C-ShipGen: A Conditional Guided Diffusion Model for Parametric Ship Hull Design

TL;DR

C-ShipGen introduces a conditional diffusion model that incorporates designer-specified principal hull characteristics and uses gradients from a total-resistance regressor to steer sampling toward low-drag designs. Built on a large, diverse hull dataset, the approach pairs four regression models with a guided diffusion process to generate feasible hulls without retraining, achieving substantial drag reductions (>/=25%) relative to NSGA-II in five test cases while maintaining volume targets. The method enables rapid, diverse design exploration for early-stage ship design, though limitations arise for non-slender hulls and when high-fidelity hydrodynamics is required. Overall, C-ShipGen demonstrates a practical pathway to data-driven hull synthesis that can shorten design cycles and expand exploration of the hull-design space.

Abstract

Ship design is a complex design process that may take a team of naval architects many years to complete. Improving the ship design process can lead to significant cost savings, while still delivering high-quality designs to customers. A new technology for ship hull design is diffusion models, a type of generative artificial intelligence. Prior work with diffusion models for ship hull design created high-quality ship hulls with reduced drag and larger displaced volumes. However, the work could not generate hulls that meet specific design constraints. This paper proposes a conditional diffusion model that generates hull designs given specific constraints, such as the desired principal dimensions of the hull. In addition, this diffusion model leverages the gradients from a total resistance regression model to create low-resistance designs. Five design test cases compared the diffusion model to a design optimization algorithm to create hull designs with low resistance. In all five test cases, the diffusion model was shown to create diverse designs with a total resistance less than the optimized hull, having resistance reductions over 25%. The diffusion model also generated these designs without retraining. This work can significantly reduce the design cycle time of ships by creating high-quality hulls that meet user requirements with a data-driven approach.

Figures (10)

• Figure 1: C-ShipGen is a guided conditional diffusion model that generates hull designs with low resistance while maintaining the principal dimensions provided by the user during sampling. The model leverages guidance gradients from pre-trained regression models to improve the performance of the hulls.
• Figure 2: A selection of hulls from the Ship-D dataset, showing the variability possible with the hull parameterization. A random sampling from the dataset may lead to unrealistic hulls, containing combinations of features that do not resemble real-world ships and features that lead to poor performance.
• Figure 3: A selection of hulls generated with multi-objective guided performance generation. Notice the relative slenderness of the hulls leading to drastically reduced drag coefficients relative to the Ship-D dataset hulls.
• Figure 4: During training, the diffusion model predicts a denoising step, given a timestep embedding and a partially noised sample design vector. The model is informed by the input conditioning at each denoising step.
• Figure 5: Two-dimensional principal component analysis of the hull parameterization shows the relative distribution between dataset hull designs, diffusion-generated hull designs, and optimized hull designs for the supercarrier test case. The optimized hulls have much less design diversity than the diffusion-generated designs.