Automatic steering of ships using neural networks

Ship steering control system design presents challenges because the dynamic properties of the vessel itself vary significantly. The use of an artificial neural network as a controller which incorporates the properties of a series of conventional controllers designed for different operating conditions could provide an alternative to adaptive control or gain scheduling in this application. Local model network methods could also provide a basis for efficient modelling of the vessel over a range of operating conditions. The paper describes an investigation of radial basis function networks for ship steering control and of local model networks for representation of ship dynamics. Performance is demonstrated by a series of simulation studies. Copyright © 1999 John Wiley & Sons, Ltd.

[1]  K Nomoto.  On the steering qualities of ships , 1957 .

[2]  T. Johansen,et al.  Constructing NARMAX models using ARMAX models , 1993 .

[3]  R. S. Burns,et al.  The use of artificial neural networks for the intelligent optimal control of surface ships , 1995 .

[4]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[5]  K.S. Narendra,et al.  Intelligent control using neural networks , 1992, IEEE Control Systems.

[6]  Roderick Murray-Smith,et al.  A fractal radial basis function network for modelling , 1992 .

[7]  D. J. Murray-Smith,et al.  Artificial neural networks for ship steering control systems , 1997 .

[8]  Tor Arne Johansen,et al.  Identification of non-linear system structure and parameters using regime decomposition , 1995, Autom..

[9]  T. Arie,et al.  An adaptive steering system for a ship , 1986, IEEE Control Systems Magazine.

[10]  R. L. Hardy.  Multiquadric equations of topography and other irregular surfaces , 1971 .

[11]  Karl Johan Åström,et al.  Identification of ship steering dynamics , 1976, Autom..

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

[13]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[14]  Karl Johan Åström,et al.  Adaptive autopilots for tankers , 1979, Autom..

[15]  T. Kavli.  ASMO—Dan algorithm for adaptive spline modelling of observation data , 1993 .

[16]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[17]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[18]  Peter J Gawthrop,et al.  CONTINUOUS-TIME LOCAL MODEL NETWORKS , 1996 .

[19]  T. Johansen,et al.  A NARMAX model representation for adaptive control based on local models , 1992 .

[20]  M. R. Katebi,et al.  LQG adaptive ship autopilot , 1988 .

[21]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[22]  Job van Amerongen,et al.  Adaptive steering of ships - A model reference approach , 1982, Autom..

[23]  M. J. D. Powell,et al.  Radial basis functions for multivariable interpolation: a review , 1987 .

[24]  Tor Arne Johansen,et al.  Design and analysis of gain-scheduled control using local controller networks , 1997 .

[25]  Katerina Hlavácková.  An upper estimate of the error of approximation of continuous multivariable functions by KBF networks , 1995, ESANN.

[26]  Yao Zhang,et al.  An on-line trained adaptive neural controller , 1995 .

[27]  Thor I. Fossen,et al.  Adaptive feedback linearization applied to steering of ships , 1993 .

[28]  Karl Johan Åström.  Why Use Adaptive Techniques for Steering Large Tankers , 1977 .

[29]  Roland Schultze,et al.  Operating Experience with a High Precision Track Controller for Commercial Ships , 1995 .

[30]  T. Koyama.  Paper 18. Improvement of Course Stability and Control by a Subsidiary Automatic Control , 1972 .