mlsanityData to 14 Oct 2026

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

arXiv 2610.02214 ↗First posted 4 Sep 2026cs.CE cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 68 references that are in the map. First posted on arXiv 4 Sep 2026.

Builds on

16 of 68 references.

References · 16

  1. 2018Datasheets for Datasetscited by 1,386
  2. 2024DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarkscited by 75
  3. 2023From Concept to Manufacturing: Evaluating Vision-Language Models for Engineering Designcited by 51
  4. 2024DrivAerNet: A Parametric Car Dataset for Data-Driven Aerodynamic Design and Predictioncited by 33
  5. 2024DesignQA: A Multimodal Benchmark for Evaluating Large Language Models' Understanding of Engineering Documentationcited by 32
  6. 2021BIKED: A Dataset for Computational Bicycle Design with Machine Learning Benchmarkscited by 27
  7. 2023Ship-D: Ship Hull Dataset for Design Optimization using Machine Learningcited by 13
  8. 2022FRAMED: An AutoML Approach for Structural Performance Prediction of Bicycle Framescited by 11
  9. 2023ShipHullGAN: A generic parametric modeller for ship hull design using deep convolutional generative modelcited by 11
  10. 2023ShipGen: A Diffusion Model for Parametric Ship Hull Generation with Multiple Objectives and Constraintscited by 11
  11. 2023DATED: Guidelines for Creating Synthetic Datasets for Engineering Design Applicationscited by 6
  12. 2025A Multi-Stage Hybrid Framework for Automated Interpretation of Multi-View Engineering Drawings Using Vision Language Modelcited by 6
4 more
  1. 2025Automated Parsing of Engineering Drawings for Structured Information Extraction Using a Fine-tuned Document Understanding Transformercited by 3
  2. 2023Designing ship hull forms using generative adversarial networkscited by 2
  3. 2023A Comprehensive End-to-End Computer Vision Framework for Restoration and Recognition of Low-Quality Engineering Drawingscited by 2
  4. 2024BIKED++: A Multimodal Dataset of 1.4 Million Bicycle Image and Parametric CAD Designscited by 2

Built on by

Not cited yet.