MiDShip: Multimodal Dataset of Ship Cargo Hold Structures for Engineering Design

2026-09-04

AI Summary

This study addresses the scarcity of ship structural design data and the difficulty of satisfying regulatory constraints by introducing the first synchronized multimodal dataset encompassing geometric, drawing, and evaluation information. Furthermore, it proposes a generative design and rule verification framework that integrates Stochastic Gradient Langevin Dynamics (SGLD) sampling, equation-aware inpainting, large language model (LLM)-based code analysis, and parametric modeling. Experimental results demonstrate that the proposed approach achieves a design compliance rate of 79.4% while reducing regulatory violations by 97.1%. These findings indicate that the framework effectively facilitates the application of machine learning techniques in ship engineering, offering a robust solution for automated, regulation-compliant structural design.

Abstract

Ship structures govern vessel strength, safety, and manufacturability, but their design must satisfy hundreds of classification society requirements, making the process complex and iterative. Data-driven approaches are limited by the lack of structured datasets linking design geometry, structural performance, and rule-based constraints. This paper presents MiDShip, a multimodal dataset of 12,753 synthetic cargo-hold structural designs: 6,020 random, 496 generated by an SGLD-inspired procedure, and 6,237 generated by an equation-informed repair procedure. Each design includes parametric data, full and mesh-ready 3D geometry, engineering drawings and annotations, a bill of materials, and preliminary structural evaluations. Twenty-five constraints derived from a subset of ABS MVR are also evaluated. None of the random designs satisfies all constraints. Among the SGLD-inspired designs, 322 (64.9%) were fully compliant, with an average of 0.409 violations, 82.7% below the seed mean and 96.9% below the random-design mean. The repair procedure, developed through LLM-assisted code analysis, produced 4,952 fully compliant designs (79.4%), averaging 0.296 violations, 97.1% below the paired-source mean. In equal-size comparisons, mean nearest-neighbor distances in the scaled 120-parameter space were 3.495 for repaired designs, 1.144 for SGLD batches, and 3.729 for random designs. The primary contribution is the synchronized dataset and its generation and evaluation infrastructure; the generation studies demonstrate its utility rather than proposing new optimization algorithms. MiDShip supports machine learning, generative design, and automated rule-based evaluation for ship structures.

Problem

• ship structural design
• multimodal dataset
• classification society rules
• data-driven design
• structural constraints

Innovation

• Multimodal Dataset
• Generative Design
• Equation-informed Repair
• SGLD
• Rule-based Evaluation