|
|
Publications
Araújo, J.P., Moreira, L. and Guedes Soares, C. (2021), “Modelling ship manoeuvrability using Recurrent Neural Networks”, Developments in Maritime Technology and Engineering, Guedes Soares, C. & Santos T.A., (Eds.), Taylor and Francis, London, UK, Vol 2, pp. 131-140.
Recurrent Neural Networks are used to learn a ship’s manoeuvrability behaviour from experimental data obtained from tests with a scale model. The goal of the study is to assess the performance of ship manoeuvrability models developed using Recurrent Neural Networks trained with low amounts of noisy experimental data from zig zag and circle tests, performed according to the IMO standards. Due to the small size of the ship model, wind interference was noticeable in all recorded tests. Two models were trained, one to predict zig zag manoeuvres, and another one to predict circle manoeuvres.
If you did not manage to obtain a copy of this paper: Request a copy of this article
For information about all CENTEC publications you can download: Download the Complete List of CENTEC Publications
|