A sequential learning algorithm for RBF networks and its application to ship course-changing control

Author

Bi, Gexin ; Dong, Fang

Author_Institution

Coll. of Navig., Dalian Maritime Univ., Dalian

fYear

2008

fDate

2-4 July 2008

Firstpage

3779

Lastpage

3784

Abstract

In this paper, a sequential learning algorithm for radial basis function (RBF) network is introduced referred to as dynamic orthogonal structure adaptation (DOSA) algorithm. Based on DOSA algorithm, a multi-step predictive control strategy is presented and applied to ship course-changing control. The combination of RBF network identification and predictive control mechanism minimizes the unfavorable effects of shippsilas time-varying dynamics and long time delay, enables accurate and smooth control of ship under various disturbances and random noises. Simulation results of ship course-changing experiment demonstrate the applicability and effectiveness of the RBF-based predictive control strategy.

Keywords

learning (artificial intelligence); motion control; neurocontrollers; position control; predictive control; radial basis function networks; ships; RBF networks; dynamic orthogonal structure adaptation algorithm; multistep predictive control; radial basis function network; sequential learning algorithm; ship course-changing control; Marine vehicles; Radial basis function networks; Radial Basis Function Network; Sequential Learning; Ship Control;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Decision Conference, 2008. CCDC 2008. Chinese

Conference_Location

Yantai, Shandong

Print_ISBN

978-1-4244-1733-9

Electronic_ISBN

978-1-4244-1734-6

Type

conf

DOI

10.1109/CCDC.2008.4598038

Filename

4598038