Adaptive Neural-net Control System for Ship Roll Stabilization

• Published in: 2007 IEEE International Conference on Control Applications pp. 735 - 740
• Main Authors: Xuejing Yang, Xiren Zhao, Xiuyan Peng
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2007
• Subjects: Adaptive control; Adaptive systems; Control system synthesis; Control systems; Fuzzy control; Linear feedback control systems; Marine vehicles; Mathematical model; Motion control; Programmable control
• DOI: 10.1109/CCA.2007.4389320
• ISBN: 9781424404421; 1424404428
• ISSN: 1085-1992

In this paper, an adaptive neural-net control system, in which learning is performed in a loop totally independent from the control loop, is proposed for the problem of ship roll stabilization. The modeling of the ship and the controller are adjusted continuously in order to deal with changes of dynamic properties caused by disturbances. Based the experimental data in tank, disturbance model caused by sea wave is presented. A recurrent neural network is used to approaching the dynamics of the ship, and the real time recurrent learning algorithm is described to train the forward model. This paper proposes the adaptation process of control system and applies it to the ship HD702. The control effect of roll stabilization and the approaching accuracy of forward model network are investigated.