Nonlinear control with linearized models and neural networks
Document Type
Conference Item
Publication Date
1-1-1995
Abstract
A nonlinear control strategy involving a geometric feedback controller and adaptive approximation of the plant is presented. The plant is approximated by a linearized model and a neural network which approximates the higher order error terms. Online adaptation of the network is performed using steepest descent with a dead zone function. The proposed strategy is applied to two case studies for output tracking of set points. The results show good tracking comparable with utilizing the actual model of the plant (usually unknown) and better than that obtained when using the linearized model alone.
Keywords
Adaptive systems, Approximation theory, Control equipment, Feedback control, Linearization, Mathematical models, Neural networks, Poles and zeros, State space methods, Vectors, Geometric feedback controller, Online adaptation, Nonlinear control systems.
Divisions
fac_eng
Publisher
IEE
Event Title
Proceedings of the 4th International Conference on Artificial Neural Networks
Event Location
Cambridge, United Kingdom
Event Dates
1995
Event Type
conference
Additional Information
Conference code: 43331 Export Date: 5 March 2013 Source: Scopus CODEN: IECPB Language of Original Document: English Correspondence Address: Hussain, M.A.; Imperial Coll, London, United Kingdom Sponsors: IEE