Combining the bidirectional long short-term memory neural network and temporal pattern attention mechanism, a machine learning model based on multi-feature inputs is developed to predict ship motion in irregular waves. An adaptive particle swarm optimisation algorithm is proposed to adapt the parameters of neural network to different feature inputs. The study indicates that the improved particle swarm optimisation algorithm avoids the problem of poor adaptability of empirical parameters to different advance time. The combination of bidirectional long short-term memory neural network and temporary pattern attention mechanism further enhances the data mining ability. Compared with the prediction mode solely based on the ship motion input, the inclusion of wave elevation input can effectively improve the accuracy and advance time for ship’s motion prediction. Importantly, the prediction accuracy will improve with an increased number of inputs of wave probes, which are arranged along the wave propagation direction.
An APSO-based TPA-BLSTM model for predicting ship motion in irregular waves using wave-series input
SHIPS AND OFFSHORE STRUCTURES
J. XUE ET AL.
Ships and Offshore Structures ; 20 , 3 ; 372-383
2025-03-04
12 pages
Article (Journal)
Electronic Resource
English
Ship Track Prediction Based on Sliding Window BLSTM Network
Springer Verlag | 2023
|A Linear Theory of Ship Motion in Irregular Waves
NTIS | 1953
|Difference in ship motion and wave load in long and short crested irregular waves
DOAJ | 2023
|Ship Resistance in Irregular Waves
NTIS | 1969
|