A data-driven approach for the preliminary design of ship hull forms has been proposed to address the issues of long design cycles and high manual effort in traditional ship hull form design methods. By focusing on the digital representation of hull lines, database construction, and data storage, classification and retrieval, a method for constructing a hull form database is proposed to enable the visualization of functionalities such as adding, deleting, viewing, modifying, and matching of hull lines. To fully utilize the existing data in the database, a feature extraction function for hull lines is developed. This function segments the ship hull surface and calculates the normal vector, Gaussian curvature and mean curvature of the hull surface, thereby facilitating dimensionality reduction of the hull surface features. A convolutional neural network is then employed with the reduced-dimensional features as inputs to predict the ship resistance in static water. Experimental results show that the database can effectively manage the data of the ship hull form, and the error of the total ship resistance coefficient predicted by the neural network is within 10%. This work enables the inheritance of high-quality data into the preliminary hull form design of new ship types.

Fire compartmentation is one of the most important and complicated ship general design work, especially for the passenger ships, such as the cruise ship and Ropax with large number of rooms. The traditional design method, which is based on two-dimensional (2D) drawings and human subjective judgement, costs heavy workload and is likely to induce mistakes. A three-dimensional (3D) assisted fire compartmentation method for ship cabins has been proposed based on the secondary development of the 3D modelling software UG through the programming analysis of the specification requirement logics. This method embeds the relevant knowledge requirements of the fire protection rules. It fulfils the functions of customizing the categories of the ship cabins, automatically creating the common interface of adjacent cabins, and automatically setting the common interface’s fire protection level, which is highlighted in different colors, according to the regulations. It also counts the usage of different fire protection levels, which can lay the foundation for helping the designers to optimize the cabin arrangement based on the objective of reducing fire protection materials.

The modelling of type-A tanks of a liquefied gas carrier is complicated and highly coupled with the principal dimension, hull lines and target cabin capacity. A parametric modelling based subdivision optimization design method for the type-A tank of a liquefied gas carrier (Parametric Optimization Method for Subdivision of type-A tanks, POMSA) has been proposed to improve the efficiency of the overall optimization design of the type-A tank of a liquefied gas carrier. The key technology of this method is the parametric modeling based on the NAPA platform.The typical midsection shape, the longitudinal position of the main transverse bulkhead and the angle of the inner hull are parametrically modelled and regarded as design variables in this paper.The principal dimension, hull lines and the initial general arrangement are taken as input. The requirements of the tank location from IGC, the minimum side length of the tank from the construction process, the target cabin capacity, the propeller immersion and the vision requirement of the ballast water are used as constraints for POMSA. The maximum cabin capacity is taken as the optimization design objective. The optimization model is solved by the optimization mathematical modelling of an exploratory global optimization algorithm (Non-dominated Sorting Genetic Algorithm-II, NSGA-II) together with a local fast convergence optimization algorithm (Hooke-Jeeves direct search method). It is proved that the optimization iteration of this method is efficient, which will facilitate the fast response at the early design stage of the overall design.