Enhancing motion forecasting of ship sailing in irregular waves based on optimized LSTM model and principal component of wave-height

Irregular waves exhibit complex and erratic behavior, posing significant challenges for accurate short-term ship motion forecasting. Reliable ship navigation depends on precise motion predictions, necessitating effective feature extraction from wave data to enhance predictive models. This study proposes a hybrid model integrating a wavelet principal component analysis (WPCA) for dimensionality reduction with an optimized double circulation-long short-term memory (DC-LSTM) network. The WPCA method retains key variance components, reducing redundant data while preserving critical wave characteristics. The DC-LSTM model is optimized using both internal and external circulation mechanisms to enhance learning efficiency and stability. Numerical simulation data are used to train and validate the model. Compared with conventional LSTM and PCA-LSTM models, the proposed WPCA-DC-LSTM model improves R 2 by 14% and reduces RMSE by 12% in validation datasets. The model demonstrates robust generalization, effectively capturing nonlinear and high-dimensional wave features. The results indicate that the hybrid model effectively mitigates the influence of redundant data, reduces prediction randomness, and improves stability in handling wave-induced ship movements. The study highlights the broad applicability of the WPCA-DC-LSTM model for complex maritime data analysis and ship motion forecasting.