Multi-Objective Optimization Data for Variable Thickness Hybrid Composite Laminates

Han Wang published a dataset on figshare in 2026, associated with a paper proposing a multi-objective optimization framework. The dataset likely contains simulation and optimization results for variable thickness hybrid composite laminates, with a total size of 22.8 MB. The framework combines a back-propagation neural network trained on finite element simulation data with a non-dominated sorting genetic algorithm.

Use Cases

• Benchmarking multi-objective optimization algorithms based on the described framework for composite laminate design.
• Training surrogate models like neural networks based on the finite element simulation data mentioned in the description.
• Analyzing trade-offs between manufacturing cost, structural performance, and dynamic characteristics for composite structures.
• Validating stacking-sequence generation methods for multi-region, multi-material laminates.

Strengths

• The associated research paper describes a validated framework tested on an eighteen-region horseshoe-shaped laminate.
• The dataset is licensed under CC-BY-4.0, allowing for open sharing and modification.
• The total file size is 22.8 MB, which is manageable for download and local processing.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for large-scale model training.
• The dataset includes files in TIF, DOCX, and JPG formats, suggesting the core data may be embedded in documents or images rather than a clean tabular structure.

Provenance

Source

figshare, author Han Wang

Collection Method

Likely generated from finite element simulations and algorithmic optimization as described in the associated paper.

Freshness

Last updated 2026-05-23 16:06:16; freshness should be verified.