Design-Space Dimensionality Reduction Benchmark Dataset – DTMB 5415 Hull

Read full text Summarise with VIRAT
Authors: Andrea Serani, Matteo Diez
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This dataset provides a benchmark database for the evaluation and comparison of design-space dimensionality reduction methods in hydrodynamic shape optimization problems. The dataset consists of 9,001 configurations of the DTMB 5415 hull geometry generated through Monte Carlo sampling of a nonlinear parametric model based on global three-dimensional shape modifications. Each configuration is described by 27 design variables defining perturbations of the reference hull geometry. The hull surface is discretized using 2,250 points, stored as flattened coordinate vectors. Each configuration includes: discretized hull geometry coordinates (2,250 × x, y, z points) normalized design variables defining the parametric model pressure distribution on the hull evaluated at 2,250 surface points wave elevation field evaluated on a structured grid (1,500 points) integrated hydrodynamic quantities: wave resistance coefficient (Cw) RMS vertical acceleration at the bridge (az) RMS pitch motion (xi5) Hydrodynamic quantities are computed using low-fidelity solvers: WARP (linear potential flow) for calm-water resistance SMP (linear strip theory) for seakeeping Simulation conditions: head waves sea state 5 Bretschneider spectrum Froude numbers: 0.25, 0.33, 0.41 The dataset combines model-scale and full-scale representations: geometry is provided at full scale (Lpp = 142 m) seakeeping quantities are evaluated at full scale calm-water quantities (resistance, pressure, wave elevation) are computed at model scale (Lpp = 5.720 m) All design variables are provided in normalized form within the interval [-1,1]. Dataset statistics: total configurations: 9001 baseline configuration: 1 (DTMB 5415 reference hull) sampled configurations: 9000 invalid simulations: 0 All configurations included in the dataset correspond to physically valid simulations. A larger number of samples was initially generated, and only those yielding valid physical responses were retained. This dataset is part of a benchmark collection aimed at providing standardized databases for evaluating dimensionality reduction techniques in engineering design spaces. The dataset follows a physics-informed representation of the design space, where geometric, parametric, and physical information are combined consistently within a unified framework. The parametrization and solvers used are described in: Serani, A., Palma, G., Wackers, J., Quagliarella, D., Gaggero, S., & Diez, M. (2025). Extending parametric model embedding with physical information for design-space dimensionality reduction in shape optimization. Engineering with Computers. Serani, A., Stern, F., Campana, E. F., & Diez, M. (2022). Hull-form stochastic optimization via computational-cost reduction methods. Engineering with computers, 38(Suppl 3), 2245-2269.

Fields of Study & Subjects

Ship Hydrodynamics and Maneuverability Model Reduction and Neural Networks Advanced Multi-Objective Optimization Algorithms

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
25 March 2026
Language
EN
Document type
Dataset