Paper Info
Title
Learning structural uncertainties of nonlinear systems with RBF neural networks via persistently exciting control
Abstract
This work presents a scheme for learning, online, the actual nonlinearities of systems in canonical form. The proposed architecture comprises of an on-line Radial Basis Function (RBF) neural network identifier and a controller, with the signals issued by the latter guaranteeing the satisfaction of a Persistency of Excitation (PE) condition for the RBF regressors employed. As a consequence, the neural network weight estimates are proven to converge to small neighborhoods of their true values; thus succeeding learning the actual system nonlinearities with quality guarantees. Key characteristic is the isolation between identifier and controller design, increasing the robustness level of the proposed on-line learning scheme. Finally, a simulation study is provided to demonstrate its effectiveness.
Year
DOI
Venue
2013
10.1109/MED.2013.6608925
Control & Automation
Keywords
Field
DocType
control nonlinearities,control system synthesis,learning (artificial intelligence),nonlinear control systems,radial basis function networks,regression analysis,uncertain systems,pe condition,rbf neural network identifier,rbf neural networks,rbf regressors,controller design,neural network weight estimates,nonlinear systems,online learning scheme,online radial basis function neural network identifier,persistency of excitation condition,robustness level,structural uncertainty learning,system nonlinearity,neural networks,steady state,vectors,convergence,learning artificial intelligence
Control theory,Nonlinear system,Radial basis function,Identifier,Computer science,Control theory,Robustness (computer science),Control engineering,Canonical form,Types of artificial neural networks,Artificial neural network
Conference
ISSN
ISBN
Citations 
2325-369X
978-1-4799-0995-7
0
PageRank 
References 
Authors
0.34
9
2
Name
Order
Citations
PageRank
Charalampos P. Bechlioulis130413.17
George A. Rovithakis258152.21