Ship-D: Ship Hull Dataset for Design Optimization using Machine Learning

TL;DR

This paper introduces a large, detailed ship hull dataset and demonstrates its use in machine learning for optimizing ship design, significantly reducing hydrodynamic drag while preserving hull shape.

Contribution

It provides the first extensive publicly available ship hull dataset with diverse representations and performance data, enabling machine learning applications in ship design optimization.

Findings

Developed a dataset of 30,000 ship hulls with detailed design and performance data.

Created a surrogate model to predict hydrodynamic drag coefficients with high accuracy.

Achieved a 60% reduction in hull drag using a genetic algorithm guided by the surrogate model.

Abstract

Machine learning has recently made significant strides in reducing design cycle time for complex products. Ship design, which currently involves years long cycles and small batch production, could greatly benefit from these advancements. By developing a machine learning tool for ship design that learns from the design of many different types of ships, tradeoffs in ship design could be identified and optimized. However, the lack of publicly available ship design datasets currently limits the potential for leveraging machine learning in generalized ship design. To address this gap, this paper presents a large dataset of thirty thousand ship hulls, each with design and functional performance information, including parameterization, mesh, point cloud, and image representations, as well as thirty two hydrodynamic drag measures under different operating conditions. The dataset is structured to allow human input and is also designed for computational methods. Additionally, the paper introduces a set of twelve ship hulls from publicly available CAD repositories to showcase the proposed parameterizations ability to accurately reconstruct existing hulls. A surrogate model was developed to predict the thirty two wave drag coefficients, which was then implemented in a genetic algorithm case study to reduce the total drag of a hull by sixty percent while maintaining the shape of the hulls cross section and the length of the parallel midbody. Our work provides a comprehensive dataset and application examples for other researchers to use in advancing data driven ship design.