Title :
A Novel Sequential Learning Algorithm for RBF Networks and Its Application to Ship Predictive Control
Author :
Yin, JianChuan ; Dong, Fang ; Wang, Nini
Author_Institution :
Dalian Maritime Univ., Dalian
Abstract :
A radial basis function (RRF) network -based predictive control strategy is proposed for ship control. The RBF network is on-line trained to identify the time-varying system dynamics using a novel sequential learning algorithm referred in as dynamic orthogonal structure adaptation (DOSA) algorithm. The combination of neural network identification and predictive control mechanism minimizes the effects of ships time-varying dynamics and long-time delay, enables accurate and smooth control of ship under various disturbances and. random noises. Simulation results of ship track-keeping control demonstrate the applicability and effectiveness of the control strategy. The quick and adaptive learning algorithm gives RBF network more representing abilities to model nonlinear systems with unstable or unknown dynamics.
Keywords :
learning (artificial intelligence); nonlinear dynamical systems; predictive control; radial basis function networks; ships; time-varying systems; RBF network; adaptive learning algorithm; dynamic orthogonal structure adaptation algorithm; nonlinear system; sequential learning algorithm; ship predictive control; time-varying system dynamics; Control systems; Delay effects; Least squares methods; Marine vehicles; Neural networks; Nonlinear dynamical systems; Predictive control; Predictive models; Process control; Radial basis function networks;
Conference_Titel :
Neural Networks, 2006. IJCNN '06. International Joint Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-9490-9
DOI :
10.1109/IJCNN.2006.247122
