Traditional numerical simulation methods based on hydrodynamics for calculating ship parametric roll encounter challenges such as high computational costs, demanding operational requirements, and limited coverage of loading conditions. To address these issues, this study proposes an integrated machine learning surrogate model that combines feature physicalization reconstruction, agglomerative hierarchical clustering (AHC), and an improved random forest (RF) algorithm for efficient prediction of ship parametric roll amplitude.

AHC is utilized to compress feature dimensions, thereby reducing model complexity and computational cost, while particle swarm optimization (PSO) is employed for global optimization of RF hyperparameters.

The validation results based on hydrodynamic numerical simulation data under multiple operating conditions of a large container ship indicate that, compared to the generalized regression neural network (GRNN) and the unoptimized RF model, the proposed model (AHC–PSO–RF) shows an average improvement of 5.84% and 0.27% in the coefficient of determination (R²) and an average reduction of 59.28% and 10.69% in the root mean square error (RMSE) when predicting roll amplitudes under head and following seas in two wave directions, indicating superior prediction accuracy. And the average calculation time per loading condition is reduced by 84.5% compared to the hydrodynamic numerical simulation method, offering significant efficiency advantages in batch prediction tasks.

These results confirm the model's practical engineering value as an efficient alternative solution.

The purpose of this study is to investigatethe safety risk of dynamic stability in waves of coastal sea-going ships in domestic waters by evaluating parametric roll, pure loss of stability and synchronous roll, based on the second generation intact stability assessment method for domestic ships.

The Froude−Krylov assumption and free trim method are used to calculate the righting levers and stability characteristics in waves, simplified nonlinear motion equations and frequency-domain motion equation based on hydrodynamics are used to obtain the time/ frequency domain results of roll amplitude and acceleration of parametric and synchronous roll, and the stability characteristics are used to evaluate pure loss of stability. Finally the risk probabilities of three failure modes are obtained based on the probability of sea-states.

The study shows that the typical ship types may be vulnerable to pure loss of stability and synchronous roll, and assessment results of dynamic stability safety level in waves are generally consistent with the accident and investigation results.

There is a risk of dynamic stability accidents in waves for typical Chinese coastal sea-going ship types. It is suggested that in the optimization of ship design, ship operation and sailing under adverse sea conditions, maritime supervision and accident investigation, special attention should be paid to the above safety level and accident risk assessment results.