Diez-Pascual, Ana María published a dataset on 2025-10-14 via e-cienciaDatos Harvested Dataverse. The data likely contains experimental results for poly(butylene succinate-co- butylene adipate) nanocomposites with functionalized single-walled carbon nanotubes. Four machine learning algorithms were applied to predict mechanical properties from the experimental characterization.
Use Cases
- Predicting nanocomposite stiffness based on SWCNT percentage and ultrasonication parameters.
- Modeling the relationship between material composition and tensile strength.
- Training regression algorithms to forecast impact strength from thermal and spectroscopic analysis data.
- Optimizing material processing conditions (amplitude and time) for desired mechanical performance.
Strengths
- Experimental data includes characterization by SEM, Infrared spectroscopy, TGA, DSC, tensile, and impact tests.
- Reports an unprecedented stiffness increase of 114% for a specific nanocomposite formulation.
- Applies four machine learning algorithms to predict mechanical properties with reported good correlation.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
Provenance
- Source
- Diez-Pascual, Ana María via e-cienciaDatos Harvested Dataverse.
- Collection Method
- Experimental data from nanocomposite synthesis, characterization, and subsequent ML modeling.
- Time Range
- null
- Freshness
- Last updated 2025-10-14 21:31:52; freshness should be verified.
- Geography
- null