Control for Ship Course-Keeping Using Optimized Support Vector Machines

Support vector machines (SVM) are proposed in order to obtain a robust controller for ship course-keeping. A cascaded system is constructed by combining the dynamics of the rudder actuator with the dynamics of ship motion. Modeling errors and disturbances are taken into account in the plant. A controller with a simple structure is produced by applying an SVM and L2-gain design. The SVM is used to identify the complicated nonlinear functions and the modeling errors in the plant. The Lagrangian factors in the SVM are obtained using on-line tuning algorithms. L2-gain design is applied to suppress the disturbances. To obtain the optimal parameters in the SVM, then particle swarm optimization (PSO) method is incorporated. The stability and robustness of the close-loop system are confirmed by Lyapunov stability analysis. Numerical simulation is performed to demonstrate the validity of the proposed hybrid controller and its superior performance over a conventional PD controller.

[1]  Yang Yu,et al.  A Novel Adaptive Neural Control Scheme for Uncertain Ship Course-keeping System , 2014 .

[2]  P. J. García Nieto,et al.  Hybrid PSO-SVM-based method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability , 2015, Reliab. Eng. Syst. Saf..

[3]  Zenon Zwierzewicz.  On the ship course-keeping control system design by using robust and adaptive control , 2014, 2014 19th International Conference on Methods and Models in Automation and Robotics (MMAR).

[4]  Johan A. K. Suykens,et al.  Optimal control by least squares support vector machines , 2001, Neural Networks.

[5]  Józef Lisowski,et al.  Multi-stage safe ship control with neural state constraints , 2015, 2015 IEEE 2nd International Conference on Cybernetics (CYBCONF).

[6]  Yann LeCun,et al.  Measuring the VC-Dimension of a Learning Machine , 1994, Neural Computation.

[7]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[8]  Thor I. Fossen,et al.  Guidance and control of ocean vehicles , 1994 .

[9]  Bin Fu,et al.  Robust Control for Ship Course-Keeping Based on Support Vector Machines: Particle Swarm Optimization and L2-Gain , 2013 .

[10]  Johan A. K. Suykens,et al.  Weighted least squares support vector machines: robustness and sparse approximation , 2002, Neurocomputing.

[11]  Kazuhiko Hasegawa,et al.  Automatic ship berthing using artificial neural network trained by consistent teaching data using nonlinear programming method , 2013, Eng. Appl. Artif. Intell..

[12]  Ping Li,et al.  Intelligent PID controller design with adaptive criterion adjustment via least squares support vector machine , 2009, 2009 Chinese Control and Decision Conference.

[13]  Shuqiang Jiang,et al.  LS-SVM application for ship course model predictive control , 2013, 2013 IEEE International Conference on Mechatronics and Automation.

[14]  Piotr Borkowski,et al.  Ship course stabilization by feedback linearization with adaptive object model , 2013 .

[15]  K. D. Do.  Global Robust and Adaptive Output Feedback Dynamic Positioning of Surface Ships , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[16]  Xianku Zhang,et al.  Ship course-keeping adaptive Fuzzy controller design using command filtering with minimal parametrization , 2013, 2013 25th Chinese Control and Decision Conference (CCDC).

[17]  Zenon Zwierzewicz,et al.  The Design of Ship Autopilot by Applying Observer - Based Feedback Linearization , 2015 .

[18]  Ming-Chung Fang,et al.  Application of neuro-fuzzy algorithm to portable dynamic positioning control system for ships , 2016 .

[19]  A. Ebrahimzadeh,et al.  Application of the PSO-SVM model for recognition of control chart patterns. , 2010, ISA transactions.

[20]  Andrea Gasparri,et al.  Simultaneous Roll Damping and Course Keeping Via Sliding Mode Control for a Marine Vessel in Seaway , 2011 .

[21]  Zoran Vukic,et al.  Adaptive Fuzzy Ship Autopilot for Track-Keeping , 2000 .

[22]  Weisheng Chen,et al.  Global generalised exponential/finite-time control for course-keeping of ships , 2016, Int. J. Control.

[23]  Zao-Jian Zou,et al.  Identification of Response Models of Ship Maneuvering Motion Using Support Vector Machines , 2007 .

[24]  Enrico Zio,et al.  A dynamic particle filter-support vector regression method for reliability prediction , 2013, Reliab. Eng. Syst. Saf..

[25]  Peng Xiu-ya.  Nonlinear H-infinity inverse optimal output feedback control for ship course , 2014 .

[26]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[27]  Dan Wang,et al.  Adaptive neural network control for a class of uncertain nonlinear systems in pure-feedback form , 2002, Autom..

[28]  Leigh McCue,et al.  Handbook of Marine Craft Hydrodynamics and Motion Control [Bookshelf] , 2016, IEEE Control Systems.

[29]  Thor I. Fossen,et al.  Path following control system for a tanker ship model , 2007 .

[30]  Minh-Duc Le,et al.  Study on a new and effective fuzzy PID ship autopilot , 2004, Artif. Life Robotics.

[31]  Tristan Perez,et al.  Ship Motion Control: Course Keeping and Roll Stabilisation Using Rudder and Fins , 2005 .

[32]  Fu Hui-xuan.  Variable universe fuzzy– least squares support-vector-machine compound control for ship course-keeping , 2011 .

[33]  Yunqian Ma,et al.  Practical selection of SVM parameters and noise estimation for SVM regression , 2004, Neural Networks.

[34]  Alireza Alfi,et al.  Reliability analysis of H-infinity control for a container ship in way-point tracking , 2015 .

[35]  M. R. Katebi,et al.  H ∞ robust control design for dynamic ship positioning , 1997 .

[36]  Mukhtiar Ali Unar,et al.  Automatic steering of ships using neural networks , 1999 .

[37]  A. Selakov,et al.  Hybrid PSO-SVM method for short-term load forecasting during periods with significant temperature variations in city of Burbank , 2014, Appl. Soft Comput..

[38]  Mogens Blanke,et al.  Dynamic Model for Thrust Generation of Marine Propellers , 2000 .

[39]  Jing Sun,et al.  Path following of underactuated marine surface vessels using line-of-sight based model predictive control ☆ , 2010 .

[40]  Davide Anguita,et al.  In-Sample and Out-of-Sample Model Selection and Error Estimation for Support Vector Machines , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[41]  Lokukaluge P. Perera,et al.  Pre-filtered sliding mode control for nonlinear ship steering associated with disturbances , 2012 .