A new system identification scheme based on model reference and random forest(RM-RF), was used to model ship maneuvering. First, the scheme establishes the relationship between a ship and the RM using the similarity rule. Second, a suitable RM was selected from public ship maneuvering models to avoid the tuning process in the empirical Maneuvering Modeling Group(MMG) model. Third, RF creates a relationship to map accelerations between the ship and the RM. Finally, the study case was implemented with fewer free running model test data. The results show the feasibility of the identification modeling scheme and validated the generalizability of the proposed approach.

Aiming at the poor accuracy and difficult verification of maneuver modeling induced by the wind, waves and sea surface currents in the actual sea, a novel sea trials correction method for ship maneuvering is proposed. The wind and wave drift forces are calculated according to the measurement data. Based on the steady turning hypothesis and pattern search algorithm, the adjustment parameters of wind, wave and sea surface currents were solved, the drift distances and drift velocities of wind, waves and sea surface currents were calculated and the track and velocity data of the experiment were corrected. The hydrodynamic coefficients were identified by the test data and the ship maneuvering motion model was established. The results show that the corrected data were more accurate than log data, the hydrodynamic coefficients can be completely identified, the prediction accuracy of the advance and tactical diameters were 93% and 97% and the prediction of the maneuvering model was accurate. Numerical cases verify the correction method and full-scale maneuvering model. The turning circle advance and tactical diameter satisfy the standards of the ship maneuverability of International Maritime Organization (IMO).

As the nonlinear and coupling characteristics of autonomous underwater vehicles (AUVs) are the challenges for motion modeling, the nonparametric identification method is proposed based on dung beetle optimization (DBO) and deep temporal convolutional networks (DTCNs). First, the improved wavelet threshold is utilized to select the optimal threshold and wavelet basis functions, and the raw model test data are denoising. Second, the bidirectional temporal convolutional networks, the bidirectional gated recurrent unit, and the attention mechanism are used to achieve the nonlinear nonparametric model of the AUV motion. And the hyperparameters are optimized by the DBO. Finally, the lazy-search-based path planning and the line-of-sight-based path following control are used for the proposed AUV model. The simulation shows that the prediction accuracy of the DBO-DTCN is better than other artificial intelligence methods and mechanical models, and the path following of AUV is feasible. The methods proposed in this paper can provide an effective strategy for AUV modeling, searching, and rescue cruising.

In ice-covered waters, ships may pass through narrow ice channels, where the interactions with the intact ice along the channel boundaries differ from those under level ice conditions. To investigate this problem, numerical simulations of a steel plate impacting on conical sea ice were first conducted to verify a constitutive model developed for ice. Subsequently, based on an explicit dynamic formulation, a coupled ship–ice–water interaction model was developed using an arbitrary Lagrangian– Eulerian algorithm for the fluid–structure interaction. This numerical approach was validated through comparison with the results of ice tank model tests in terms of ice failure patterns and icebreaking resistance, which confirmed the applicability of the proposed model. On this basis, a series of simulations was carried out to examine the icebreaking behaviour of a ship in a narrow channel with varying widths, ship speeds and ice thicknesses. The results showed that the icebreaking resistance in an extremely narrow channel is lower than under level ice conditions, and that the occurrence of lateral cracks is associated with a reduction in resistance. As the channel width was increased, the variation in the resistance became less pronounced. In addition, icebreaking resistance increased with ship speed and ice thickness, and this trend became more evident under confined channel conditions. The findings of this study contribute to the evaluation of ship performance in narrow ice channels and provide reference information for engineering applications in ice-covered waters.

With global warming enhancing the navigability of Arctic routes, the accurate prediction of ice resistance during navigation is of great engineering significance for the design and performance evaluation of polar ships. This study proposes a high-fidelity numerical simulation method that combines image recognition with CFD–DEM coupling and a six-degree-of-freedom (6-DOF) dynamic model to predict ship resistance in pack ice conditions. Using ice images from the CEHINAV towing tank experiments in Spain, the watershed image segmentation algorithm was applied to extract the spatial distribution and size information of ice blocks. A digital ice field was then reconstructed by surface injection of ice fragments of various sizes, thereby achieving consistency with the physical ice field. In the fluid–structure interaction simulations, a dynamic overset mesh and 6-DOF motion model were introduced to realistically reproduce the ship’s motion and the ship–ice interactions in the pack ice zone. Numerical simulations under different speeds and ice concentrations show that the average deviation from experimental data remains within 10%, thus confirming the accuracy and reliability of the proposed method. The results indicate that the bow region is the main area of ice loading and resistance concentration, with resistance increasing significantly as the ice concentration rises. The resistance curves exhibit evident nonlinear fluctuations and unloading phenomena. Further regional analysis reveals that the transverse resistance distribution along the hull gradually decreases from the midship toward both sides, while local regions exhibit transient fluctuations, a finding that highlights the complex and unsteady characteristics of ship–ice interactions.