Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/29288
Title: | Nonlinear adaptive control using gaussian networks with composite adaptation for improved convergence |
Authors: | Fabri, Simon G. Kadirkamanathan, Visakan |
Keywords: | Nonlinear control theory Neural networks (Computer science) Adaptive control systems |
Issue Date: | 1996 |
Publisher: | University of Sheffield. Department of Automatic Control & Systems Engineering |
Citation: | Fabri, S., & Kadirkamanathan, V. (1996). Nonlinear adaptive control using gaussian networks with composite adaptation for improved convergence. (ACSE Research Report 653). Sheffield. |
Abstract: | The use of composite adaptive laws for control of the affine class of nonlinear systems having unknown dynamics is proposed. These dynamics are approximated by Gaussian radial basis function neural networks whose parameters are updated by a composite law that is driven by both tracking and estimation errors, combining techniques used in direct and indirect adaptive control. This is motivated by the need to improve the speed of convergence of the unknown parameters, hence resulting in a better system performance. The inherent approximation error of the neural networks might lead to instability because of parameter drift. This is compensated for by augmenting the control law with a low gain sliding mode component and using deadzone adaptation for the indirect part of the composite law. The stability of the system is analysed and the effectiveness of the method is demonstrated by simulation and comparison with a direct adaptive control scheme. |
URI: | https://www.um.edu.mt/library/oar//handle/123456789/29288 |
Appears in Collections: | Scholarly Works - FacEngSCE |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Nonlinear_adaptive_control_using_gaussian_networks_with_composite_adaptation_for_improved_convergence.pdf Restricted Access | 342.25 kB | Adobe PDF | View/Open Request a copy |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.