Neuro-Fuzzy Controller for Rudder Roll Stabilization of Ships

Abstract:

The uncertainty of ship models and interferences can lead to reduce the effectiveness of conventional roll stabilization controller depending upon accurate mathematical model.This paper proposes the design of neuro-fuzzy controller for rudder roll stabilization. Learning ability of neural network is utilized to optimize the fuzzy controller. Hybrid learning rule which is a combination of backpropagation algorithm and least square estimator is utilized to realized parameter adjustment of fuzzy control rule and membership function in order to improve the adaptive capacity of controller. The simulation tests under various situations such as different navigational speed, sea conditions, wave-to-course angle and ship parameter perturbation are to check the performance of roll stabilizatin controller. Simulation results show that the neuro-fuzzy controller has better robustness and effectiveness for rudder roll stabilization in beam seas.

• Periodical: Applied Mechanics and Materials (Volumes 66-68)
• Pages: 1278-1285
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.66-68.1278
• Online since: July 2011
• Authors: Ming Hui Wang, Yong Quan Yu, Bi Zeng
• Keywords: Fuzzy Control, Neural Network (NN), Neuro-Fuzzy Controller, Rudder Roll Stabilization

References

[1] Hickey N.A., Robust fin roll stabilization of surface ships, in Proceedings of the 36th Conference on Decision and Control, San Diego, California, USA, 1997, p.4225–4230.

[2] Hickey N.A., PID controller optimization for fin roll stabilization, in Proceedings of the 1999 IEEE International Conference on Control Applications, Hawaii, USA, 1999, p.1785–1790.

[3] K. D. Do, J. Pan and Z. P. Jiang, Robust adaptive control of underactuated ships on a linear course with comfort, Ocean Engineering, vol. 30, p.2201–2225, (2003).

DOI: 10.1016/s0029-8018(03)00080-5

[4] J. Aranda, J. M. de la Cruz and J. M. Diaz, Design of a multivariable robust controller to decrease the motion sickness incidence in fast ferries, Control Engineering Practice, vol. 13, p.985–999, Dec. (2005).

DOI: 10.1016/j.conengprac.2004.11.003

[5] Do, K.D. and Pan, J., Smooth asymptotic robust fin roll stabilization of surface ships, in Proceedings of the International Conference on Modeling, Identification and Control, Innsbruck, Austria, 2000, p.1–5.

[6] Alarin, Fuat, Internal model control using fuzzy control for ship roll stabilization, Journal of Marine Science and Technology, v 15, n 2, (2008), pp.141-147.

[7] Tiano, et al, Rudder roll stabilization by neural network-based control systems, Control Engineering Practice, (2009), 33-44.

[8] T. I. Fossen., Guidance and Control of Ocean Vehicles, John Wiley and Sons Ltd, (1994).

[9] Jyh-Shing Roger Jang , Chuen Tsai Sun, Mizutani E, Neuro-Fuzzy and soft computing, Prentice-Hall, Int., Inc., (1997).

[10] Amerongen, J.V., Van der Klugt, P.G.M., Pieffers, J.B.M., Rudder roll stabilization controller design and experimental results, IEEE Control System v 16, n 1, (2007), 1120-1142.

DOI: 10.23919/acc.1986.4788942

[11] Lloyd and A.R.J.M., Seakeeping: Ship Behaviour in Rough Water. RPM, Sussex, UK: Horwood, E. (Ed. ), (1998).