Over 60,000 stationary 3D flow fields simulated for diverse electronics cooling geometries using Simcenter STAR-CCM+. This dataset, created by bgce, provides a large-scale library for machine learning tasks in computational fluid dynamics. Documentation is hosted at cooldata.readthedocs.io.
Use Cases
- Training surrogate models for fluid simulation based on 3D flow field data.
- Developing generative models for cooling system design based on diverse geometry inputs.
- Benchmarking machine learning algorithms for computational fluid dynamics tasks.
- Analyzing flow patterns and heat transfer in electronics cooling systems.
Strengths
- Contains over 60,000 data points, providing a substantial scale for training.
- Simulated with a commercial solver, Simcenter STAR-CCM+, suggesting a degree of industrial relevance.
- Focuses on a diverse set of geometries, which may increase model generalization.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
- Last updated 2026-05-06 22:54:39; freshness should be verified.
Provenance
- Source
- bgce
- Collection Method
- Simulated with the commercial solver Simcenter STAR-CCM+.