A Novel Ship Design Optimization Framework Using Fine-Tuned and Reward-Directed Diffusion Model

Abstract Optimizing ship hull design using existing datasets poses significant challenges in the marine industry. This study presents an innovative framework for generative artificial intelligence (AI) that uses fine-tuned and reward-weighted sampling during inference in a diffusion model to generate ship hull designs with reduced resistance. We use a parametric approach for the design representation of the ship hull and apply the developed framework to generate new parameters that represent a hull with reduced resistance. Empirical results indicate that the reward guidance substantially improves the diffusion model’s ability to produce samples with reduced resistance in ship design generation tasks. A specific advantage of the reward-directed approach is its effectiveness when engineering simulations are needed to compute performance metrics, such as resistance. This makes the objectives non-differentiable and thus challenging for traditional gradient-based optimization techniques. We first show that the diffusion model can generate 3D ship designs within complex simulation environments. Then, we demonstrate that our framework successfully generates high-performance ship designs that meet engineering criteria directly from tabular data. This work introduces the use of reward guidance for a Markov decision process (MDP), providing an intuitive approach to provide directional sampling in diffusion models, particularly in complex and nondifferentiable settings. This study is a steppingstone towards constrained-based design optimization using generative AI for engineering applications. Using this approach, performance and operational considerations will be embedded in the optimization process during sampling and reward augmentation.