NN simultaneously approximate the nonlinear dynamics of the system. Using the Lyapunov approach, the uniform ultimately boundedness (UUB) of the closed-loop tracking error and weight estimates of action generating NN, critic NN and the third NN are shown by using a novel weight update.
typeArticle - Conference proceedings
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.
rights.URI
http://www.ieee.org/web/publications/rights/policies.html
date.accessioned2007-04-05T14:15:57Z
date.available2007-04-05T14:15:57Z
identifier.persist.URI
http://scholarsmine.mst.edu/post_prints/01184632_09007dcc8030cd62.html
Full Text
01184632_09007dcc8030cd67.pdf