Robust Adaptive Nn Control of Ship Course Autopilot Based on DSC

Abstract:

The problem of adaptive control design of ship autopilot with rudder dynamics is studied. The model is described by a third order nonlinear model for parametric uncertainties. An adaptive neural network (NN ) control algorithm based on dynamic surface control (DSC) is developed. With only one learning parameter and reduced computation load, the proposed algorithm can avoid both problem of explosion of complexity in the conventional backstepping method and singularity problem. In addition, the boundedness stability of the closed-loop system is guaranteed and tracking error can be made arbitrary small. The effectiveness of the presented autopilot has been demonstrated in the simulation.

• Periodical: Applied Mechanics and Materials (Volumes 321-324)
• Pages: 2017-2022
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.321-324.2017
• Online since: June 2013
• Authors: Hong Ying Sun, Feng Wei Yu
• Keywords: Autopilot, Backstepping, Dynamic Surface Control (DSC), Neural Network (NN), Parametric Uncertainty

References

[1] ANNA WITKOOWSKA,MIROSLAW TOMERA:submitted to Journal of Appl.Math.Comput( 2007)

[2] Healey A.J ,Lienard D:submitted to Journal of Oceanic Engineering(1993)

[3] M. Krstic,I. Kanellakopoulos and P. V. Kokotovic:Nonlinear and Adaptive Control Design(Wiley Publications,New York1995)

[4] S. S. Ge,J. Wang:submitted to Journal of IEEE Trans. Neural Network(2002)

[5] Y. S. Yang,T. S. Li and X. F. Wang:Computer Science(Springer Publication,Verlag Berlin Heidelberg 2006)

[6] D. Wang ,J. Huang:submitted to Journal of IEEE Trans. Neural Network(2005)

[7] T. S. Li,Z. J. Zou and X. M. Zhou:Proceedings of the 2008 American Control Conference(2008),pp.81-86.

[8] S. Swaroop,J. K. Hedrick and P. P. Yip:submitted to Journal of IEEE Trans. Autom.Control(2002)