Search

To investigate the parametric rolling motion of container ships navigating in head seas, this study utilizes the unsteady RANS approach combined with dynamic overlapping grid technology to simulate parametric roll in a container ship under the coupled motions of roll, pitch, and heave. Initially, the model was validated against experimental results, demonstrating good agreement and thus confirming the reliability of the computational method. Furthermore, the paper investigates the impacts of the initial roll angle, encounter frequency, and the addition of bilge keels on parametric rolling. The research findings indicate that the initial angles of rolling impact the duration needed to attain a steady roll condition, yet they have minimal effect on the amplitude post-stabilization. The likelihood of parametric rolling arises when the frequency of encounters doubles that of the ship’s inherent roll frequency. Furthermore, the likelihood of parametric rolling escalates when the wavelengths approach the length of the ship. Installing bilge keels markedly reduces the parametric rolling movement in vessels, and the occurrence of parametric rolling is also delayed.

Designing a ship hull to keep the hydrodynamic performance meet the requirements is an indispensable step in the ship's preliminary design. However, in the traditional design process, the design workload is labor-intensive and time-consuming due to the need to estimate a large number of design schemes. To address this issue, this work developed a Neural Network Proxy Model (NNPM) to assist the hydrodynamic resistance prediction for the ship hull design process. The data used in the NNPM construction was supported by two Computational Fluid Dynamic (CFD) methods with different fidelity where the low-fidelity one for tuning and pre-training, and the high-fidelity one for fine-training. To mitigate the risk of overfitting stemming from disparities in data volumes, the parameter freezing strategy is adopted during the high-fidelity dataset-based fine-training. The results obtained from validation numerical experiments indicated that the NNPM exhibited a forecast error of less than 1% when compared to the high-fidelity CFD method. Importantly, this high accuracy is achieved while maintaining a low construction workload, demonstrating the potential of Artificial Intelligence (AI) to predict the hydrodynamic load of hulls in the ship's preliminary design, which can further advance the artificial intelligence-assisted design (AIAD) technology for various marine structures. [ABSTRACT FROM AUTHOR]

Based on the potential flow theory and traditional boundary element method (BEM), Taylor expansion boundary element method (TEBEM) is introduced in this paper for the prediction of the flow field around ship, as a result, hull gesture and pressure distribution on hull surface are obtained. By this method, dipole strength of every field point is expanded in Taylor expansion, so that approximately continuous hull and free surface boundary condition could be achieved. To close the new equation system, the boundary condition of tangent velocity in every control point is introduced. With the simultaneous solving of hull boundary condition and free surface condition, the disturbance velocity potential could be obtained. The present method is used to predict the flow field and hull gesture of Wigley parabolic hull, Series 60 and KVLCC2 models. To validate the numerical model for full form ship, the wave profile, the computed hull gesture and hull surface pressure of KVLCC2 model are compared with experimental results.

The stability of navigation in waves is crucial for ships, and the effect of the waves on navigation stability is complicated. Hence, the LSTM neural network technique is applied to predict the course changing of a ship in different wave conditions, where K-means clustering analysis is used for the category of the ship's navigation data to improve the quality of the database. In this paper, the effect of the initial database obtained by the K-means clustering analysis on prediction accuracy is studied first. Then, different input features are used to establish the database to train the neural network, and the influence of the database by different input features on the accuracy of the navigation prediction is discussed and analyzed. Finally, multi-task learning is used to make the neural network better predict the navigation in various wave conditions. Using the improved neural network model, the course of an autopilot ship in waves is predicted, and the results show that the current database and the neural network model are accurate enough for the course prediction of the autopilot ship in waves. [ABSTRACT FROM AUTHOR]