Dynamic Positional Attention Fusion (DPAF): Adaptive Encoding and Weighted Attention for Ship Motion Attitude Prediction

Enhanced accuracy and long-term predictions of ship motion during sea operations can effectively mitigate safety risks associated with aircraft takeoff and landing on board. This article proposes a transformer-based ship motion attitude prediction model. Our work leverages a novel self-attention mechanism (AM) with adaptive position encoding and learnable attention weights to improve long-term prediction accuracy. Furthermore, we also incorporate a pretraining phase using a random masking strategy to enhance the model's training capability and reduce prediction phase duration. The proposed model is evaluated using data from a ship undergoing constant speed and Z-word motion to predict the roll and pitch angles of the ship. The model is compared with autoregressive moving average (ARMA), EMD-ARMA, long-short-term memory (LSTM), bidirectional LSTM (Bi-LSTM), and traditional transformer models. The experimental results demonstrate that the proposed method outperforms these models in multistep prediction scenarios.