Recurrent-type Neural Networks for Real-time Short-term Prediction of Ship Motions in High Sea State
This work addresses ship motion prediction for maritime safety and operations, but it is incremental as it applies existing neural network methods to a specific domain.
The study tackled real-time short-term prediction of ship motions in high sea states using recurrent-type neural networks, achieving promising results for about 20-second ahead predictions with comparable performance across methods.
The prediction capability of recurrent-type neural networks is investigated for real-time short-term prediction (nowcasting) of ship motions in high sea state. Specifically, the performance of recurrent neural networks, long-short term memory, and gated recurrent units models are assessed and compared using a data set coming from computational fluid dynamics simulations of a self-propelled destroyer-type vessel in stern-quartering sea state 7. Time series of incident wave, ship motions, rudder angle, as well as immersion probes, are used as variables for a nowcasting problem. The objective is to obtain about 20 s ahead prediction. Overall, the three methods provide promising and comparable results.