Generative Design of Ship Propellers using Conditional Flow Matching

2026-01-29

AI Summary

This work addresses the challenge of efficiently generating diverse marine propeller designs that meet specific performance targets—a task where traditional methods often fall short. For the first time, conditional flow matching is introduced into inverse propeller design to establish a bidirectional mapping between design parameters and performance labels. By integrating vortex-lattice method simulations, a forward surrogate model, and a pseudo-label data augmentation strategy, the proposed framework enables the generation of multiple geometrically distinct propellers with highly consistent performance characteristics from sampled noise vectors alone. The approach significantly enhances both the diversity of generated designs and the controllability of their performance, thereby demonstrating the effectiveness and potential of generative AI in complex engineering inverse design problems.

Technology Category

• Natural Language Processing: Generation
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

In this paper, we explore the use of generative artificial intelligence (GenAI) for ship propeller design. While traditional forward machine learning models predict the performance of mechanical components based on given design parameters, GenAI models aim to generate designs that achieve specified performance targets. In particular, we employ conditional flow matching to establish a bidirectional mapping between design parameters and simulated noise that is conditioned on performance labels. This approach enables the generation of multiple valid designs corresponding to the same performance targets by sampling over the noise vector. To support model training, we generate data using a vortex lattice method for numerical simulation and analyze the trade-off between model accuracy and the amount of available data. We further propose data augmentation using pseudo-labels derived from less data-intensive forward surrogate models, which can often improve overall model performance. Finally, we present examples of distinct propeller geometries that exhibit nearly identical performance characteristics, illustrating the versatility and potential of GenAI in engineering design.

Problem

• Generative Design
• Ship Propellers
• Conditional Flow Matching
• Performance Targets
• Generative AI

Innovation

• Generative AI
• Conditional Flow Matching
• Propeller Design
• Data Augmentation
• Surrogate Modeling