Dynamic neural-fuzzified adaptive control of ship course with parametric modelling uncertainties. (1st January 2011)

• Record Type: Journal Article
• Authors: Wang, Yang; Guo, Chen; Sun, Fuchun; Shen, Zhipeng; Guo, Di
• Is Part Of: International journal of modelling, identification and control. Volume 13:Number 4(2011)
• Page Start: 251
• Page End: 258
• Publication Date: 2011-01-01
• Subjects: dynamic neural-fuzzified system -- DNFS -- uncertainties -- course tracking -- adaptive control; Engineering -- Methodology -- Periodicals; Science -- Methodology -- Periodicals; 001.42
• DOI: 10.1504/IJMIC.2011.041780
• Languages: English
• ISSNs: 1746-6172

Abstract

A dynamic neural-fuzzified system (DNFS) based adaptive control algorithm is presented in this paper, aiming at the uncertainties arising from changes of the model parameters in ship course control. The inverse dynamics of the Norrbin non-linear NARX ship model is identified by the DNFS properly, and the structure and parameters of the DNFS are adjusted simultaneously. Well-trained DNFS is then connected in parallel with a PD controller to construct an adaptive controller for course control, while the weights of DNFS are more adjusted by the adaptive law whose independent variable is the output of PD controller. Simulation results of the course tracking of a 5, 446 TEU container ship validate the effectiveness of the proposed algorithm.