Nonlinear Model Predictive Control for Fin Stabilizer System of Marine Vessels Based on Recurrent Neural Network

In this paper, a model predictive control (MPC) method for ship nonlinear fin stabilizer system based on recurrent neural network is proposed. MPC is an effective method in process control, which can be used to improve efficiency of the control system. However, one of the constraints of MPC is the heavy computational burden when solving the optimization problem. To tackle this problem, the recurrent neural network (RNN) is introduced to solve quadratic programming (QP) problem so that a higher convergence can be achieved. In our work, the ship nonlinear fin stabilizer system is firstly linearized by means of the exact feedback linearization method, then MPC is applied to the linearized model to derive the control strategy for the fin stabilizer system. Finally, a numerical simulation is given to validate effectiveness and performance of the designed algorithm.

[1]  Alireza Nazemi,et al.  A neural network model for solving convex quadratic programming problems with some applications , 2014, Eng. Appl. Artif. Intell..

[2]  Martin T. Hagan,et al.  Neural network design , 1995 .

[3]  Zhang Xianku.  Fin stabilizer control based on backstepping and closed-loop gain shaping algorithms , 2008 .

[4]  Xiaolin Hu,et al.  A New Recurrent Neural Network for Solving Convex Quadratic Programming Problems With an Application to the $k$-Winners-Take-All Problem , 2009, IEEE Transactions on Neural Networks.

[5]  S. J. O. Tinn.  A CONTROL SYSTEM FOR ACTIVE FIN ROLL STABILIZATION , 1970 .

[6]  D A Bennett.  COMPARISON OF SHIP ROLL STABILISATION METHODS , 1970 .

[7]  Li Xiao-fang.  3-D Visual Simulation of Irregular Ocean Waves Based on Matlab , 2003 .

[8]  Hui Li,et al.  Adaptive fuzzy sliding mode controller design for ship fin stabilizer under rough sea conditions , 2014, 2014 IEEE International Conference on Information and Automation (ICIA).

[9]  Zheng Yan,et al.  Model Predictive Control for Tracking of Underactuated Vessels Based on Recurrent Neural Networks , 2012, IEEE Journal of Oceanic Engineering.

[10]  Qingshan Liu,et al.  A One-Layer Recurrent Neural Network With a Discontinuous Hard-Limiting Activation Function for Quadratic Programming , 2008, IEEE Transactions on Neural Networks.

[11]  John J. Hopfield,et al.  Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[12]  Tieshan Li,et al.  Adaptive backstepping-based nonlinear disturbance observer for fin stabilizer system , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).