Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/84268
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLuan, X.-
dc.contributor.authorLiu, F.-
dc.contributor.authorShi, P.-
dc.date.issued2010-
dc.identifier.citationInternational Journal of Innovative Computing Information and Control, 2010; 6(8):3715-3723-
dc.identifier.issn1349-4198-
dc.identifier.issn1349-418X-
dc.identifier.urihttp://hdl.handle.net/2440/84268-
dc.description.abstractThis paper deals with the problem of stochastic optimal control for a class of nonlinear systems subject to Markovian jump parameters. The nonlinearities in the different jump modes are initially parameterized by multilayer neural networks (MNNs), which lead to neural Markovian jump systems. A stochastic neural Lyapunov function (NLF) is used to analyze the stability of the resulting neural control MJSs. Then, based on this stochastic NLF and the neural model, a linear state feedback controller is designed to stabilize the closed-loop nonlinear system and guaranteed an upper bound of the system performance for all admissible approximation errors of the MNNs. The control gains can be derived by solving a set of linear matrix inequalities. Finally, a single link robot arm is demonstrated to show the effectiveness of the proposed design techniques.-
dc.description.statementofresponsibilityXiaoli Luan, Fei Liu and Peng shi-
dc.language.isoen-
dc.publisherICIC International-
dc.rightsICIC International © 2010-
dc.subjectMarkovian jump systems-
dc.subjectNonlinearities-
dc.subjectMultilayer neural networks-
dc.subjectStochastic optimal control-
dc.subjectLinear matrix inequalities (LMIs)-
dc.titleNeural network based stochastic optimal control for nonlinear Markov jump systems-
dc.typeJournal article-
pubs.publication-statusPublished-
dc.identifier.orcidShi, P. [0000-0001-8218-586X]-
Appears in Collections:Aurora harvest
Electrical and Electronic Engineering publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.