Abstract
A neural network based vessel drift predicting system has been developed. The network takes as input signals velocity components values, a rudder deflection angle and the transversal projection of relative wind velocity. These values are taken at the bounds of a time prediction interval. A value of drift speed at the right bound of the interval is the network output. A usual fully-connected perceptron-type neural network is used for the prediction problem solution. The training data are collected by imitation modeling for a containership. Marine Systems Simulator (MSS) MATLAB based toolbox is used as the software for the purpose. The process of the data collection includes repeating prevention and classification stages. The first stage ensures that closely placed input samples are not to be used. The second stage ensures the uniformity of samples distribution in the working space of the input signal. The training data are simulated to be collected during usual operation of the ship, when the ship is track controlled. The result of the test of the proposed neural scheme shows that the network may either improve dead reckoning accuracy or decrease it, as well.
Similar content being viewed by others
REFERENCES
Faltinsen, O.M., Sea Loads on Ships and Offshore Structures, Cambridge Ocean Technology Series, Cambridge: Cambridge Univ. Press, 1990.
Fossen, T.I., Handbook of Marine Craft Hydrodynamics and Motion Control, Hoboken, N.J.: John Wiley & Sons, 2021.https://doi.org/10.1002/9781119994138
Guide for Vessel Maneuverability, Houston: American Bureau of Shipping, 2017.
Deryabin, V.V., Neural networks based prediction model for vessel track control, Autom. Control Comput. Sci., 2019, vol. 53, no. 6, pp. 502–510. https://doi.org/10.3103/S0146411619060038
Haykin, S., Neural Networks and Learning Machines, New York: Prentice Hall, 2009.
Hornik, K., Some new results on neural network approximation, Neural Networks, 1993, vol. 6, no. 8, pp. 1069–1072. https://doi.org/10.1016/S0893-6080(09)80018-X
Kainen, P.C., Kůrková, V., and Sanguineti, M., Approximating multivariable functions by feedforward neural nets, Handbook on Neural Information Processing, Bianchini, M., Maggini, M., and Jain, L., Eds., Intelligent Systems Reference Library, vol. 49, Berlin: Springer, 2013, pp. 143–181. https://doi.org/10.1007/978-3-642-36657-4_5
Deryabin, V.V. and Sazonov, A.E., A vessel’s dead reckoning position estimation by using of neural networks, Proceedings of the Third International Scientific Conference “Intelligent Information Technologies for Industry” (IITI’18), Abraham, A., Kovalev, S., Tarassov, V., Snasel, V., and Sukhanov, A., Eds., Advances in Intelligent Systems and Computing, vol. 874, Cham: Springer, 2019, pp. 493–502. https://doi.org/10.1007/978-3-030-01818-4_49
Ebada, A., Intelligent techniques-based approach for ship maneuvering simulations and analysis (artificial neural networks application), PhD Dissertation, Duisburg: Inst. of Ship Technology und Transport Systems, 2007.
Knight, B. and Maki, K., Multi-degree of freedom propeller force models based on a neural network and regression, J. Marine Sci. Eng., 2020, vol. 8, no. 2, p. 89. https://doi.org/10.3390/jmse8020089
Kula, K.S., Model-based controller for ship track-keeping using neural network, IEEE 2nd Int. Conf. on Cybernetics (CYBCONF), Gdynia, Poland, 2015, IEEE, 2015, pp. 178–183. https://doi.org/10.1109/CYBConf.2015.7175928
Rajesh, G. and Bhattacharyya, S.K., System identification for nonlinear maneuvering of large tankers using artificial neural network, Appl. Ocean Res., 2008, vol. 30, no. 4, pp. 256–263. https://doi.org/10.1016/j.apor.2008.10.003
Skulstad, R., Li, G., Fossen, T.I., Vik, B., and Zhang, H., Dead reckoning of dynamically positioned ships: Using an efficient recurrent neural network, IEEE Rob. Autom. Mag., 2019, vol. 26, no. 3, pp. 39–51. https://doi.org/10.1109/MRA.2019.2918125
Woo, J., Park, J., Yu, C., and Kim, N., Dynamic model identification of unmanned surface vehicles using deep learning network, Appl. Ocean Res., 2018, vol. 78, pp. 123–133. https://doi.org/10.1016/j.apor.2018.06.011
Son, K. and Nomoto, K., On the coupled motion of steering and rolling of a high-speed container ship, Naval Archit. Ocean Eng., 1982, vol. 1981, no. 150, pp. 232–244. https://doi.org/10.2534/jjasnaoe1968.1981.150_232
Blendermann, W., Parameter identification of wind loads on ships, J. Wind Eng. Ind. Aerodynamics, 1994, vol. 51, no. 3, pp. 339–351. https://doi.org/10.1016/0167-6105(94)90067-1
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The author declares that he has no conflicts of interest.
About this article
Cite this article
Deryabin, V.V. The Assessment of Ship Drift on the Basis of a Neural Network. Aut. Control Comp. Sci. 56, 447–454 (2022). https://doi.org/10.3103/S0146411622050030
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411622050030